Hong Huang, Decheng Wu, Qiangqiang Hu, Guanghua Yu, Jinhai Yang, Jianchen Zhu, Xue Liu, Dapeng Wu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Hao Wang, Hao Gu, Hongming Piao, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue, Sirui Han, Yike Guo, Dapeng Wu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Integrated sensing and communication (ISAC) has emerged as a transformative paradigm, merging the capabilities of sensing and communication to enhance efficiency and enable advanced applications. Mobile crowdsensing (MCS), as a important example of ISAC, leverages unmanned vehicles such as UAVs to continuously gather and transmit environmental data, supporting critical applications like traffic monitoring, urban congestion management, and accident investigation. In this paper, we focus on multi-task-oriented UAV crowdsensing (UCS), where diverse tasks—such as surveillance and emergency response—each have distinct age-of-information (AoI) requirements. We introduce a novel metric, the “valid task handling index,” to evaluate the performance of handling multiple tasks effectively. Our proposed hierarchical multi-agent deep reinforcement learning (MADRL) framework, DRL-MTUCS, integrates seamlessly with multi-agent actor-critic reinforcement learning methods. It features dynamically weighted queues for UAV goal assignment, enabling efficient management of multiple emergency tasks, and a low-level UAV execution module with a self-balancing intrinsic reward mechanism. This ensures all tasks are completed within their individual AoI constraints. Extensive experiments and trajectory visualizations validate the superior performance and robustness of DRL-MTUCS compared to six baselines across varying conditions, including the number of UAVs, surveillance task AoI thresholds, and emergency task image blur requirements.

Traditional unimodal sensing faces limitations in accuracy and capability, and its decoupled implementation with communication systems increases latency in bandwidth-constrained environments. Additionally, single-task-oriented sensing systems fail to address users’ diverse demands. To overcome these challenges, we propose a semantic-driven integrated multimodal sensing and communication (SIMAC) framework. This framework leverages a joint source-channel coding architecture to achieve simultaneous sensing, decoding, and transmission of sensing results. Specifically, SIMAC first introduces a multimodal semantic fusion (MSF) network, which employs two extractors to extract semantic information from radar signals and images, respectively. MSF then applies cross-attention mechanisms to fuse these unimodal features and generate multimodal semantic representations. Secondly, we present a large language model (LLM)-based semantic encoder (LSE), where relevant communication parameters and multimodal semantics are mapped into a unified latent space and input to the LLM, enabling channel-adaptive semantic encoding. Thirdly, a task-oriented sensing semantic decoder (SSD) is proposed, in which different decoded heads are designed according to the specific needs of tasks. Simultaneously, a multi-task learning strategy is introduced to train the SIMAC framework, achieving diverse sensing services. Finally, experimental simulations demonstrate that the proposed framework achieves diverse and higher-accuracy sensing services.

Human cognitive mechanism depends on a sophisticated information processing framework, including perception, attention, memory, language, reasoning, problem solving and decision-making. However, current research only focuses on isolated process rather than systematically simulating human cognitive mechanism. Meanwhile, with the rapid development of large language models, related works have predominantly centered on language-level exploration, while in-depth mining of visual information remains insufficient. Here, to deeply activate the multi-modal understanding ability, a Systematic Human-like Cognitive (SHC) method is proposed for visual question answering, where the above mentioned sophisticated seven processes are systematically modeled as three core modules: hierarchical perception, semantic refinement and dynamic reasoning. The Hierarchical Perception Module (HPM) extracts hierarchical features from different levels to simulate the incremental integration mode of biological neural system. Based on the selective attention theory, one Semantic Refinement Module (SRM) is designed as a key-value accumulation optimization mechanism that enhances high-level semantics from low-level features via a multi-level cascaded attention structure. Finally, the Dynamic Reasoning Module (DRM), following the utility maximization decision theory, employs a dual weighting mechanism to dynamically fuse high-level semantic features and low-level fine-grained features, forming a unified high-quality visual representation that is then fed into the large language model for reasoning together with the text input. Experimental results demonstrate that SHC achieves competitive performance on multiple visual question answering benchmarks, including VQA-v2, Text-VQA, GQA, and ScienceQA, as well as multimodal evaluation benchmarks such as POPE, MMB, MME, and MM-Vet. Comparative experiments with multiple models of the same-scale validate the latent capacity of SHC to prompt the performance of multi-modal understanding tasks and its superiority in fine-grained visual information perception, and even surpasses multimodal models with larger-scale on certain tasks.

Scene Graph Generation (SGG) is a critical cross-modal task for scene understanding, which aims to detect visual relations in an image. Most SGG methods are significantly affected by highly skewed long-tailed bias, and prefer predicates with sufficient samples regardless of the semantic accuracy. Current unbiased SGG methods focus on compensating for the imbalanced long-tailed distribution, but they are fragile to dataset changes. The fundamental cause for this problem is the limited generalization ability, thus the diversity of classes needs to be modeled explicitly. By imitating the human cognition, a Grounded Cognition Method (GCM) for unbiased scene graph generation is proposed here, where the simulation, bodily states, and situated action are modeled. For simulations, an Out Domain Knowledge Injection module is proposed to expand the model's visual perception by reducing the reliance on an isolated class. Meanwhile, a Semantic Group Aware Synthesizer is proposed for linguistic perception modeling by categorizing specific predicate classes into a high-level semantic group. For bodily states, the modalities are erased separately to imitate the limited state of physical senses, which forces the model to rely on the remaining modality to compensate for the understanding of the whole scene. For situated actions, a Shapley Enhanced Multimodal Counterfactual module is proposed to model the dynamic interaction with the environment and cope with diverse contexts. Experiments on Visual Genome, GQA, and Open Images V6 demonstrate the effectiveness of our GCM, which outperforms state-of-the-art methods and achieves a better trade-off.

To address the complexities of spatial non-stationary (SnS) effects and spherical wave propagation in near-field channel estimation (CE) for extremely large-scale multiple-input multiple-output (XL-MIMO) systems, this paper proposes an SnS-aware CE framework based on adaptive subarray partitioning. We first investigate spherical wave propagation and various SnS characteristics and construct an SnS near-field channel model for XL-MIMO systems. Due to the limitations of uniform subarray patterns in capturing SnS, we analyze the adverse effects of the non-ideal array segmentation (over- and under-segmentation) on CE accuracy. To counter these issues, we develop a dynamic hybrid beamforming-assisted power-based subarray segmentation paradigm (DHBF-PSSP), which integrates power measurements with a dynamic hybrid beamforming structure to enable joint subarray partitioning and decoupling. A power-adaptive subarray segmentation (PASS) algorithm leverages the statistical properties of power profiles, while subarray decoupling is achieved via a subarray segmentation-based sampling method (SS-SM) under radio frequency (RF) chain constraints. For subarray CE, we propose a subarray segmentation-based assorted block sparse Bayesian learning algorithm under the multiple measurement vectors framework (SS-ABSBL-MMV). This algorithm exploits angular-domain block sparsity under a discrete Fourier transform (DFT) codebook and inter-subcarrier structured sparsity. Simulation results confirm that the proposed framework outperforms existing methods in CE performance.

Radio frequency (RF) signals have gained widespread adoption in intelligent perception systems due to their unique advantages, including non-line-of-sight propagation capability, robustness in low-light environments, and inherent privacy preservation. However, their substantial data volumes, generated by the dual-polarization direction characteristic, result in significant challenges to data storage and transmission. To address this, we propose the first end-to-end deep dynamic RF signal compression (DRFC) framework, which primarily focuses on exploiting cross-directional correlation in dynamic RF signals. The proposed framework incorporates four key innovations: (1) a mask-guided RF motion estimation module that leverages Doppler shifts and electromagnetic noise characteristics to identify regions of significant motion using a threshold-based mask, significantly improving motion estimation accuracy; (2) a cross-directional RF motion entropy model that utilizes cross-directional RF motion latent priors to refine the probability distribution for motion entropy coding; (3) a cross-directional RF context mining module that predicts RF contexts from temporal and cross-directional reference signals, adaptively fusing these contexts with confidence maps to maximize complementary information utilization; and (4) a cross-directional RF contextual entropy model that incorporates cross-directional RF contextual latent priors to optimize contextual entropy modeling. Experimental results demonstrate the superiority of our framework over existing codecs. Our DRFC framework achieves significant bitrate savings on benchmark datasets, establishing a strong baseline for future research in this field.

Recent self-supervised stereo matching methods have made significant progress, but their performance significantly degrades under adverse weather conditions such as night, rain, and fog. We identify two primary weaknesses contributing to this performance degradation. First, adverse weather introduces noise and reduces visibility, making CNN-based feature extractors struggle with degraded regions like reflective and textureless areas. Second, these degraded regions can disrupt accurate pixel correspondences, leading to ineffective supervision based on the photometric consistency assumption. To address these challenges, we propose injecting robust priors derived from the visual foundation model into the CNN-based feature extractor to improve feature representation under adverse weather conditions. We then introduce scene correspondence priors to construct robust supervisory signals rather than relying solely on the photometric consistency assumption. Specifically, we create synthetic stereo datasets with realistic weather degradations. These datasets feature clear and adverse image pairs that maintain the same semantic context and disparity, preserving the scene correspondence property. With this knowledge, we propose a robust self-supervised training paradigm, consisting of two key steps: robust self-supervised scene correspondence learning and adverse weather distillation. Both steps aim to align underlying scene results from clean and adverse image pairs, thus improving model disparity estimation under adverse weather effects. Extensive experiments demonstrate the effectiveness and versatility of our proposed solution, which outperforms existing state-of-the-art self-supervised methods. Codes are available at https://github.com/cocowy1/RoSe-Robust-Self-supervised-Stereo-Matching-under-Adverse-Weather-Conditions.

Medical image translation plays a crucial role in assisting clinical diagnosis by enabling cross-modal synthesis (e.g., Computed Tomography to Magnetic Resonance Imaging) and super-resolution, effectively addressing clinical challenges such as radiation exposure, prolonged scan times, and allergic reactions to contrast agents. However, existing approaches primarily focus on developing specialized models for specific tasks, limiting their adaptability across different applications. Developing a general model capable of handling arbitrary medical image translation tasks not only enhances cross-domain generalization but also aligns with the broader trend of artificial intelligence evolving from specialized to general-purpose solutions. Achieving such one-for-all model, however, presents three key challenges: (1) varying task complexity, (2) modality discrepancies, and (3) structural variations across anatomical regions within the same modality. To tackle the first challenge, we utilize an advanced diffusion-based training paradigm to endow the denoising model with extensive pattern coverage capabilities, thereby handling tasks of varying difficulty levels. Subsequently, a General Diffusion Transformer incorporating a Fuzzy Mixture-of-Experts (FMoE) module and an Entropy-guided Attention Soft Prompt (EASP) module is proposed. The FMoE module, equipped with nonlinear modeling capabilities, is designed to address modality discrepancies, while the EASP module is employed to enhance the model's perception of structural variations in images. Extensive qualitative and quantitative experiments demonstrate the effectiveness of the proposed model in the arbitrary medical image translation task.

Cloth-changing person re-identification (CC-ReID) aims to match individuals wearing varying clothes across camera views. Existing CC-ReID methods typically focus on extracting clothing-invariant features such as body shape, pose, gait,etc. However, these features are diverse and often entangled with clothing-related visual clues, posing significant challenges for comprehensively and effectively separating and leveraging them for re-identification. To address these challenges, we propose a text-guided clothing generalizable (Tex-CG) model, which employs multi-modal large language models (MLLMs) to comprehensively and explicitly decouple clothing-invariant features from pedestrian images in the textual domain. By shifting feature disentanglement to the textual domain, the interference caused by visual entanglement between clothing and clothing-invariant clues can be significantly reduced. Additionally, to ensure compatibility between offline-decoupled features from MLLMs and our online-trained Tex-CG model, we utilize CLIP-based image-text matching to train implicit clothing-invariant prompts that embed discriminative pedestrian information. A dynamic fusion module is subsequently introduced to leverage these implicit prompts for selectively integrating valuable and compatible components from the MLLM’s explicitly decoupled features, constructing robust guidance to direct our model to effectively capture clothing-invariant visual clues for re-identification. Extensive experiments demonstrate the effectiveness of our method, and the Tex-CG model achieves state-of-the-art performance on five mainstream CC-ReID benchmarks. Our code is available at https://github.com/JiaoBL1234/Tex-CG.

Recent self-supervised stereo matching methods have made significant progress. They typically rely on the photometric consistency assumption, which presumes corresponding points across views share the same appearance. However, this assumption could be compromised by real-world disturbances, resulting in invalid supervisory signals and a significant accuracy gap compared to supervised methods. To address this issue, we propose SMFormer, a framework integrating more reliable self-supervision guided by the Vision Foundation Model (VFM) and data augmentation. We first incorporate the VFM with the Feature Pyramid Network (FPN), providing a discriminative and robust feature representation against disturbance in various scenarios. We then devise an effective data augmentation mechanism that ensures robustness to various transformations. The data augmentation mechanism explicitly enforces consistency between learned features and those influenced by illumination variations. Additionally, it regularizes the output consistency between disparity predictions of strong augmented samples and those generated from standard samples. Experiments on multiple mainstream benchmarks demonstrate that our SMFormer achieves state-of-the-art (SOTA) performance among self-supervised methods and even competes on par with supervised ones. Remarkably, in the challenging Booster benchmark, SMFormer even outperforms some SOTA supervised methods, such as CFNet.

Scene Graph Generation (SGG) is a challenging cross-modal task, which aims to identify entities and relationships in a scene simultaneously. Due to the highly skewed long-tailed distribution, the generated scene graphs are dominated by relation categories of head samples. Current works address this problem by designing re-balancing strategies at the data level or refining relation representations at the feature level. Different from them, we attribute this impact to catastrophic interference, that is, the subsequent learning of dominant relations tends to overwrite the earlier learning of rare relations. To address it at the modeling level, a Hippocampal Memory-Like Separation-Completion Collaborative Network (HMSC2) is proposed here, which imitates the hippocampal encoding and retrieval process. Inspired by the pattern separation of dentate gyrus during memory encoding, a Gradient Separation Classifier and a Prototype Separation Learning module are proposed to relieve the catastrophic interference of tail categories by modeling the separated classifier and prototypes. In addition, inspired by the pattern completion of area CA3 of the hippocampus during memory retrieval, a Prototype Completion Module is designed to supplement the incomplete information of prototypes by introducing relation representations as cues. Finally, the completed prototype and relation representations are connected within a hypersphere space by a Contrastive Connected Module. Experimental results on the Visual Genome and GQA datasets show our HMSC2 achieves state-of-the-art performance on the unbiased SGG task, effectively relieving the long-tailed problem. The source codes are released on GitHub: https://github.com/Nora-Zhang98/HMSC2.

The robustness of intelligent IoT device networking is vital for maintaining communication connectivity within intelligent manufacturing systems, impacting the reliability of the customized Industrial Internet of Things (CuIoT). Current studies enhance network connectivity and resilience against cyber attacks through combinatorial optimization theory by redeploying topologies. However, these approaches often overlook the transformative potential of network motifs in the optimization process. To address this, we introduce CuIoT-MET, an innovative approach that enhances CuIoT robustness by leveraging motif evolutionary transfer knowledge from historical evolution processes. By analyzing changes in connection relationships and emphasizing network motifs' unique contributions, we design a novel robustness metric to optimize the evolutionary trajectory, resulting in more robust CuIoT connection patterns. Extensive experiments show that CuIoT-MET outperforms state-of-the-art methods in improving network robustness.

Edge intelligence deploys artificial intelligence models on edge nodes proximal to data sources, and delivers real-time inference support for resource-constrained devices. To realize this vision, inference offloading differs from conventional computation offloading by tailoring offloading strategies to the intrinsic characteristics of AI inference tasks. In this field, existing researchs generally lack fine-grained model partitioning capabilities and long-term resource adaptability, failing to optimize resource utilization and sustain stable performance in mobile environments. To address these issues, we propose an adaptive inference acceleration framework that dynamically partitions inference models into hierarchical subtasks and offloads these subtasks to heterogeneous edge servers. We formulate a joint optimization problem for task partitioning, offloading and resource allocation, which takes queue stability as the constraint and aims to minimize the long-term average task completion time. To realize the optimal trade-off between latency and stability without future state prediction, we adopt Lyapunov optimization to decompose the long-term stochastic optimization into slot-by-slot solvable deterministic subproblems. For these slot-by-slot subproblems, we design a Q-network Mixing (QMIX)-based multi-agent reinforcement learning method to enable collaborative strategy selection across edge servers. Experimental simulations show that, compared with baseline algorithms including the greedy, genetic and MAD2RL methods, our proposed framework achieves a substantial reduction in task completion time while preserving inference accuracy and queue stability.

Edge intelligence enhances the computational capabilities of resource-limited devices by offloading inference tasks to edge servers. Traditional methods either execute the entire model on the device, resulting in slow inference, or fully offload it to the server, incurring communication delays and privacy risks due to raw data transmission. Model partitioning addresses these challenges by splitting the model for execution on both the device and edge server, transmitting only intermediate inference results. However, current model partitioning methods lack consideration of device mobility, resulting in reduced inference efficiency and task interruptions. To address these limitations, we introduce MobiSplit, a novel mobility-aware framework that dynamically partitions inference models between resource-constrained devices and edge servers. MobiSplit adapts to real-time device mobility, fluctuating network conditions, and computational constraints to minimize inference latency and energy consumption while ensuring robust task execution. Additionally, we propose a distributed auction-based algorithm that empowers edge devices to autonomously determine optimal partitioning and offloading strategies in a scalable and adaptive manner. Extensive simulations demonstrate that MobiSplit enhances inference efficiency, achieving a 60% latency reduction and a 20% energy consumption decrease compared to the best-performing baseline across diverse edge scenarios.

Indoor localization is crucial for applications such as navigation, asset tracking, and emergency response. Fingerprint-based methods that use RSSI are widely adopted; however, they fail under large environmental changes. Unmanned Vehicles (UVs) equipped with high precision sensors are able to collect fingerprints, serving as a promising way by forming a Vehicular Crowdsensing (VCS) campaign. In this paper, we propose “BRAVE”, a Bayesian RL Approach for VCS under Environment changing, while introducing a new metric “Calibration Benefit” to explicitly quantify how effectively a learned trajectory updates those regions of the fingerprint database that have changed and matter most for localization. Specifically, we propose a spatial-temporal Bayesian Network(BN) for change detection, a region rearrangement method for fewer restarts, and an optimistic strategy to balance the exploration and exploitation trade-offs in optimizing calibration benefit. Extensive results on two real-world datasets from SML Center (Shanghai) and Haopu Fashion City (Shanghai) demonstrate that BRAVE outperforms eight baselines and the derived dataset has better localization accuracy compared with the original dataset.

Zero-shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging yet rewarding task, as it demands models to possess both brain- like zero-shot learning and cross-view alignment capabilities. Recent advances suggest that powerful pre-trained vision encoders, such as CLIP, offer a promising alternative for addressing the ZS-SBIR task. However, the problem of simultaneously evoking the zero-shot learning capability and cross-view alignment capability of pre-trained vision encoders has barely been discussed. To this end, we propose the CrOss-view Attention Prompt (COP) framework, which is composed of an Attention Prompt module and a Cross-view Query module. Specifically, we formulate prompt construction as a retrieval problem by introducing a prompt pool and attention mechanism, thereby constructing attention prompts with fine granularity to enhance the zero-shot learning capability. Furthermore, to endow COP with cross-view alignment capabilities, we replace single-view queries with carefully designed cross-view queries, which can be smoothly inserted into the Attention Prompt module. The proposed COP is scenario-agnostic and supports vision encoders with diverse pre-training schemes. Comprehensive experiments show that COP achieves competitive performance in ZS-SBIR, Generalized ZS-SBIR, and Cross-data ZS-SBIR scenarios, regardless of whether it is based on the ImageNet pre-trained vision encoder or the CLIP pre-trained vision encoder.

The prediction of network latency with partial measurements is of importance for ever-increasing personal devices to ensure their Quality of Service (QoS). However, the current matrix-factorization-based efforts, as a promising paradigm, for network latency prediction have failed to intelligently exploit inherent factors hidden in networks to accurately infer the unknown network latency. Furthermore, it is more complicated to execute extensive network measurements on pervasive personal devices due to unstable communication environments. To alleviate these problems, in this paper, a novel accurate network latency prediction (DALP) solution via Deep Reinforcement Learning (DRL) is proposed for personal devices under cost-aware sampling. Specifically, we first alternately implement cost-aware latency measurement based on temporal correlation, and model it as a network latency matrix, in which unmeasured and missing elements need to be inferred. In order to achieve accurate prediction performance, the DRL-based Matrix Factorization with Double Weights (DWMF) is designed to exploit the potential network factors and multiple rules of matrix factorization, which can be alternatively executed, to minimize the prediction errors. Furthermore, an angle-loss-based reward strategy is designed to enhance the quality of model training. Simulation results on real-world datasets illustrate that DALP outperforms the previous approaches with quicker convergence and lower prediction errors.

Pinching-antenna systems (PASS) reshape wireless channels by moving pinching elements along dielectric waveguides. Movable signals (MS) and rate-splitting multiple access (RSMA) add frequency-domain flexibility and robust interference management, but these three dimensions are often studied in isolation. This paper proposes a unified PASS–MS–RSMA framework for downlink max–min fairness (MMF). We first develop a channel model that captures in-waveguide attenuation and phase via an effective refractive index, together with free-space path loss and phase, and extend it to MS by small carrier-frequency offsets. On this basis, we formulate a joint MMF problem over pinching-antenna positions, carrier frequency, and RSMA power and common-rate allocation. To solve the resulting nonconvex problem, we design two optimization algorithms. The first scheme is a baseline alternating optimization (AO) scheme that combines bisection on the MMF level with a proximal successive convex approximation (P-SCA) for the RSMA variables and a proximal gradient step for the PASS–MS geometry and frequency. The second method uses an explicit geometry–frequency analysis to strengthen the design. In a high-SNR regime, we show that the MMF rate is well approximated by a monotone function of the harmonic mean of the users’ channel gains. This leads to a surrogate MMF objective that depends only on the PASS–MS channel and yields closed-form gradients with respect to antenna positions and carrier frequency. We then build a harmonic-mean-guided proposal-and-refinement algorithm in which the baseline AO–P-SCA scheme provides local exact-MMF refinement and the harmonic-mean gradient provides geometry–frequency trial moves filtered by the same exact-MMF Armijo acceptance rule. Numerical results demonstrate that the proposed PASS–MS–RSMA design achieves a much higher MMF rate and coverage probability than PASS-only, MS-only, and MS–NOMA/OMA benchmarks, and that it also outperforms compact and aperture-matched single-RF phased-array baselines together with an RIS-aided baseline under matched element counts, carrier/bandwidth settings, and total-power budget. They also show that the harmonic-mean-guided variant attains almost the same MMF performance as the exact alternating scheme while requiring substantially lower computational effort.

The reconfigurable intelligent surface (RIS)-aided cognitive radio (CR) system holds significant promise for enhancing spectrum utilization. However, its practical implementation hinges critically on accurate channel state information (CSI). Obtaining full cascaded CSI in RIS-aided CR systems with the cross interference between multiple cascaded channels is challenging. To fill this gap, we propose the deep learning-based channel acquisition schemes for the users in static scenario and mobile scenario, respectively. In static scenario, we propose a novel deep neural network (DNN)-based channel estimation scheme named dual output parameter estimation (DOPE). This scheme achieves remarkable normalized mean square error (NMSE) performance in CSI estimation while significantly reducing the required pilot overhead. In mobile scenario, we propose a channel prediction scheme with hybrid recurrent neural network (RNN) and Transformer (HRT-CP). This scheme utilizes RNN to extract dynamic and static features of cascaded channels, and introduces Transformer’s powerful parallel processing capability to efficiently predict dynamic features. By combining static and dynamic features appropriately, the HRT-CP scheme has predicted the future cascaded CSI accurately, and mitigated the error accumulation phenomenon effectively. The simulation results under both near-field and far-field channel models demonstrate that our proposed schemes provide significant gains on NMSE performance compared to other benchmarks.

Large language models (LLMs) have made exciting achievements across various domains, yet their deployment on resource-constrained personal devices remains hindered by the prohibitive computational and memory demands of task-specific fine-tuning. While quantization offers a pathway to efficiency, existing methods struggle to balance performance and overhead, either incurring high computational/memory costs or failing to address activation outliers, a critical bottleneck in quantized fine-tuning. To address these challenges, we propose the Outlier Spatial Stability Hypothesis (OSSH): During fine-tuning, certain activation outlier channels retain stable spatial positions across training iterations. Building on OSSH, we propose Quaff, a Quantized parameter-efficient fine-tuning framework for LLMs, optimizing low-precision activation representations through targeted momentum scaling. Quaff dynamically suppresses outliers exclusively in invariant channels using lightweight operations, eliminating full-precision weight storage and global rescaling while reducing quantization errors. Extensive experiments across ten benchmarks validate OSSH and demonstrate Quaff's efficacy. Specifically, on the GPQA reasoning benchmark, Quaff achieves a 1.73× latency reduction and 30% memory savings over full-precision fine-tuning while improving accuracy by 0.6% on the Phi-3 model, reconciling the triple trade-off between efficiency, performance, and deployability. By enabling consumer-grade GPU fine-tuning (e.g., RTX 2080 Super) without sacrificing model utility, Quaff democratizes personalized LLM deployment. The code is available at https://github.com/Little0o0/Quaff.git. © 2025 Association for Computational Linguistics.

Sensor data analysis is a crucial task for environmental cognition in smart traffic systems. Recently, vehicle-to-everything (V2X) collaborative analysis has leveraged intermediate feature communication between vehicles and infrastructure to achieve superior analysis performance compared to single-vehicle approaches. However, due to the limited bandwidth of V2X communication links, directly transmitting features can be inefficient, resulting in significant delays that are unacceptable for real-time decision-making. To address this challenge, we propose a compact feature representation method in the bird's eye view (BEV) space for communication-efficient collaborative analysis. As shown in Fig. 1, the proposed method can be viewed as a task-aware distributed coding approach with decoder side information. First, the ego vehicle and the networked infrastructure convert raw LiDAR data into BEV features using a shared PointPillars feature extractor. The infrastructure then applies the proposed BEV codec to transform these BEV features into a compact representation, encoding them into a binary bitstream through entropy coding based on the estimated distribution. The received features are subsequently warped and fused with the ego vehicle's features using a bidirectional attention fusion module, and processed by a single-shot detector to perform 3D object detection. Experimental results on the DAIR-V2X-C dataset demonstrate that the proposed framework achieves more than 1000 times compression compared to directly transmitting floating-point features, while maintaining high analysis performance in real-world V2X scenarios.

In reconfigurable intelligent surfaces (RIS)-aided cognitive radio (CR) systems, the estimation of high-dimensional channel state information (CSI) with the interferences for all the cascaded channels between the RIS and any pair of the transceivers is challenging. To solve this problem, we propose a three-stage scheme of the full cascaded channel estimation based on the deep neural network (DNN). At the beginning, the protocol of the two-step pilot transmissions is designed for generating the labeled channel dataset in data preparation stage. Specifically, we propose dual-output parameter estimation (DOPE) architecture to establish and train the DNN model for full cascaded channel estimation simultaneously with a low pilot overhead in model construction and training stage. Notably, our proposed DNNbased DOPE architecture can accomplish the estimation of both the near-field and far-field cascaded channels in the RIS-aided CR system. Besides, the protocol of only one pilot transmission is introduced for online channel estimation in the model deployment stage. The simulation results show that our proposed scheme outperforms the compared benchmark estimation algorithms at the aspects of both the normalized mean square error (NMSE) performance and the cost of the pilot overhead.

Knowledge Graph Question Answering (KGQA) addresses natural language questions by leveraging structured information stored in knowledge graphs. However, existing KGQA methods are overly concerned with improving the quality of responses by retrieving information, neglecting to identify which type of knowledge is truly useful to optimize the performance of the KGQA system, resulting in redundant retrieval. At the same time, these methods have limitations in aligning user intent and insufficient semantic richness in responses. In this work, we propose IP-KGQA, which introduce a intent-aware prompt learning scheme for KGQA framework. A Selection-Driven Efficient Retrieval (SER) module is incorporated in the framework, which classifies user questions to ensure that only long-tail questions are directed to the knowledge graph retrieval to enhance system efficiency. To filter and select the most relevant triplets, aligning retrieved information more closely with user intent, we introduce the User Intent-aware Filtering (UIF) module, where Monte Carlo sampling is applied to obtain the optimal triplets. The Domain-specific Context Prompt Extension (DCPE) module is utilized in collaboration with a fine-tuned large language model (LLM) to integrate domain-specific knowledge into the responses, ensuring that the answers are enriched in terms of semantic quality. Extensive experiments have been conducted on the CommonSenseQA and TriviaQA datasets, which demonstrate that IP-KGQA outperforms the existing methods in terms of retrieval efficiency, answer accuracy and user intent alignment.

Face image inpainting, especially with user-controllable customization, aims to restore degraded facial regions while adhering to user-provided instructions. Traditional inpainting methods often focus solely on restoring visual fidelity, lacking the ability to incorporate user prompts or semantic guidance. In this work, we present InpaintFormer, a novel framework for user-controlled face image inpainting guided by textual prompts. Specifically, we propose a Prompt-guided Feature Modulation (PGFM) module to align visual features with user instructions by utilizing a pre-trained CLIP model to extract text and image embeddings. These embeddings are fused to modulate the encoded image features, ensuring semantic consistency with the prompt. Additionally, a Degradation Mask Predictor (DMP) is introduced to identify degraded regions requiring inpainting, while a Mask-Aware Self-Attention (MASA) mechanism within the Transformer refines the inpainting process by selectively attending to non-degraded regions for generating realistic results. By combining PGFM, DMP, and MASA, InpaintFormer enables controllable face image inpainting with high fidelity and semantic alignment. Extensive experiments demonstrate that InpaintFormer outperforms state-of-the-art inpainting methods in terms of controllability and naturalness.

Federated Learning (FL) enables collaborative model training across distributed clients without data sharing, but its high computational and communication demands strain resource-constrained devices. While existing methods use dynamic pruning to improve efficiency by periodically adjusting sparse model topologies while maintaining sparsity, these approaches suffer from issues such as **greedy adjustments**, **unstable topologies**, and **communication inefficiency**, resulting in less robust models and suboptimal performance under data heterogeneity and partial client availability. To address these challenges, we propose **Fed**erated **R**obust pruning via combinatorial **T**hompson **S**ampling (FedRTS),a novel framework designed to develop robust sparse models. FedRTS enhances robustness and performance through its Thompson Sampling-based Adjustment (TSAdj) mechanism, which uses probabilistic decisions informed by stable and farsighted information, instead of deterministic decisions reliant on unstable and myopic information in previous methods. Extensive experiments demonstrate that FedRTS achieves state-of-the-art performance in computer vision and natural language processing tasks while reducing communication costs, particularly excelling in scenarios with heterogeneous data distributions and partial client participation. Our codes are available at: https://github.com/Little0o0/FedRTS.

Model editing has become a *de-facto* practice to address hallucinations and outdated knowledge of large language models (LLMs). However, existing methods are predominantly evaluated in isolation, i.e., one edit at a time, failing to consider a critical scenario of compositional model editing, where multiple edits must be integrated and jointly utilized to answer real-world multifaceted questions. For instance, in medical domains, if one edit informs LLMs that COVID-19 causes "fever" and another that it causes "loss of taste", a qualified compositional editor should enable LLMs to answer the question "What are the symptoms of COVID-19?" with both "fever" and "loss of taste" (and potentially more). In this work, we define and systematically benchmark this compositional model editing (CME) task, identifying three key undesirable issues that existing methods struggle with: *knowledge loss*, *incorrect preceding* and *knowledge sinking*. To overcome these issues, we propose A$^3$E, a novel compositional editor that (1) ***a**daptively combines and **a**daptively regularizes* pre-trained foundation knowledge in LLMs in the stage of edit training and (2) ***a**daptively merges* multiple edits to better meet compositional needs in the stage of edit composing. Extensive experiments demonstrate that A$^3$E improves the composability by at least 22.45\% without sacrificing the performance of non-compositional model editing.

Temporally consistent depth estimation from stereo video is critical for real-world applications such as augmented reality, where inconsistent depth estimation disrupts the immersion of users. Despite its importance, this task remains challenging due to the difficulty in modeling long-term temporal consistency in a computationally efficient manner. Previous methods attempt to address this by aggregating spatio-temporal information but face a fundamental trade-off: limited temporal modeling provides only modest gains, whereas capturing long-range dependencies significantly increases computational cost. To address this limitation, we introduce a memory buffer for modeling long-range spatio-temporal consistency while achieving efficient dynamic stereo matching. Inspired by the two-stage decision-making process in humans, we propose a Pick-and-Play Memory (PPM) construction module for dynamic Stereo matching, dubbed as PPMStereo. PPM consists of a pick process that identifies the most relevant frames and a play process that weights the selected frames adaptively for spatio-temporal aggregation. This two-stage collaborative process maintains a compact yet highly informative memory buffer while achieving temporally consistent information aggregation. Extensive experiments validate the effectiveness of PPMStereo, demonstrating state-of-the-art performance in both accuracy and temporal consistency.Codes are available at \textcolor{blue}{https://github.com/cocowy1/PPMStereo}.

Safety validation, which assesses the safety of an autonomous system's motion planning decisions, is critical for the safe deployment of autonomous vehicles. Existing input validation techniques from other machine learning domains, such as image classification, face unique challenges in motion planning due to its contextual properties, including complex inputs and one-to-many mapping. Furthermore, current output validation methods in autonomous driving primarily focus on open-loop trajectory prediction, which is ill-suited for the closed-loop nature of motion planning. We introduce REDOUBT, the first systematic safety validation framework for autonomous vehicle motion planning that employs a duo mechanism, simultaneously inspecting input distributions and output uncertainty. REDOUBT identifies previously overlooked unsafe modes arising from the interplay of In-Distribution/Out-of-Distribution (OOD) scenarios and certain/uncertain planning decisions. We develop specialized solutions for both OOD detection via latent flow matching and decision uncertainty estimation via an energy-based approach. Our extensive experiments demonstrate that both modules outperform existing approaches, under both open-loop and closed-loop evaluation settings. Our codes are available at: https://github.com/sgNicola/Redoubt.

The Internet of Underwater Things (IoUT) connects underwater devices for applications like environmental monitoring, marine exploration, and disaster response. Accurate localization of acoustic sources is vital to IoUT, enabling tasks such as sensor deployment and vehicle navigation. The Time Difference of Arrival (TDOA) method, which uses differences in signal arrival times at multiple receivers, is widely employed for this purpose. However, traditional TDOA approaches assume a constant sound speed, overlooking depth-dependent variations caused by changes in salinity, temperature, and pressure. Additionally, multipath propagation complicates localization, as the first received signal may include reflections rather than the direct path. This paper presents a novel synchronization-free localization method, Synchronized-Transmission TDOA (ST-TDOA), tailored for IoUT environments. The proposed method eliminates the need for clock synchronization among receivers, while addressing sound speed variability and mitigating multipath effects. A dynamic model is developed to adaptively adjust for sound speed changes, and a synchronized transmission algorithm ensures accurate TDOA measurements, reducing errors caused by clock discrepancies. Simulation results demonstrate significant improvements in localization accuracy and reliability, highlighting the effectiveness of ST-TDOA in addressing critical challenges in underwater localization for IoUT systems.

As the Internet of Things (IoT) technology and artificial intelligence (AI) technology continue to evolve, many envisaged concepts regarding smart cities are gradually becoming a reality. However, the proliferation of numerous IoT devices in smart cities has led to several challenges. The existing 5G networks are incapable of meeting the requirements of these devices in terms of channel capacity and network coverage. Additionally, traditional cloud-based centralized machine-learning methods fail to ensure the privacy of user data. At this juncture, space-air–ground information network, along with federated learning (FL), are perceived as viable solutions to address these issues. This article focuses on addressing FL challenges in smart cities using the space-air–ground information network. Here, data distribution heterogeneity leads to increased federated training time and higher energy costs. This article begins by analyzing the reasons for the nonindependent and nonidentically distributed (Non-IID) data collected by devices in this scenario. Subsequently, from the perspective of device selection, this article proposes a node selection model based on near-edge strategy optimization, termed “low node selection in FL” (LCNSFL). Finally, the LCNSFL algorithm is compared with federated averaging algorithms based on random selection strategies and the FedProx algorithm. Experimental results demonstrate that the FL model aided by the LCNSFL algorithm achieves the target accuracy with fewer communication rounds, considerably reducing the required training time and energy costs compared to the other two algorithms.

The Age of Information (AoI), which measures the time since the generation of the latest update, quantifies information freshness in timeliness-critical systems. Minimizing AoI and characterizing it precisely are crucial for system efficiency and decision-making. This work investigates AoI under external interference modeled as an On-Off process, providing a foundation for future research in more complex scenarios. We consider a discrete-time remote status-updating system with a monitor and a sensor, where the sensor observes a physical process, generates timestamped updates, and sends them to the monitor. Both inter-arrival and service times follow geometric distributions, with service interrupted according to a two-state On-Off process. We analyze AoI under two queuing disciplines: 1) non-preemptive, where arriving updates are discarded if the server is occupied, and 2) preemptive, where in-service updates are replaced with new ones during the Off state. For both, we derive closed-form expressions for average AoI and peak AoI (PAoI). We also explore the relationship between discrete-time and continuous-time systems, showing that the latter is the limiting case of the former. Numerical results validate the theoretical analysis, revealing a linear relationship between the relative normalized increase in average PAoI and AoI and the proportion of Off state time. Frequent On-Off switching and higher service rates under the same system load help mitigate freshness deterioration caused by interruptions. The On-Off process is shown to have a large impact on the average AoI (resp. PAoI) of systems with relatively high (resp. low) arrival and service rates.

Federated learning, as a promising distributed learning paradigm, enables collaborative training of a global model across multiple network edge clients without the need for central data collecting. However, the heterogeneity of edge data distribution drags the model towards the local minima, which can be distant from the global optimum. Such heterogeneity often leads to slow convergence and substantial communication overhead. To address these issues, we propose a novel federated learning framework calledFedCMD, a model decoupling tailored to the Cloud-edge supported federated learning that separates deep neural networks into a body for capturing shared representations in Cloud and a personalized head for migrating data heterogeneity. Our motivation is that, by the deep investigation of the performance of selecting different neural network layers as the personalized head, we found rigidly assigning the last layer as the personalized head in current studies is not always optimal. Instead, it is necessary to dynamically select the personalized layer that maximizes the training performance by taking the representation difference between neighbor layers into account. To find the optimal personalized layer, we utilize the low-dimensional representation of each layer to contrast feature distribution transfer and introduce a Wasserstein-based layer selection method, aimed at identifying the best-match layer for personalization. Additionally, a weighted global aggregation algorithm is proposed based on the selected personalized layer for the practical application ofFedCMD. Extensive experiments on ten benchmarks demonstrate the efficiency and superior performance of our solution compared with nine state-of-the-art solutions. All code and results are available athttps://github.com/elegy112138/FedCMD.

This paper is concerned with the theoretical modeling and analysis of uplink connection performance of a radiosonde network deployed in a typhoon. Similar to existing works, the stochastic geometry theory is leveraged to derive the expression of the uplink connection probability (CP) of a radiosonde. Nevertheless, existing works assume that network nodes are spherically or uniformly distributed. Different from the existing works, this paper investigates two particular motion patterns of radiosondes in a typhoon, which significantly challenges the theoretical analysis. According to their particular motion patterns, this paper first separately models the distributions of horizontal and vertical distances from a radiosonde to its receiver. Secondly, this paper derives the closed-form expressions of cumulative distribution function (CDF) and probability density function (PDF) of a radiosonde’s three-dimensional (3D) propagation distance to its receiver. Thirdly, this paper derives the analytical expression of the uplink CP for any radiosonde in the network. Finally, extensive numerical simulations are conducted to validate the theoretical analysis, and the influence of various network design parameters is comprehensively discussed. Simulation results show that when the signal-to-interference-noise ratio (SINR) threshold is below -35 dB, and the density of radiosondes remains under 0.01/km3, the uplink CP approaches 26%, 39%, and 50% in three patterns.

This work studies information freshness of a V2I status updating link in IoV. The status updating link is modeled as a multi-source Ber/Geo/1/1 non-preemptive or preemptive queue. We focus on statistical characteristics of the age of information (AoI) and peak AoI (PAoI). To fully track the AoI evolutions under non-preemptive and preemptive policies, Markov three-dimensional age process (3DAP) and two-dimensional age process (2DAP) are respectively introduced. Their first element is the AoI process; The second one stands for if an update of the concerned source is in transmission and its current age; The third element of 3DAP denotes if an update of another source is in transmission. An analytical approach for studying the AoIs and PAoIs in discrete-time multi-source systems is presented. By studying the state transitions, balance equations, and stationary distributions of 3DAP and 2DAP, analytical expressions of the distributions and averages of AoIs and PAoIs under both queueing policies are derived. Moreover, the optimal probabilistic update selection mechanism (PUSM) that maximizes overall freshness is derived in closed-form for the two-source case. Numerical results validate effectiveness of the theoretical analyses and reveal usefulness of the retransmission. It is found that in terms of improving the overall freshness, the PUSM should be designed to make effective update generation probabilities of sources as close as possible.

Most existing Domain Generalizable Person Re-identification (DG-ReID) methods focus on addressing style disparities between domains but often overlook the impact of unpredictable camera view changes, which we have identified as a significant factor responsible for poor generalization performance. To address this issue, we propose a novel approach from a 3D perspective, utilizing a customized 2D-to-3D reconstruction model to convert images captured from arbitrary camera views into canonical view images. However, merely applying a 3D reconstruction model in isolation may not result in improved DG-ReID performance, as reconstruction quality can be influenced by multiple factors, such as insufficient image resolution, extreme viewpoint, and environmental variations. These factors may lead to error accumulation and the loss of critical discriminative clues in the reconstructed results. To address this difficulty, we propose fusing the canonical view image with the original image using a transformer-based module. The transformer’s cross-attention mechanism is ideal for aligning and fusing the key semantic clues of the original image with the canonical view image, compensating for reconstruction errors. We demonstrate the effectiveness of our method through extensive experiments in various evaluation settings, achieving superior DG-ReID performance compared to existing approaches. Our approach addresses the impact of unpredictable camera view changes and provides a new perspective for designing DG-ReID methods.

The balance between accuracy and computational efficiency is crucial for the applications of deep learning-based stereo matching algorithms in real-world scenarios. Since matching cost aggregation is usually the most computationally expensive component, a common practice is to construct cost volumes at a low resolution for aggregation and then directly regress a high-resolution disparity map. However, current solutions often suffer from limitations such as the loss of discriminative features caused by downsampling operations that treat all pixels equally, and spatial misalignment resulting from repeated downsampling and upsampling. To overcome these challenges, this paper presents two sampling strategies: the Adaptive Downsampling Module (ADM) and the Disparity Alignment Module (DAM), to prioritize real-time inference while ensuring accuracy. The ADM leverages local features to learn adaptive weights, enabling more effective downsampling while preserving crucial structure information. On the other hand, the DAM employs a learnable interpolation strategy to predict transformation offsets of pixels, thereby mitigating the spatial misalignment issue. Building upon these modules, we introduce ADStereo, a real-time yet accurate network that achieves highly competitive performance on multiple public benchmarks. Specifically, our ADStereo runs over faster than the current state-of-the-art CREStereo (0.054s vs. ) under the same hardware while achieving comparable accuracy (1.82% vs. 1.69%) on the KITTI stereo 2015 benchmark. The codes are available at: https://github.com/cocowy1/ADStereo.

Robust Topology is a key prerequisite to providing consistent connectivity for highly dynamic Internet-of-Things (IoT) applications that are suffering node failures. In this paper, we present a two-step approach to organizing the most robust IoT topology. First, we propose a novel robustness metric denoted as$I$, which is based on network motifs and is specifically designed to sensitively analyze the dynamic changes in topology resulting from node failures. Second, we introduce a Distributed duAl-layer collaborative competition optimization strategy based on Motif density (DAiMo). This strategy significantly expands the search space for optimal solutions and facilitates the identification of the optimal IoT topology. We utilize the motif density concept in the collaborative optimization process to efficiently search for the optimal topology. To support our approach, extensive mathematical proofs are provided to demonstrate the advantages of the metric$I$in effectively perceiving changes in IoT topology and to establish the convergence of the DAiMo algorithm. Finally, we conduct comprehensive performance evaluations of DAiMo and investigate the influence of network motifs on the resilience and reliability of IoT topologies. Experimental results clearly indicate that the proposed method outperforms existing state-of-the-art topology optimization methods in terms of enhancing network robustness.

The delivery of goods to numerous indoor stores poses significant safety risks, with heavy, high-stacked packages on delivery trolleys posing a potential hazard to passersby. This paper reports our experiences of developing and operating DeMo, a practical system for real-time monitoring of indoor delivery. DeMo employs sensors attached to trolleys, utilizing Inertial Measurement Unit (IMU) and Bluetooth Low Energy (BLE) readings to detect delivery violations, such as speeding and the use of non-designated delivery paths, and ensure accurate matching of each delivery to its intended destination store. Unlike typical indoor localization applications, DeMo addresses unique challenges, including sensor placement and the complex electromagnetic characteristics encountered in underground settings. Specifically, DeMo adapts the classical logarithmic radio signal model to facilitate fingerprint-free localization, significantly reducing deployment and maintenance costs. DeMo has been operating since May 2020, covering more than 200 shops with 74,537 deliveries (6193.2 km) across 12 subway stations in Hong Kong. DeMo's 4-year operation witnessed a significant violation rate drop, from 19% (May 2020) to 0.9% (Mar 2024).

The accurate prediction of Quality of Service (QoS) in terms of response time, packet loss rate, latency and throughput for component services is essential for 5 G to fulfill specific Service Level Agreements (SLAs). However, most current efforts failed to fully exploit the time-varying mobility features of users and parallel iteration multi-rules to perform QoS prediction for component services, incurring poor prediction accuracy. Therefore, in this paper, we are devoted to accurate QoS Prediction of Component Services (QPCS) for 5 G via Graph-based Deep Reinforcement Learning (GDRL) to tackle this issue. Towards this end, the QoS prediction is modeled as GDRL-based QoS tensor factorization by designing a Spatio-Temporal-Recurrent-based Graph Attention Network (STR-GAT) and introducing it into Deep Deterministic Policy Gradient (DDPG) to factorize QoS tensor with multiple available rules in parallel. Specifically, a low-rank QoS tensor and an adjacency tensor are established, which include partial QoS observations of component services in each Base Station (BS), along with some missing elements, and evolving spatial information of users across these BSs, respectively. Then, the novel STR-GAT is designed by introducing spatio-temporal relations into conventional GAT to fully derive the mobility features of users to explore potential actions, while the derivative DDPG is adopted to perform tensor factorization with multiple available rules in parallel. Furthermore, the action smoothing and hierarchical-based replay buffer with priority-based and random sampling are designed and introduced into DDPG to stabilize training process and accelerate model convergence. Experimental simulation results on real-world datasets validate the superiorities of QPCS compared with the state-of-the-art approaches in predicting the QoS of component services in 5 G.

By harnessing the capabilities of unmanned aerial and ground vehicles (UAVs and UGVs), equipped with high-precision sensors, air-ground mobile crowdsensing (AG-MCS) has proven to be effective for data collection in urban environments. In this paper, by optimizing the metric of age-of-information (AoI) that measures the freshness of collected data, we consider the problem of AoI-Aware AG-MCS (A3G-MCS), where UGVs dispatch UAVs from multiple UGV stops to collect data from point-of-interests (PoIs). We propose a novel multi-agent curriculum learning framework called “MACL(MCS)”, that explicitly balances the individual and team goals of both UAV/UGV controllers to facilitate the exploration of policy towards globally-optimal performance. It is further enhanced by a UAV/UGV collaborative observation augmentation (COA) module for improved inter-controller communication. Extensive results reveal that MACL(MCS) consistently outperforms five baselines, and achieves comparable performance to exact method with better scalability and efficiency. It also showcases strong generalization capability towards real-world scenarios on both TSPLIB and Purdue, KAIST and NCSU datasets.

Predicting stock trends is a highly rewarding but high-risk endeavor due to the complex interplay of market dynamics, irrational behaviors, and diverse sentiments. Previous studies have used time-series analysis on historical prices or sentiment analysis on textual information. However, these methods often fail to capture the dynamic interactions between text and time-series modalities and overlook the different perspectives embedded in textual data. To address these limitations, we propose the pleno-alignment framework (PAFrame) that enhances multimodal stock information through intermodal and intramodal alignment to capture market dynamics. Our framework first integrates textual and time-series data in a shared representation space to learn modal-invariant information. To tackle divergent sentiments in textual data, we employ a contrastive learning approach to extract abstract semantic meanings from objective and subjective perspectives, thereby improving the robustness of language representations. Finally, we use a hybrid approach that explicitly combines cross-attention mechanisms to create a unified representation and utilizes prompts to implicitly guide language models with numerical financial indicators for final prediction. Our comprehensive experiments on five real-world datasets show that PAFrame outperforms existing methods in predicting stock trends.

Combining half-duplex (HD) and full-duplex (FD) is promising in improving the information transmission rate of relay channels. This work proposes a novel two-phase hybrid duplex scheme for Gaussian relay channel where the relay operates in FD mode for a fraction of time and only transmits information for the rest of time. The achievable rate of the proposed hybrid duplex scheme is characterized in detail. Based on the obtained result, a joint time division and power allocation problem is formulated to maximize the achievable rate. In particular, the formulated problem is solved through a two-step optimization method. Firstly, the optimal relay power allocation is obtained for given time division factors. Then, the achievable rate maximization problem is addressed by finding the optimal time division factors. The closed-form expression for the maximal achievable rate is derived for some specific cases. Numerical results show that the proposed two-phase hybrid duplex scheme significantly improves the achievable rate of Gaussian relay channel compared with existing benchmark schemes.

In Federated Continual Learning (FCL), the challenge lies in effectively facilitating knowledge transfer and enhancing the performance across various tasks on different clients. Current FCL methods predominantly focus on avoiding interference between tasks, thereby overlooking the potential for positive knowledge transfer across tasks learned by different clients at separate time intervals. To address this issue, we introduce a **P**rompt-based kn**ow**le**d**ge transf**er** FCL algorithm, called **Powder**, designed to effectively foster the transfer of knowledge encapsulated in prompts between various sequentially learned tasks and clients. Furthermore, we have devised a unique approach for prompt generation and aggregation, intending to alleviate privacy protection concerns and communication overhead, while still promoting knowledge transfer. Comprehensive experimental results demonstrate the superiority of our method in terms of reduction in communication costs, and enhancement of knowledge transfer. Code is available at https://github.com/piaohongming/Powder.

Unmanned aerial vehicles (UAVs) have emerged as a promising solution for enhancing mobile-edge computing (MEC) networks. However, the integration of UAVs into MEC networks poses unique challenges, such as the presence of dynamic devices and complex resource allocation. This research investigates the problem of task offloading in a distributed MEC network with multiple ground and aerial base stations (UAV base stations). With a focus on the cost-sensitive nature of Internet of Things Devices (IoTDs), our objective is to maximize the Quality of Experience (QoE) in terms of average task response time and cache queue length in IoTDs by jointly optimizing device association, offloading decision, and UAV trajectory planning. To address the combinatorial and nonconvex nature of the problem, we propose an artificial intelligence (AI)-based optimization scheme. First, the association between IoTDs and stations is determined using a recursive selection and replacement transmission-rate-based (RSRT) algorithm. Subsequently, the offloading problem is formulated as a 0-1 Backpack Problem with variable value, for which we present a backtracking task offloading (BTO) algorithm. Additionally, we employ a multiagent deep deterministic policy gradient (MADDPG) approach to determine the trajectory planning of UAVs. Numerical results demonstrate the effectiveness of the proposed scheme in terms of reduction in average response time, and cache queue length in IoTDs within the MEC system when compared to benchmark schemes.

Emerging applications in industrial Internet of things (IIoT) pursue ultra-reliability, low-latency, and high data rate. While majority of the industries are in the remote areas, capability of distant ultra-reliable and low-latency communication (uRLLC) has become one of the key performance indices of IIoT which we need to make a breakthrough. While relaying provides intuitive solution for improving communication distance, the introduction of relay in distant uRLLC intensifies the conflict between reliability and low-latency which further deteriorates the throughput of the relaying-based IIoT. In this work, we adopt full-duplex relaying to enhance the performance of distant uRLLC in IIoT. Specifically, we improve the reliability at MAC layer and throughput at physical layer in full-duplex relaying-based IIoTs, through jointly optimizing the coding rate and the power allocation between the source and relay node. In particular, a low-complexity algorithm is developed to find the exact optimal coding rate and relay power under total system power constraint. Extensive numerical results validate the conclusion that the reliability and throughput of distant uRLLC in IIoT are enhanced through full-duplex relaying, power allocation, and rate adaptation.

In practical status updating systems, most decisions made at monitors are based on diverse data streams. Due to the cask effect, it can be cognised that the effectiveness of decisions is often constrained by the stalest one, i.e., the straggler among all the streams. This work studies the statistical characteristics of age of the stalest information (AoSI) which describes the timeliness of the stalest stream. The AoSI is defined as the time elapsed since the latest successfully received update of the currently stalest stream among all different streams at the monitor was generated. Peak age of the stalest information (PAoSI) is also studied for evaluating the worst cases, i.e., the peaks of AoSI process. We develop an analytical approach to derive the AoSI and PAoSI based on the per-stream age of information (AoI) and peak age of information (PAoI), for the multi-stream single-monitor system with separate status updating. In particular, to comprehensively characterize the timeliness of the stalest stream, the distributions of AoSI and PAoSI are derived in closed-form for the general multi-stream system. Moreover, we concisely derive the explicit expressions of the distributions and averages of AoSI and PAoSI, upon a typical two-stream case with the classical automatic repeat-request protocol. Finally, the accuracy of the theoretical analyses is validated by the numerical results. Appropriateness and advantages of the AoSI (PAoSI) are elaborated by comparing with the maximum average AoI (PAoI), i.e., the maximal one among the averages of all the per-stream AoIs (PAoIs).

Indoor localization is drawing more and more attentions due to the growing demand of various location-based services, where fingerprinting is a popular data driven techniques that does not rely on complex measurement equipment, yet it requires site surveys which is both labor-intensive and time-consuming. Vehicular crowdsensing (VCS) with unmanned vehicles (UVs) is a novel paradigm to navigate a group of UVs to collect sensory data from certain point-of-interests periodically (PoIs, i.e., coverage holes in localization scenarios). In this paper, we formulate the multi-floor indoor fingerprint collection task with periodical PoI coverage requirements as a constrained optimization problem. Then, we propose a multi-agent deep reinforcement learning (MADRL) based solution, “MADRL-PosVCS”, which consists of a primal-dual framework to transform the above optimization problem into the unconstrained duality, with adjustable Lagrangian multipliers to ensure periodic fingerprint collection. We also propose a novel intrinsic reward mechanism consists of the mutual information between a UV’s observations and environment transition probability parameterized by a Bayesian Neural Network (BNN) for exploration, and a elevator-based reward to allow UVs to go cross different floors for collaborative fingerprint collections. Extensive simulation results on three real-world datasets in SML Center (Shanghai), Joy City (Hangzhou) and Haopu Fashion City (Shanghai) show that MADRL-PosVCS achieves better results over four baselines on fingerprint collection ratio, PoI coverage ratio for collection intervals, geographic fairness and average moving distance.

The integrated ground-air-space (GAS) communications system can enhance post-disaster rescue and management efforts when traditional networks fail, by navigating unmanned ground vehicles (UGVs) and unmanned arieal vehicles (UAVs) to collaboratively collect sufficient data from point-of-interests (PoIs) in a timely manner. In this paper, we consider the GAS vehicular crowdsensing (VCS) campaign, where UGVs dispatch and callback UAVs periodically across multiple stops in the workzone, to maximize the total collected amount of data, geographic fairness while minimizing the energy consumption simultaneously. Specifically, we propose an energy-efficient, go-directed hierarchical multi-agent deep reinforcement learning (MADRL) method with discrete diffusion models called “gMADRL-VCS”, to optimize the high-level goal-conditioned navigation policies of UGVs, and the low-level long-term sensing strategies of UAVs. Extensive experimental results on two real-world datasets in Roma, Italy, and Hong Kong SAR, China show that gMADRL-VCS outperforms baselines in terms of energy efficiency, data collection ratio, energy consumption, and UAV-UGV cooperation factor.

Scene Graph Generation (SGG) aims to detect visual relationships in an image. However, due to long-tailed bias, SGG is far from practical. Most methods depend heavily on the assistance of statistics co-occurrence to generate a balanced dataset, so they are dataset-specific and easily affected by noises. The fundamental cause is that SGG is simplified as a classification task instead of a reasoning task, thus the ability capturing the fine-grained details is limited and the difficulty in handling ambiguity is increased. By imitating the way of dual process in cognitive psychology, a Visual-Textual Semantics Consistency Network (VTSCN) is proposed to model the SGG task as a reasoning process, and relieve the long-tailed bias significantly. In VTSCN, as the rapid autonomous process (Type1 process), we design a Hybrid Union Representation (HUR) module, which is divided into two steps for spatial awareness and working memories modeling. In addition, as the higher order reasoning process (Type2 process), a Global Textual Semantics Modeling (GTS) module is designed to individually model the textual contexts with the word embeddings of pairwise objects. As the final associative process of cognition, a Heterogeneous Semantics Consistency (HSC) module is designed to balance the type1 process and the type2 process. Lastly, our VTSCN raises a new way for SGG model design by fully considering human cognitive process. Experiments on Visual Genome, GQA and PSG datasets show our method is superior to state-of-the-art methods, and ablation studies validate the effectiveness of our VTSCN.

The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In this paper, we present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection by addressing three key aspects specifically tailored for this task. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context. To solve the problem of missing hard cases in the proposed output of the encoder in the current frame, we incorporate the output of the previous frame to initialize the query input of the decoder. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match. And similar queries are insufficiently suppressed and turn into redundant prediction boxes. To address this issue, our proposed IoU regularization term encourages similar queries to be distinct during the refinement. Through extensive experiments, we demonstrate the effectiveness of our approach in handling challenging scenarios, while incurring only a minor additional computational overhead.

For moving cameras, the video content changes significantly, which leads to inaccurate prediction in traditional inter prediction and results in limited compression efficiency. To solve these problems, first, we propose a camera pose-based background modeling (CP-BM) framework that uses the camera motion and the textures of reconstructed frames to model the background of the current frame. Compared with the reconstructed frames, the predicted background frame generated by CP-BM is more geometrically similar to the current frame in position and is more strongly correlated with it at the pixel level; thus, it can serve as a higher-quality reference for inter prediction, and the compression efficiency can be improved. Second, to compensate the motion of the background pixels, we construct a pixel-level motion vector field that can accurately describe various complex motions with only a small overhead. Our method is more general than other motion models because it has more degrees of freedom, and when the degrees of freedom are decreased, it encompasses other motion models as special cases. Third, we propose an optical flow-based depth estimation (OF-DE) method to synchronize the depth information at the codec, which is used to build the motion vector field. Finally, we integrate the overall scheme into the High Efficiency Video Coding (HEVC) and Versatile Video Coding (VVC) reference software HM-16.7 and VTM-10.0. Experimental results demonstrate that in HM-16.7, for in-vehicle video sequences, our solution has an average Bjøntegaard delta bit rate (BD-rate) gain of 8.02% and reduces the encoding time by 20.9% due to the superiority of our scheme in motion estimation. Moreover, in VTM-10.0 with affine motion compensation (MC) turned off and turned on, our method has average BD-rate gains of 5.68% and 0.56%, respectively.

Cost aggregation plays a critical role in existing stereo matching methods. In this paper, we revisit cost aggregation in stereo matching from disparity classification and propose a generic yet efficient Disparity Context Aggregation (DCA) module to improve the performance of CNN-based methods. Our approach is based on an insight that a coarse disparity class prior is beneficial to disparity regression. To obtain such a prior, we first classify pixels in an image into several disparity classes and treat pixels within the same class as homogeneous regions. We then generate homogeneous region representations and incorporate these representations into the cost volume to suppress irrelevant information while enhancing the matching ability for cost aggregation. With the help of homogeneous region representations, efficient and informative cost aggregation can be achieved with only a shallow 3D CNN. Our DCA module is fully-differentiable and well-compatible with different network architectures, which can be seamlessly plugged into existing networks to improve performance with small additional overheads. It is demonstrated that our DCA module can effectively exploit disparity class priors to improve the performance of cost aggregation. Based on our DCA, we design a highly accurate network named DCANet, which achieves state-of-the-art performance on several benchmarks.

In the past decade, backscatter communications have drawn significant attention as they are an ultra-low-power solution to transmit IoT sensor data, including video and audio. However, most of the state-of-the-art backscatter systems that are fully compatible with commodity radios suffer from poor synchronization accuracy and low throughput, being unable to support various multimedia sensors. In this paper, we propose Bitalign, a Bluetooth backscatter system that can make use of uncontrolled ambient signals as excitations and deliver high throughput for multimedia streaming applications. To do so, we identify several backscatter bottlenecks and employ a set of techniques to considerably boost backscatter throughput. In particular, we introduce an identification-based synchronization method that can efficiently distinguish various ambient signals and accurately decide where to modulate. We further propose a matching-based synchronization method with higher synchronization accuracy. In addition, we propose header reconstruction to make Bitalign truly compatible with commercial Bluetooth devices. Finally, we implement a tag prototype using FPGAs and conduct extensive experiments. Results show that the minimum bit error rate of Bitalign is 0.5%, which is 60 times better than that of FreeRider, a state-of-the-art Bluetooth system that features uncontrolled excitors. The maximal theoretical throughput of Bitalign is 1.98 Mbps.

Users tend to own multiple accounts on different location-based social network (LBSN) platforms, and they typically engage with diverse social circles on each platform within the same locations. Consequently, linking these accounts across separate networks becomes essential, playing a critical role in information fusion. Previous works accomplishing user identity linkage (UIL) utilize individual mobility records, which are significantly affected by the issue of data scarcity. In this paper, we propose EgoMUIL, a heterogeneous graph embedding approach specifically devised for information propagation, aiming to alleviate the scarcity problem to some extent. Considering that follow relations of respective networks also hold great significance for the UIL task, we are inspired to enrich individual limited mobility records through follow relations. Our preliminary research reveals that direct common follow relations are quite insufficient. Since the followers with the same spatio-temporal mode tend to have social connections, we first mine closely-related users for each user through topology and locality similarity, generating respective cross-domain ego-networks. Subsequently, we construct a heterogeneous ego-mo hypergraph consisting of mobility and ego-networks. We propose a novel graph convolutional network (GCN)-based approach to learn user representations, which enables the aggregation of information from surrounding nodes, incorporating topological similarities, stay locality similarities, and co-occurrence frequencies. The resulting embeddings provide comprehensive representations of users and locations, capturing their characteristics and relationships across platforms, which further facilitates the UIL task. Our experimental results on real-world check-in datasets from Foursquare and Twitter demonstrate that EgoMUIL outperforms the state-of-the-art methods on the UIL task. Notably, EgoMUIL exhibits superior performance in scenarios involving limited check-in records and follow relations.

Numerous sensor nodes deployed in the Internet of Things (IoT) can form a large heterogeneous network. The increased energy consumption of sensor nodes and the unbalanced communication load on multiple sink nodes reduce the energy efficiency of the network. Moreover, frequent network attacks also pose severe challenges to topology robustness. Optimizing the network topology to achieve the balance between energy efficiency and robustness is a complex problem. Multi-objective heuristic algorithms based on genetic evolution are commonly used to solve joint optimization problems. However, due to the lack of global search ability caused by the loss of genetic diversity, genetic operations are prone to premature convergence during multi-objective evolution. Therefore, this paper introduces multi-population cooperation into the multi-objective evolution process and proposes a novel layered-cooperation Topology Evolution Algorithm for Multi-sink IoT (TEAM). In TEAM, information entropy is used to measure the effectiveness of load balancing on multiple sink nodes. The crossover and mutation probabilities of different populations are dynamically adjusted to ensure genetic diversity. A layered-cooperation mechanism is designed to avoid premature convergence. Extensive experiments confirm that TEAM can effectively improve the energy efficiency and robustness of network topology while balancing the communication load on multi-sink nodes.

The robustness of scale-free Internet of Things (IoT) topology is seriously affected by malicious attacks. Improving the tolerance to node failures is critical to the stability of IoT systems. Heuristic algorithms, especially genetic algorithms, enhance the stability of network topology through the evolution of population chromosomes. However, the loss of genetic diversity makes the optimization easily fall into local optimum. Although the problem can be alleviated by adjusting population size and genetic probability, the genetic diversity is still not guaranteed in the limited number of iterations. Inspired by the quantum superposition that simultaneously operates on an exponential number of states, we propose a quantum-inspired robust networking model with multiverse co-evolution for the scale-free IoT (Q-Robust). This model designs quantum chromosomes with double-chain structures to represent the connections between all nodes. Then we present the quantum measurement method of quantum chromosomes based on the degree distribution of nodes. Furthermore, this model constructs a primary-secondary quantum multiverse co-evolution mechanism to improve the convergence efficiency of topology evolution. The experimental results show that the topology robustness optimized by Q-Robust is about 60% and 10% higher than the initial topology and the state-of-the-art topology evolution algorithm, respectively.

Fast-advancing mobile communication technologies have increased the scale of the Internet of Things (IoT) dramatically. However, this poses a tough challenge to the robustness of IoT networks when the network scale is large. In this paper, we present DAC-Motif, a distributed co-evolutionary method for optimizing network robustness based on network motifs. Unlike centralized evolutionary optimization approaches, DAC-Motif uses the technique of Divide-And-Conquer (DAC) to divide the large-scale IoT topology into partitions and then merge the self-evolving partitions into a global robust topology. This approach leverages both distributed computing and asynchronous communication mechanisms to mitigate premature convergence and reduce time complexity for large-scale IoT topologies. In our evaluation, DAC-Motif achieves three to four orders of magnitude shorter running time and over 10% robustness improvement compared to other centralized evolutionary algorithms under a scale of around 5,000 IoT devices.

A large number of distributed applications necessitate accurate network distance, for example, in the form of delay or latency, to ensure the Quality of Service (QoS). Due to high network measurement overhead and severe traffic congestion, network distance prediction has been introduced, instead of direct network measurements, to infer the unknown network distance with the partial measurements. However, most existing efforts neglect to fully capitalize on the potential latent factors, such as spatial correlations, long-existing temporal results and multi-rule exploration fusion, to achieve better accuracies with quicker convergence. To fill this gap, in this paper, we propose an Accurate Prediction of Network Distance (APND) solution via Federated Deep Reinforcement Learning (FDRL), which has four novel features distinguishing from the previous work. Firstly, a local feature-based matrix with low rank is established in each network cluster, referring to a set of neighbor nodes, to represent the potential spatial correlations among reachable node-pairs. Secondly, the parallel FDRL-based matrix factorization with multi-rule exploration fusion is introduced into APND and executed in all local clusters to minimize prediction errors and accelerate learning convergence. Thirdly, the long-existing learning experience is designed for local model training via Deep Reinforcement Learning (DRL) with rapid convergence. Fourthly, following the real-world routing paths, the cross-domain network nodes are simultaneously classified into adjacent clusters, built on the spatial correlations among them, and their coordinates will be further refined with error-based and average-based policies. Extensive experiments built on available real-world datasets illustrate that APND can accurately predict network distance compared with state-of-the-art approaches at the moderate computing cost.

Network Function Virtualization (NFV) introduces a new network architecture that offers different network services flexibly and dynamically in the form of Service Function Chains (SFCs), which refer to a set of Virtualization Network Functions (VNFs) chained in a specific order. However, the service latency often increases linearly with the length of SFCs due to the sequential execution of VNFs, resulting in sub-optimal performance for most delay-sensitive applications. In this paper, a novel Parallel VNF Placement (PVFP) approach is proposed for real-world networks via Federated Deep Reinforcement Learning (FDRL). PVFP has three remarkable characteristics distinguishing from previous work: 1) PVFP designs a specific parallel principle, with three parallelism identification rules, to reasonably decide partial VNF parallelism; 2) PVFP considers SFC partition in multi-domains built on their remaining resources and potential parallel VNFs to ensure that VNFs can be reasonably distributed for resource balancing among domains; 3) FDRL-based framework of parallel VNF placement is designed to train a global intelligent model, with time-variant local autonomy explorations, for cross-domain SFC deployment, avoiding data sharing among domains. Simulation results in different scenarios demonstrate that PVFP can significantly reduce the end-to-end latency of SFCs at the medium resource expenditures to place VNFs in multiple administrative domains, compared with the state-of-the-art mechanisms.

Topology robustness is critical to the connectivity and lifetime of large-scale Internet-of-Things (IoT) applications. To improve robustness while reducing the execution cost, the existing robustness optimization methods utilize neural learning schemes, including neural networks, deep learning, and reinforcement learning. However, insufficient exploration of reinforcement learning agents for topological environments is likely to yield local optima. Moreover, convergence speed is influenced by the sparse reward problem generated while exploring topological environments. To address these problems, this study proposes a self-adaptive robustness optimization method with an evolutionary multi-agent for IoT topology (ROMEM). ROMEM introduces a new multi-agent co-evolution scheme that leverages a non-deterministic strategy to extend the exploration in multi-directions, enabling the reinforcement learning agent to transcend local optima. Furthermore, ROMEM presents a novel distributed training mechanism for multiple agents to accelerate convergence. Experimental results demonstrate that ROMEM can achieve multi-directional collaborative training and outperform other state-of-the-art learning-based robustness optimization methods in terms of convergence efficiency and robustness.

Network operators often need to modify Access Control List (ACL) policies to align with to network upgrades. An essential part of the ACL update task is reachability satisfaction. Previous studies formalize reachability requirements as a set of constraints and then use Boolean Satisfiability (SAT) or Satisfiability Modulo Theories (SMT) solvers to search for solutions. However, as today’s networks grow in size and complexity, the constraints derived from the requirements become increasingly complex, leading to an unacceptable time cost to obtain a correct policy. The sluggish updating of ACL policies can affect the properties of a network, such as connectivity and security. This paper presents a novel approach for fast and scalable ACL policy synthesis under complex constraints. We utilize Graph Neural Networks (GNNs) to learn the relations between nodes and reason the solution that satisfies the update requirements. We further integrate global position encoding into the GNN architecture, which allows for better differentiation of nodes in ACL update tasks. Additionally, an enhanced stochastic local search solver is introduced to address incorrect predictions made by the GNN. Experiments on real-world topologies show that GNN saves up$278\times $time costs compared to advanced SAT/SMT solvers on a 125-node network, and this advantage expands with the network size. Furthermore, our model extrapolates well when faced with different requirements and topologies, demonstrating its ability to handle frequent network upgrades.

This paper studies the joint three-dimensional (3D) deployment and beamforming problem for a rate-splitting multiple access (RSMA)-enabled unmanned aerial vehicle base station (UBS) assisted by geographic information. Specifically, we maximize the minimum achievable rate among users by optimizing the beamforming, rate allocation and UBS deployment considering the power and building blockages constraints. To solve the intractable problem, an alternating optimization scheme is proposed. In particular, we first split the formulated problem into three sub-problems of deployment region modeling, joint beamforming and rate allocation, and 3D UBS deployment. For the first sub-problem, we define the allowable deployment region with geographic information with the aim of ensuring line-of-sight connections between the UBS and users. The feasible region is expressed as tractable constraints via the Big-M method and penalty function method. For the other sub-problems, semi-definite programming and successive convex approximation are employed to design the joint beamforming and rate allocation, and UBS deployment, respectively. These two sub-problems are optimized iteratively until convergence. Finally, numerical results validate the superiority of our proposed solution in comparison with the benchmark schemes with regard to the minimum achievable rate.

This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great potential of a pre-trained vision Transformer (ViT). Particularly, we delicately investigate plug-and-play training augmentations that encourage the ViT to bridge the vast distribution gap between the two modalities, enabling comprehensive cross-modal information interaction and thus enhancing its ability. Specifically, we propose a mask modeling strategy that randomly masks a specific modality of some tokens to enforce the interaction between tokens from different modalities interacting proactively. To mitigate network oscillations resulting from the masking strategy and further amplify its positive effect, we then theoretically propose an orthogonal high-rank loss to regularize the attention matrix. Extensive experiments demonstrate that our plug-and-play training augmentation techniques can significantly boost state-of-the-art one-stream and two-stream trackers to a large extent in terms of both tracking precision and success rate. Our new perspective and findings will potentially bring insights to the field of leveraging powerful pre-trained ViTs to model cross-modal data. The code is publicly available at https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker.

Neural network pruning is an essential technique for reducing the size and complexity of deep neural networks, enabling large-scale models on devices with limited resources. However, existing pruning approaches heavily rely on training data for guiding the pruning strategies, making them ineffective for federated learning over distributed and confidential datasets. Additionally, the memory- and computation-intensive pruning process becomes infeasible for recourse-constrained devices in federated learning. To address these challenges, we propose FedTiny, a distributed pruning framework for federated learning that generates specialized tiny models for memory-and computing-constrained devices. We introduce two key modules in FedTiny to adaptively search coarse- and finer-pruned specialized models to fit deployment scenarios with sparse and cheap local computation. First, an adaptive batch normalization selection module is designed to mitigate biases in pruning caused by the heterogeneity of local data. Second, a lightweight progressive pruning module aims to finer prune the models under strict memory and computational budgets, allowing the pruning policy for each layer to be gradually determined rather than evaluating the overall model structure. The experimental results demonstrate the effectiveness of FedTiny, which outperforms state-of-the-art approaches, particularly when compressing deep models to extremely sparse tiny models. FedTiny achieves an accuracy improvement of 2.61% while significantly reducing the computational cost by 95.91% and the memory footprint by 94.01% compared to state-of-the-art methods.

Personalized location prediction is key to many mobile applications and services. In this paper, motivated by both statistical and visualized preliminary analysis on three real datasets, we observe a strong spatiotemporal correlation for user trajectories among the visited area-of-interests (AoIs) and different time periods on both weekly and daily basis, which directly motivates our time-aware location prediction model design called "t-LocPred". It models the spatial correlations among AoIs by coarse-grained convolutional processing of the user trajectories in AoIs of different time periods ("ConvAoI"); and predicts his/her fine-grained next visited PoI using a novel memory-augmented attentive LSTM model ("mem-attLSTM") to capture long-term behavior patterns. Experimental results show that t-LocPred outperforms 8 baselines. We also show the impact of hyperparameters and the benefits ConvAoI can bring to these baselines.

We propose a novel face compression framework that leverages the external priors for joint human and machine perception under ultra-low bitrate scenarios. The proposed framework leverages the semantic richness of face images by representing the faces into sketches and thumbnails, resulting in improved bitrate utility for both human and machine vision. At the decoder side, the framework introduces a two-stage generative reconstruction, which faithfully enhances the reconstructed image via semi-parametric modeling and retrieved guidance from the external database. In particular, this coarse-to-fine strategy also results in improved identity consistency and analysis performance of the reconstructed image. Extensive evaluations of the proposed method have been conducted on the public face dataset by comparing it with end-to-end image compression techniques as well as traditional image compression standards. The experimental results demonstrate the effectiveness of the proposed method via superior perceptual and analytical performance under ultra-low bitrate conditions.

Abstract Recently, several in‐loop filtering algorithms based on convolutional neural network (CNN) have been proposed to improve the efficiency of HEVC (High Efficiency Video Coding). Conventional CNN‐based filters only apply a single model to the whole image, which cannot adapt well to all local features from the image. To solve this problem, an in‐loop filtering algorithm based on a dynamic convolutional capsule network (DCC‐net) is proposed, which embeds localized dynamic routing and dynamic segmentation algorithms into capsule network, and integrate them into the HEVC hybrid video coding framework as a new in‐loop filter. The proposed method brings average 7.9% and 5.9% BD‐BR reductions under all intra (AI) and random access (RA) configurations, respectively, as well as, 0.4 dB and 0.2 dB BD‐PSNR gains, respectively. In addition, the proposed algorithm has an outstanding performance in terms of time efficiency.

The emerging network-softwarization technologies, such as software-defined networking and network function virtualization play important roles in 5G communication and future networks. One of the critical challenges of the practical application of the softwarized networks is to appropriately place virtual network functions (VNFs). The underlying resources and traffic requirements are often factored in the previous works of VNF placement. However, VNFs’ dynamic abilities of changing traffic are usually ignored. Resources allocated to VNFs can vary their traffic-change ratios, and the adjustment of resource volumes should be provisioned to support traffic changes. In this work, we pay attention to the joint optimization problem of VNF Placement, CPU Allocation, and flow Routing (VNFPAR) in the scenarios consisting of VNFs that can dynamically change traffic. We employ the logarithmic functions to approximate VNFs’ traffic change relations and formulate VNFPAR as a mixed-integer nonlinear programming (MINLP) problem. We demonstrate that this problem is highly nonconvex and involves highly coupled variables. For small-scale VNFPAR problems, we propose an optimal algorithm based on relaxation and programming to consume the minimum bandwidth resources. Because VNFPAR is NP-hard, to quickly find near-optimal solutions for large-scale VNFPAR problems, we present heuristic algorithms based on multistage greedy and simulated annealing, respectively. Besides, to achieve a tradeoff between solution quality and execution time, we decompose VNFPAR into subproblems and design an alternating optimization-based method. We evaluate our algorithms on real-work topologies and traffic patterns. Extensive simulations show that our proposed heuristic algorithms are convergent, stable, and effective in terms of solving VNFPARs. The proposed algorithms have small optimality gaps within 7.4%–26.3%. Meanwhile, they save 39.3%–48.4% bandwidth resources compared with relevant baseline technologies.

Mobile-edge computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network’s edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of the Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, artificial intelligence (AI) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this article, we comprehensively provide a survey of security and privacy in MEC from the perspective of AI. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our-based framework while merging the software-defined network (SDN) and network function virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI. Finally, we comprehensively discuss the opportunities and challenges associated with applying AI to MEC security and privacy as possible future research directions.

Abundant real-time applications over Internet of Things (IoT) have imperative demands on timely information. Compared to average Age of Information (AoI), distribution of AoI characterizes the timeliness in more details. This article studies the timeliness of an IoT-based multisource status update system. By modeling the system as a multisource M/G/1/1 bufferless preemptive queue, general formulas of violation probabilities and probability density functions (p.d.f.s) of AoI and PAoI are derived based on a time-domain approach. For the case with exponentially distributed service time, the violation probabilities and p.d.f.s are obtained in closed form. To fully characterize the overall timeliness of the multisource system, the maximal violation probabilities of AoI and PAoI are proposed. To improve the overall timeliness under the resource constraint of IoT device, the arrival rate allocation is optimized to control the maximal violation probabilities. It is proved that the optimal arrival rates can be found by convex optimization. In particular, we show that the minimum of maximal violation probability of AoI (PAoI) is achieved only if all violation probabilities of AoI (PAoI) are equal. Finally, numerical results verify the theoretical analysis and show the effectiveness of the arrival rate allocation in improving the overall timeliness.

Federated Edge Learning considers a large amount of distributed edge nodes collectively train a global gradient-based model for edge computing in the Artificial Internet of Things, which significantly promotes the development of cloud computing. However, current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. This drawback directly results in expensive communication overhead for edge devices. Inspired by recent work on dataset distillation and distributed one-shot learning, we propose Distilled One-Shot Federated Learning (DOSFL) to significantly reduce the communication cost while achieving comparable performance. In just one round, each client distills their private dataset, sends the synthetic data to the server, and collectively trains a global model. The distilled data look like noise and are only useful to the specific model weights,i.e.,become useless after the model updates. With this weight-less and gradient-less design, the total communication cost of DOSFL is up to three orders of magnitude less than FedAvg while preserving up to 99% performance of centralized training on both vision and language tasks with different models including CNN, LSTM, Transformer,etc. We demonstrate that an eavesdropping attacker cannot properly train a good model using the leaked distilled data, without knowing the initial model weights. DOSFL serves as an inexpensive method to quickly converge on a performant pre-trained model with less than 0.1% communication cost of traditional methods.

Resource allocation for mobile edge computing (MEC) in unmanned aerial vehicle (UAV) networks has been a popular research issue. Different from existing works, this paper considers a multi-UAV-aided uplink communication scenario and investigates a resource allocation problem of minimizing the total system latency and the energy consumption, subject to constraints on transmit power of mobile users (MUs), system latency caused by transmission and computation. The problem is confirmed to be a challenging time-series mixed-integer non-convex programming problem, and we propose a joint UAV Movement control, MU Association and MU Power control (UMAP) algorithm to solve it effectively, where three sub-problems are optimized iteratively. Specifically, UAV movement and MU association are optimized utilizing deep reinforcement learning (DRL) to decrease the energy consumption and system latency. Next, a closed-form solution of the MU transmit power is derived. Finally, simulation results show that the UMAP algorithm can significantly decrease the system latency and energy consumption and increase the coverage rate compared with benchmark algorithms.

Unsupervised domain adaptation (UDA) aims to utilize knowledge from a label-rich source domain to understand a similar yet distinct unlabeled target domain. Notably, global distribution statistics across domains and local semantic characteristics across samples, are two essential factors of data analysis that should be fully explored. Most existing UDA approaches either harness only one of them or fail to closely associate them for efficient adaptation. In this work, we propose a unified framework, called Collaborative Alignment Framework (CAF), which simultaneously reduces the global domain discrepancy and preserves the local semantic consistency for cross-domain knowledge transfer in a collaborative manner. Specifically, for domain-oriented alignment, we utilize adversarial training or minimize the Wasserstein distance between the two distributions to learn domain-level invariant representations. For semantic-oriented matching, we capture the semantic discrepancy between the predictions of two diverse task-specific classifiers and enhance the features of target data to be near the support of the source data class-wisely, which promotes semantic consistency across domains effectively. These two adaptation processes can be deeply intertwined in CAF via collaborative training, thus CAF can learn domain-invariant and semantic-consistent feature representations. Extensive experiments on four popular benchmarks, including DomainNet, VisDA-2017, Office-31, and ImageCLEF, demonstrate the proposed methods significantly outperform the existing methods, especially on the large-scale dataset. The code is available athttps://github.com/BIT-DA/CAF.

With the rapid growth in the demand for location-based services in indoor environments, wireless fingerprint localization has attracted increasing attention because of its high precision and easy implementation. However, an effective method does not exist owing to the problems of data loss, noise interference in the fingerprint database, and being time-consuming during the offline training phase. Therefore, this paper presents a novel indoor wireless fingerprint localization algorithm, termed BLS-Location, based on a broad learning system (BLS) that utilizes channel state information (CSI) to overcome the aforementioned problems. It includes an offline training phase and an online localization phase. In the offline training phase, the Kalman filter and the expectation-maximization (EM) algorithm are utilized for completing and denoising the data. Moreover, principal component analysis (PCA) is used to reconstruct the CSI data to reduce complexity and train the weights by BLS. In the online localization phase, we employ a novel probabilistic method based on the regression results of BLS to obtain the estimated location. The experimental results show that BLS-Location can significantly reduce the training time with a high accuracy, compared to several machine learning algorithms and four existing methods in two representative indoor environments.

With the growing demand of Location-Based Service, the fingerprint localization based on Channel State Information (CSI) has become a vital positioning technology because it has easy implementation, low device cost and adequate accuracy which benefits from fine-grained information provided by CSI. However, the main drawback is that the approach has to construct the fingerprint map manually during the off-line stage, which is tedious and time-consuming. In this paper, we propose a novel data collection strategy for path planning based on reinforcement learning, namely Asynchronous Advantage Actor-Critic (A3C). Given the limited exploration step length, it needs to maximize the informative CSI data for reducing manual cost. We collect a small amount of real data in advance to predict the rewards of all sampling points by multivariate Gaussian process and mutual information. Then the optimization problem is transformed into a sequential decision process, which can exploit the informative path by A3C. We complete the proposed algorithm in two real-world dynamic environments and extensive experiments verify its performance. Compared to coverage path planning and several existing algorithms, our system not only can achieve similar indoor localization accuracy, but also reduce the CSI collection task.

The feature pyramid has been widely used in many visual tasks, such as fine-grained image classification, instance segmentation, and object detection, and had been achieving promising performance. Although many algorithms exploit different-level features to construct the feature pyramid, they usually treat them equally and do not make an in-depth investigation on the inherent complementary advantages of different-level features. In this article, to learn a pyramid feature with the robust representational ability for action recognition, we propose a novel collaborative and multilevel feature selection network (FSNet) that applies feature selection and aggregation on multilevel features according to action context. Unlike previous works that learn the pattern of frame appearance by enhancing spatial encoding, the proposed network consists of the position selection module and channel selection module that can adaptively aggregate multilevel features into a new informative feature from both position and channel dimensions. The position selection module integrates the vectors at the same spatial location across multilevel features with positionwise attention. Similarly, the channel selection module selectively aggregates the channel maps at the same channel location across multilevel features with channelwise attention. Positionwise features with different receptive fields and channelwise features with different pattern-specific responses are emphasized respectively depending on their correlations to actions, which are fused as a new informative feature for action recognition. The proposed FSNet can be inserted into different backbone networks flexibly, and extensive experiments are conducted on three benchmark action datasets, Kinetics, UCF101, and HMDB51. Experimental results show that FSNet is practical and can be collaboratively trained to boost the representational ability of existing networks. FSNet achieves superior performance against most top-tier models on Kinetics and all models on UCF101 and HMDB51.

Resource provisioning for the ever-increasing applications to host the necessary network functions necessitates the efficient and accurate prediction of required resources. However, the current efforts fail to leverage the inherent features hidden in network traffic, such as temporal stability, service correlation and periodicity, to predict the required resources in an intelligent manner, incurring coarse-grain prediction accuracies. To tackle this problem, in this paper, we propose an Accurate Prediction of Required virtual Resources (APRR) approach via Deep Reinforcement Learning (DRL). We first confirm the resource requests have more similar features and identify the high-dimensional required resources in computing, storage and bandwidth can be effectively consolidated into a single standardized value. Built upon these observations, we then model the required resources as a time-variant network matrix, which includes a number of elements, obtained from the network measurements, and some missing elements needed to be inferred. To obtain accurately predicted results, DRL-based matrix factorization with a set of available rules has been introduced into APRR and alternately executed in agent to minimize the prediction errors. Moreover, the error-prioritized designed for model training with quicker convergence. Simulation experiments on real-world datasets illustrate that APRR can accurately predict the required virtual resources compared with the related approaches.

This paper presents GeoDMA , which processes the GPS data from multiple vehicles to detect anomalous driving maneuvers, such as rapid acceleration, sudden braking, and rapid swerving. First, an unsupervised deep auto-encoder is designed to learn a set of unique features from the normal historical GPS data of all drivers. We consider the temporal dependency of the driving data for individual drivers and the spatial correlation among different drivers. Second, to incorporate the peer dependency of drivers in local regions, we develop a geographical partitioning algorithm to partition a city into several sub-regions to do the driving anomaly detection. Specifically, we extend the vehicle-vehicle dependency to road-road dependency and formulate the geographical partitioning problem into an optimization problem. The objective of the optimization problem is to maximize the dependency of roads within each sub-region and minimize the dependency of roads between any two different sub-regions. Finally, we train a specific driving anomaly detection model for each sub-region and perform in-situ updating of these models by incremental training. We implement GeoDMA in Pytorch and evaluate its performance using a large real-world GPS trajectories. The experiment results demonstrate that GeoDMA achieves up to 8.5% higher detection accuracy than the baseline methods.

Network Functions Virtualization (NFV), which decouples network functions from the underlying hardware, has been regarded as an emerging paradigm to provide flexible virtual resources for various applications through the ordered interconnection of Virtual Network Functions (VNFs), in the form of Service Function Chains (SFCs). In order to achieve the desired performance as dedicated hardware, how to efficiently deploy SFCs in NFV-enabled networks with limited resources is still a tremendous challenge. In this article, RQAP, an effective Resource and Quality of Service (QoS) Aware SFC Placement approach is proposed to mitigate this issue with the QoS-guaranteed service provisioning at acceptable resource consumption. With the Markov property of VNFs, the resource and QoS aware placement of SFCs is modeled as a Markov-chain-based optimization problem, where the set of all possible placement states on diverse nodes is regarded as a state space in the Markov chain and each state is jointly determined by the initial state and transition matrices. Furthermore, the SFCs associated with traffic requests are re-sorted so as to efficiently instantiate VNFs of the same type in a resource-saving manner. On this basis, an efficient Backward-Viterbi-based heuristic mechanism is presented to conduct the optimal VNF placement in Markov chain space, with the aim of consumed-resource reduction, along with the QoS-based instantiation of virtual links between adjacent VNFs. Simulation results conducted in several scenarios demonstrate that RQAP can significantly achieve a trade-off between resource consumption optimization and QoS guarantee. Besides, the results show that our proposed approach can also effectively improve the SFC acceptance ratio and achieve desirable load balancing and scalability.

Federated learning enables multiple distributed devices to collaboratively learn a shared prediction model without centralizing their on-device data. Most of the current algorithms require comparable individual efforts for local training with the same structure and size of on-device models, which, however, impedes participation from resource-constrained devices. Given the widespread yet heterogeneous devices nowadays, in this paper, we propose an innovative federated learning framework with heterogeneous on-device models through Zero-shot Knowledge Transfer, named by FedZKT. Specifically, FedZKT allows devices to independently determine the on-device models upon their local resources. To achieve knowledge transfer across these heterogeneous on-device models, a zero-shot distillation approach is designed without any prerequisites for private on-device data, which is contrary to certain prior research based on a public dataset or a pre-trained data generator. Moreover, this compute-intensive distillation task is assigned to the server to allow the participation of resource-constrained devices, where a generator is adversarially learned with the ensemble of collected on-device models. The distilled central knowledge is then sent back in the form of the corresponding on-device model parameters, which can be easily absorbed on the device side. Extensive experimental studies demonstrate the effectiveness and robustness of FedZKT towards on-device knowledge agnostic, on-device model heterogeneity, and other challenging federated learning scenarios, such as heterogeneous on-device data and straggler effects.

Indoor positioning technology based on Wi-Fi fingerprint recognition has been widely studied owing to the pervasiveness of hardware facilities and the ease of implementation of software technology. However, the similarity-based method is not sufficiently accurate, whereas the offline training of the neural network-based method is overly time consuming. An efficient model with high positioning accuracy is therefore not yet available. We propose a stacking ensemble broad learning localization system using channel state information as a fingerprint, which is termed EnsemLoca. A bootstrapping method is used to build the training set, which enables the EnsemLoca system to build the base learner in parallel by using bagging. The broad learning system (BLS), which is a novel neural network model, as a base learner, not only has the advantage of time complexity but also offers a sparse representation in which the features are filtered. A unique base learner is constructed by randomly selecting the samples and features, and they are combined by stack generalization. The experimental results show that the EnsemLoca system achieves higher accuracy than several machine-learning algorithms in both line-of-sight (LOS) and non-LOS environments, and is even stronger than deep neural networks characterized by accuracy. At the same time, it has the same theoretical complexity as BLS, which greatly reduces the offline training time.

Federated learning (FL) enables multiple clients to collaboratively build a global learning model without sharing their own raw data for privacy protection. Unfortunately, recent research still found privacy leakage in FL, especially on image classification tasks, such as the reconstruction of class representatives. Nevertheless, such analysis on image classification tasks is not applicable to uncover the privacy threats against natural language processing (NLP) tasks, whose records composed of sequential texts cannot be grouped as class representatives. The finer (record-level) granularity in NLP tasks not only makes it more challenging to extract individual text records, but also exposes more serious threats. This article presents the first attempt to explore the record-level privacy leakage against NLP tasks in FL. We propose a framework to investigate the exposure of the records of interest in federated aggregations by leveraging the perplexity of language modeling. Through monitoring the exposure patterns, we propose two correlation attacks to identify the corresponding clients when extracting their specific records. Extensive experimental results demonstrate the effectiveness of the proposed attacks. We have also examined several countermeasures and shown that they are ineffective to mitigate such attacks, and hence further research is expected.

Computational drug design relies on the calculation of binding strength between two biological counterparts especially a chemical compound, i.e., a ligand, and a protein. Predicting the affinity of protein-ligand binding with reasonable accuracy is crucial for drug discovery, and enables the optimization of compounds to achieve better interaction with their target protein. In this paper, we propose a data-driven framework named DeepAtom to accurately predict the protein-ligand binding affinity. With 3D Convolutional Neural Network (3D-CNN) architecture, DeepAtom could automatically extract binding related atomic interaction patterns from the voxelized complex structure. Compared with the other CNN based approaches, our light-weight model design effectively improves the model representational capacity, even with the limited available training data. We carried out validation experiments on the PDBbind v.2016 benchmark and the independent Astex Diverse Set. We demonstrate that the less feature engineering dependent DeepAtom approach consistently outperforms the other baseline scoring methods. We also compile and propose a new benchmark dataset to further improve the model performances. With the new dataset as training input, DeepAtom achieves Pearson's R=0.83 and RMSE=1.23 pK units on the PDBbind v.2016 core set. The promising results demonstrate that DeepAtom models can be potentially adopted in computational drug development protocols such as molecular docking and virtual screening.

Erasure coding is widely used in distributed storage systems (DSSs) to efficiently achieve fault tolerance. However, when the original data need to be updated, erasure coding must update every encoded block, resulting in long update time and high bandwidth consumption. Exiting solutions are mainly focused on coding schemes to minimize the size of transmitted update information, while ignoring more efficient utilization of bandwidth among update racks. In this article, we propose a parallel Cross-rack Pipelining Update scheme (CPU), which divides the update information into small-size units and transmits these units in parallel along with an update pipeline path among multiple racks. The performance ofCPUis mainly determined by slice size and update path. More slices bring finer-grained parallel transmissions over cross-rack links, but also introduces more overheads. An update path that traverses all racks with large-bandwidth links provide short update time. We formulate the proposed pipelining update scheme as an optimization problem, based on a new theoretical pipelining update model. We prove the optimization problem is NP-hard and develop a heuristic algorithm to solve it based on the features of practical DSSs and our implementations, includingBig chunkandSmall overhead. Specifically, we determine the best update path first by solving a max-min problem and then decide the slice size. We further simplify the slice size selection by offline learning a range of interesting (RoI), in which all slice sizes provide similar performance. We implementCPUand conduct experiments on Amazon EC2 under a variety of scenarios. The results show thatCPUcan reduce the average update time by 48.2 percent, compared with the state-of-the-art update schemes.

The statistical value of latencies between two sets of hosts over a given period, which is referred as to the statistical latency, can benefit many applications in the next-generation networks, for example, Network-in-a-Box-based resource provisioning. However, the existing methods can hardly achieve low measurement cost and high prediction accuracy simultaneously in large-scale scenarios. In this article, we design a light-weight statistical latency measurement platform named DMS (DNS-based statistical latency Measurement platform at Scale). DMS achieves high measurement accuracy by introducing a metric space to select the closest open recursive DNS (Domain Name System) server to a given host, and predicting the end-to-end latency between two hosts via the measured latency between the two corresponding DNS servers. To reduce the overall measurement overhead, DMS clusters the hosts in the metric space with the open recursive DNS infrastructure in the network as the cluster center, thus achieving low measurement cost and good scalability in large scale simultaneously. To evaluate the performance of DMS, we implement a prototype system in the network. Compared to the widely adopted method King, DMS can reduce the relative error by 18.5% for real-time end-to-end latency prediction and 33% for statistical latency prediction.

Personalized location prediction is key to many mobile applications and services. In this paper, motivated by both statistical and visualized preliminary analysis on three real datasets, we observe a strong spatiotemporal correlation for user trajectories among the visited area-of-interests (AoIs) and different time periods on both weekly and daily basis, which directly motivates our time-aware location prediction model design called “$t$t-LocPred”. It models the spatial correlations among AoIs by coarse-grained convolutional processing of the user trajectories in AoIs of different time periods (“ConvAoI”); and predicts his/her fine-grained next visited PoI using a novel memory-augmented attentive LSTM model (“mem-attLSTM”) to capture long-term behavior patterns. Experimental results show that$t$t-LocPred outperforms 8 baselines. We also show the impact of hyperparameters and the benefits ConvAoI can bring to these baselines.

Large volumes of video data recorded by the increasing mobile devices and embedded sensors can be leveraged to answer queries of our lives, physical world and our evolving society. Especially, the rapid development of convolutional neural networks (CNNs) in the past few years offers the great advantage for multiple tasks in video analysis. However, adopting running CNNs directly on mobile devices and embedded sensors for video analytics brings heavy burden due to their limited capacity, especially for learning a large volume of data. A promising approach is to outsource the computation-intensive part of CNN to cloud. However, the reveal of data to cloud may cause privacy leakage. In addition, the cloud-assisted approach may also bring some communication efficiency challenges for large volume of data. To address both privacy and efficiency issues, we design a privacy-preserving and computationally efficient framework for mobile video analytics. To protect the private information, we split the CNN model into two subnetworks, and first part is used as a feature extractor deployed in the mobile side and the second part is utilized as a classifier deployed in the cloud side. A specific-designed adversarial training process is adopted in order to extract features for normal task classification while hiding the features for sensitive task. In addition, to improve video process efficiency, we design a two-stage framework. The first stage is to extract key frames and necessary intermediate frames, while skipping redundant ones. The second stage is to extract the features of key frames by CNN-based feature extractor but apply optical-flow-based feature propagation algorithm to obtain the features of intermediate frames. Extensive experiments demonstrate our proposed system PrivacyEye can effectively protect private information while keep the accuracy of the normal tasks with less than 2 percent drop, and it saves up to 82.9 percent execution time and 78.8 percent energy consumption.

Internet of Things (IoT) includes numerous sensing nodes that constitute a large scale-free network. Optimizing the network topology to increase resistance against malicious attacks is a complex problem, especially on 3-dimension (3D) topological deployment. Heuristic algorithms, particularly genetic algorithms, can effectively cope with such problems. However, conventional genetic algorithms are prone to falling into premature convergence owing to the lack of global search ability caused by the loss of population diversity during evolution. Although this can be alleviated by increasing population size, the additional computational overhead will be incurred. Moreover, after crossover and mutation operations, individual changes in the population are mixed, and loss of optimal individuals may occur, which will slow down the population’s evolution. Therefore, we combine the population state with the evolutionary process and propose an Adaptive Robustness Evolution Algorithm (AREA) with self-competition for scale-free IoT topologies. In AREA, the crossover and mutation operations are dynamically adjusted according to population diversity to ensure global search ability. A self-competitive mechanism is used to ensure convergence. We construct a 3D IoT topology that is optimized by AREA. The simulation results demonstrate that AREA is more effective in improving the robustness of scale-free IoT networks than several existing methods.

The span of Internet of Things (IoT) is expanding owing to numerous applications being linked to massive devices. Subsequently, node failures frequently occur because of malicious attacks, battery exhaustion, or other malfunctions. A reliable and robust network topology can alleviate the cascading collapse caused by local node failures. Existing optimization methods for fixed topologies enhance the robustness of the IoT topology by reconstructing the connections among the devices. However, the application of existing algorithms requires global topology optimizations or local adjustments when new nodes are added, which leads to high computational complexity. To address this problem, based on neuroevolution and network motifs, this study proposes an evolutionary algorithm to generate a robust IoT topology called “Born This Way: a self-organizing evolution scheme with Motif” (BTW-Motif). Using novel mutation and crossover operators, BTW-Motif generates an IoT topology with intrinsic robustness when new nodes are added. We design an adaptive edge density control mechanism to avoid an increase in energy consumption resulting from redundant connections. Specifically, BTW-Motif innovatively introduces network motif as a guide structure which has been proven to have a positive effect on the network robustness. Experiments indicate that BTW-Motif can effectively produce a robust topology. With different network sizes and edge densities, BTW-Motif can generate more robust topologies compared with the existing topology optimization algorithms. And the time consumption for the large-scale topology to achieve similar robustness is reduced by 50%.

In the areas after natural disaster strikes, the ground communication network can be failed, due to the damage of the communication infrastructure. However, during or after the natural disasters such as earthquakes or tsunamis, ground vehicles may not enter the affected areas easily to set up mobile base stations. Unmanned Aerial Vehicles (UAVs) can be an alternate to provide emergency coverage for ground nodes (GNs). Therefore, how to determine the best location for UAV to achieve the maximum coverage is a key issue. In this paper, an adaptive UAV deployment scheme is proposed to solve the coverage problem of UAV- aided GNs communication. The objective is to optimize the location of the UAV to cover as many GNs as possible and reduce communication energy consumption. We construct a unique analysis method assisted by the collected ground information to solve this problem. First, we propose an information collection method based on the communication probability of Line-of-Sight (LoS) to guarantee the integrity of ground information acquisition. Then, based on the results of the information collection, a virtual obstacle model is built around each GN. Meanwhile, the UAV’s coverage problem is decomposed from the horizontal and vertical dimensions to simplify the difficulty of solving the problem. Finally, the best location of the UAV and the optimal transmission power of GNs can be obtained through the iterative methods and the power control, respectively. The extensive simulation results demonstrate that the proposed deployment scheme outperforms its counterparts.

3D human pose estimation (HPE) from a single image can be decomposed into two subtasks, i.e., 2D HPE followed by 2D-to-3D pose lifting. Despite recent success in 2D HPE, 3D pose regression from 2D detections remains challenging due to the substantial depth ambiguity. Recently, graph convolutional networks (GCNs) have been exploited to model the relationships among body joints and demonstrate promising results. In this paper, we go one step further along this direction and propose a novel framework, termed Compositional GCN, for 3D HPE. It learns compositional relationships among body parts of different semantic levels and then exploits multilevel structural reasoning to reduce the depth uncertainty. Furthermore, we introduce a novel part-aware graph convolution. It not only disentangles self and neighbor transformations but also captures different relational patterns between each part and their respective neighbors. Experimental results demonstrate the effectiveness of the proposed approach.

In this paper, we propose a single-agent Monte Carlo based reinforced feature selection (MCRFS) method, as well as two efficiency improvement strategies, i.e., early stopping (ES) strategy and reward-level interactive (RI) strategy. Feature selection is one of the most important technologies in data prepossessing, aiming to find the optimal feature subset for a given downstream machine learning task. Enormous research has been done to improve its effectiveness and efficiency. Recently, the multi-agent reinforced feature selection (MARFS) has achieved great success in improving the performance of feature selection. However, MARFS suffers from the heavy burden of computational cost, which greatly limits its application in real-world scenarios. In this paper, we propose an efficient reinforcement feature selection method, which uses one agent to traverse the whole feature set, and decides to select or not select each feature one by one. Specifically, we first develop one behavior policy and use it to traverse the feature set and generate training data. And then, we evaluate the target policy based on the training data and improve the target policy by Bellman equation. Besides, we conduct the importance sampling in an incremental way, and propose an early stopping strategy to improve the training efficiency by the removal of skew data. In the early stopping strategy, the behavior policy stops traversing with a probability inversely proportional to the importance sampling weight. In addition, we propose a reward-level interactive strategy to improve the training efficiency via reward-level external advice. Finally, we design extensive experiments on real-world data to demonstrate the superiority of the proposed method.

This paper is concerned with the resource allocation in a multi-unmanned aerial vehicle (UAV)-aided network for providing enhanced mobile broadband (eMBB) services for user equipments. Different from most of the existing network resource allocation approaches, we investigate a joint non-orthogonal user association, subchannel allocation and power control problem. The objective of the problem is to maximize the network energy efficiency under the constraints on user equipments' quality of service, UAVs' network capacity and power consumption. We formulate the energy efficiency maximization problem as a challenging mixed-integer non-convex programming problem. To alleviate this problem, we first decompose the original problem into two subproblems, namely, an integer non-linear user association and subchannel allocation subproblem and a non-convex power control subproblem. We then design a two-stage approximation strategy to handle the non-linearity of the user association and subchannel allocation subproblem and exploit a successive convex approximation approach to tackle the non-convexity of the power control subproblem. Based on the derived results, we develop an iterative algorithm with provable convergence to mitigate the original problem. Simulation results show that our proposed framework can improve energy efficiency compared with several benchmark algorithms.

Future wireless networks are envisioned to serve massive Internet of Things (mIoT) via some radio access technologies, where the random access channel (RACH) procedure should be exploited for IoT devices to access the networks. However, the theoretical analysis of the RACH procedure for massive IoT devices is challenging. To address this challenge, we first correlate the RACH request of an IoT device with the status of its maintained queue and analyze the evolution of the queue status by the probability theory. Based on the analysis result, we then derive the closed-form expression of the random access (RA) success probability, which is a significant indicator characterizing the RACH procedure of the device by the stochastic geometry theory. Besides, considering the agreement on converging different services onto a shared infrastructure, we investigate the radio access network (RAN) slicing for mIoT and bursty ultrareliable and low-latency communication (URLLC) service multiplexing. Specifically, we formulate the RAN slicing problem as an optimization one to maximize the total RA success probabilities of all IoT devices and provide URLLC services for URLLC devices in an energy-efficient way. A slice resource optimization (SRO) algorithm, exploiting relaxation and approximation with provable tightness and error bound, is then proposed to mitigate the optimization problem. Simulation results demonstrate that the proposed SRO algorithm can effectively implement the service multiplexing of mIoT and bursty URLLC traffic.

In mobile social networks (MSNs), mobile users communicate with each other via mobile devices, such as smartphones and tablets, transmitting data through intermittent connections. Mobile users have high mobility, which creates higher requirements for efficient data forwarding in MSNs. Therefore, forwarding data efficiently and quickly becomes a key problem. To tackle this problem, this article proposes a routing method based on a dynamic transient social community (DTSC) to optimize the routing and forwarding performance in MSNs. In this process, combined with the duration of intensive contact between nodes and the social relations of mobile users, the similarity of each pair of contact nodes is calculated, and community detection is carried out. Then, by analyzing the emergence mode of the DTSC, the measurement value and corresponding routing algorithm of the community’s ability to deliver messages are designed. Our algorithm fully considers the duration of the node’s direct encounter and the social connection of the indirect contact to ensure that the node can deliver successfully in a short time. The experimental results show that the DTSC has an excellent performance in data forwarding.

Internet of Underwater Things (IoUT) has a wide range of application prospects in civil and military fields. As a key enabling technology of IoUT, underwater acoustic sensor networks (UASNs) feature a variety of unique characteristics, including high latency, high mobility, and low bandwidth. All these problems pose challenges in the design of efficient and effective routing protocols. To address such challenges, we propose an adaptive-location-based routing protocol named ALRP for 3-D UASNs. First, the ALRP defines a forwarding area to confine the scope of the candidate forwarders. Second, it adaptively calculates the forwarding probability to reduce redundant forwarding. Third, it adaptively obtains the forwarding delay to determine the forwarding order. By using these ways, ALRP can find the beneficial relays to forward packets, and increase the forwarding efficiency. We implement the ALRP and evaluate its performance in the Aqua-sim. Simulation results show that the ALRP significantly improves the network performance compared to several existing protocols.

Unmanned aerial vehicle (UAV) relay networks are convinced to be a significant complement to terrestrial infrastructures to provide robust network capacity. However, most of the existing works either considered enhanced mobile broadband (eMBB) payload communication or ultra-reliable and low latency communications (URLLC) control information communication. In this paper, we investigate resource allocation for the eMBB payload and URLLC control information communication multiplexing in a multi-UAV relay network. We firstly propose a multi-UAV relay model comprehensively considering path loss, small-scale channel fading and different quality of service requirements of eMBB and URLLC communications. Then we formulate the multiplexing problem as a joint user association, bandwidth and transmit power optimization problem to improve total transmission data rate and reduce power consumption. The solution of this problem is challenging due to different capacity characteristics of eMBB and URLLC communications, the coupling of continuous variables and integer variables, and the non-convexity. To mitigate these challenges, we equivalently decompose the original optimization problem into a URLLC problem and an eMBB problem. For the URLLC problem, we derive closed-form expressions of the optimal bandwidth and transmit power. For the eMBB problem, we develop an iterative solution framework of alternatively optimizing user association, bandwidth and transmit power.

This paper is concerned with the security problem of Time of Arrival (ToA) based localization schemes in a wireless sensor network (WSN) with multiple attackers and this paper focuses on defending against external attacks, especially under cooperative external attackers. The prior scheme for defending against the attacks in the localization scheme often introduce high communication overhead and their security relies on the capability of the attackers. In this paper, we propose a lightweight secure ToA-based localization scheme in a WSN by exploiting the noise feature caused by external distance attacks. In comparison with the prior scheme, our scheme provides lower communication overhead and a higher level of security. We theoretically analyze the performance of the proposed scheme over fading channels and derive the closed-form expressions. We implemented our scheme and conducted extensive performance comparisons through simulations. Our experimental results show that the closed-form expressions for the detection performance perfectly match with their simulation results as we expected. The communication overhead of the proposed scheme is saved by 72.8% than that of the prior scheme for different numbers of anchors and is independent of the times of measurements.

Future wireless networks are convinced to provide flexible and cost-efficient services via exploiting network slicing techniques. However, it is challenging to configure slicing systems for bursty ultra-reliable and low latency communications (URLLC) service provision due to its stringent requirements on low packet blocking probability and low codeword decoding error probability. In this paper, we propose to orchestrate network resources for a slicing system to guarantee more reliable bursty URLLC transmission. We re-cut physical resource blocks and derive the minimum upper bound of bandwidth for URLLC transmission with a low packet blocking probability. We correlate coordinated multipoint beamforming with channel uses and derive the minimum upper bound of channel uses for URLLC transmission with a low codeword decoding error probability. Considering the agreement on converging diverse services onto shared infrastructures, we further investigate the network slicing for URLLC and enhanced mobile broadband (eMBB) service multiplexing. Particularly, we formulate the service multiplexing as an optimization problem, which is challenging to be mitigated due to requirements of future channel information and of tackling a two timescale issue. To address the challenges, we develop a resource optimization algorithm based on a sample average approximate technique and a distributed optimization method with provable performance guarantees.

Occupying the most significant portion of global data traffic, video is being generated in almost every aspect of our life. Because of its huge volume, we are depending much more heavily on machine intelligence based analysis. In the meantime, video coding technology has been continuously improved for better compression efficiency. However, the state-of-the-art video coding standards, such as H.265/HEVC and versatile video coding (VVC), are still designed assuming that the compressed video will be watched by a human later. Such a design is not optimal when the compressed video will be used by computer vision applications. While the human visual system (HVS) is consistently sensitive to the content with high contrast, the impact of pixels on computer vision algorithms is task driven. For example, because of the different categories of objects used to train detection algorithms, the influence of the same image content on those detectors also varies. Therefore, human oriented video coding strategies may not be optimal when the compressed signal is further processed by algorithms, as the encoder is unaware of the task specific information. In this article, taking object detection as an example, we propose a novel video coding strategy for computer vision. By protecting the information according to its importance for an object detector rather than for the human visual system, our proposed method has the potential to achieve a better object detection performance with the same bandwidth. The main contributions of our paper are: 1) the modeling of the relationship between object detection accuracy and bit rate; 2) a back propagation based method to analyze the influence of each pixel on the detection of target objects; 3) an object detection oriented bit allocation and codec control parameter determination scheme; 4) an evaluation metric to compare the impact of video coding strategies on a given object detector over a predefined range of bit rate. Experimental results demonstrate that our proposed algorithm can better preserve the video content vital for object detection than state-of-the-art video coding schemes.

By exploiting the massive data generated from the numerous interconnected machines and control systems, industrial Internet-of-Things (IIoT) provides unprecedented opportunities for facilitating the intelligence and smartness of manufacturing. Timely processing the large-scaled IIoT data by the conventional computation framework, such as Cloud computing, however, is nontrivial due to its costly resource usage, intolerable delay, and unbearable backbone pressures. By leveraging the idle resources of smart objects at the edge, mobile device cloud (MDC) becomes promising for the IIoT data analysis, thanks to the flexible resource provision and nearby task offloading. However, MDC workers are mostly human-carried devices with large scale, high dynamic resource provision, and untruthful behaviors, which pose significant challenges on MDC task allocation. In this article, we propose a blockchain-based decentralized and truthful framework for MDC (BC-MDC). BC-MDC enables the decentralization and prevents dishonesty by incorporating a plasma-based blockchain into the MDC. We design four smart contracts for distributedly managing the worker registration, task posting/allocation, rewarding, and penalizing. Furthermore, MDC task allocation is formulated as a stochastic optimization problem that jointly minimizes the long-term processing cost and risk of task failing. We also design a truthful reward/penalty algorithm that stimulates workers to provide resources and enforce them to keep the promise as well. Collaborated by the extensive simulation tests, we show how our proposed scheme achieves low cost on usage and high truthfulness and outperforms state-of-the-art solutions.

Random mobility models (RMMs) capture the random mobility patterns of mobile agents, and have been widely used as the modeling framework for the evaluation and design of mobile networks. All existing RMMs in the literature assume independent movements of mobile agents, which does not hold for unmanned aircraft systems (UASs). In particular, UASs must maintain a safe separation distance to avoid collision. In this paper, we propose a new modeling framework of random mobility models equipped with physical sense-and-avoid protocols to capture the flexible, variable, and uncertain movement patterns of UASs subject to separation safety constraints. For the random direction (RD) RMM equipped with a commonly used sense-and-avoid (S&A) protocol, named sense-and-stop (S&S), we provide its statistical properties including stationary location distribution and stationary inter-vehicle distance distribution, using the Markov analysis. This study provides knowledge on the impact of S&A protocols to critical UAS networking statistics. In addition, we define collision probabilities and airspace capacity concepts for UASs based on the inter-vehicle distance distribution, and derive their closed-form expressions. This analytical framework mathematically bridges local autonomy with global airspace capacity, and allows the impact analysis of local autonomy configurations for effective UAS airspace capacity management.

Mobile crowdsensing (MCS) represents a new sensing paradigm that utilizes the smart mobile devices to collect and share data. Traditional MCS systems mainly leverages the people carried smartphones and other wearable devices which are constrained by the limited sensing capability and battery power. With the popularity of unmanned vehicles like unmanned aerial vehicles (UAVs) and driverless cars, they can provide much more reliable, accurate and cost-efficient sensing services due to to their equipped more powerful sensors. In this paper, we propose a distributed control framework for energy-efficient and DIstributed VEhicle navigation with chaRging sTations, called “e-Divert”. It is a distributed multi-agent deep reinforcement learning (DRL) solution, which uses a convolutional neural network (CNN) to extract useful spatial features as the input to the actor-critic network to produce a real-time action. Also, e-Divert incorporates a distributed prioritized experience replay for better exploration and exploitation, and a long short-term memory (LSTM) enabled N-step temporal sequence modeling module. The solution fully explores the spatiotemporal nature of the considered scenario for better vehicle cooperation and competition between themselves and charging stations, to maximize the energy efficiency, data collection ratio, geographic fairness, and minimize the energy consumption simultaneously. Through extensive simulations, we find an appropriate set of hyperparameters that achieve the best performance, i.e., 5 actors in Ape-X architecture, priority exponent 0.5, and LSTM sequence length 3. Finally, we compare with four baselines including one state-of-the-art approach MADDPG. Results show that our proposed e-Divert significantly improves the energy efficiency, as compared to MADDPG, by 3.62 and 2.36 times on average when varying different numbers of vehicles and charging stations, respectively.

Convolutional neural networks (CNNs) have shown an effective way to learn spatiotemporal representation for action recognition in videos. However, most traditional action recognition algorithms do not employ the attention mechanism to focus on essential parts of video frames that are relevant to the action. In this article, we propose a novel global and local knowledge-aware attention network to address this challenge for action recognition. The proposed network incorporates two types of attention mechanism called statistic-based attention (SA) and learning-based attention (LA) to attach higher importance to the crucial elements in each video frame. As global pooling (GP) models capture global information, while attention models focus on the significant details to make full use of their implicit complementary advantages, our network adopts a three-stream architecture, including two attention streams and a GP stream. Each attention stream employs a fusion layer to combine global and local information and produces composite features. Furthermore, global-attention (GA) regularization is proposed to guide two attention streams to better model dynamics of composite features with the reference to the global information. Fusion at the softmax layer is adopted to make better use of the implicit complementary advantages between SA, LA, and GP streams and get the final comprehensive predictions. The proposed network is trained in an end-to-end fashion and learns efficient video-level features both spatially and temporally. Extensive experiments are conducted on three challenging benchmarks, Kinetics, HMDB51, and UCF101, and experimental results demonstrate that the proposed network outperforms most state-of-the-art methods.

The Internet of Things (IoT) has been extensively deployed in smart cities. However, with the expanding scale of networking, the failure of some nodes in the network severely affects the communication capacity of IoT applications. Therefore, researchers pay attention to improving communication capacity caused by network failures for applications that require high quality of services (QoS). Furthermore, the robustness of network topology is an important metric to measure the network communication capacity and the ability to resist the cyber-attacks induced by some failed nodes. While some algorithms have been proposed to enhance the robustness of IoT topologies, they are characterized by large computation overhead, and lacking a lightweight topology optimization model. To address this problem, we first propose a novel robustness optimization using evolution learning (ROEL) with a neural network. ROEL dynamically optimizes the IoT topology and intelligently prospects the robust degree in the process of evolutionary optimization. The experimental results demonstrate that ROEL can represent the evolutionary process of IoT topologies, and the prediction accuracy of network robustness is satisfactory with a small error ratio. Our algorithm has a better tolerance capacity in terms of resistance to random attacks and malicious attacks compared with other algorithms.

Deep learning (DL) models are increasingly built on federated edge participants holding local data. To enable insight extractions without the risk of information leakage, DL training is usually combined with differential privacy (DP). The core theme is to tradeoff learning accuracy by adding statistically calibrated noises, particularly to local gradients of edge learners, during model training. However, this privacy guarantee unfortunately degrades model accuracy due to edge learners' local noises, and the global noise aggregated at the central server. Existing DP frameworks for edge focus on local noise calibration via gradient clipping techniques, overlooking the heterogeneity and dynamic changes of local gradients, and their aggregated impact on accuracy. In this article, we present a systematical analysis that unveils the influential factors capable of mitigating local and aggregated noises, and design PrivateDL to leverage these factors in noise calibration so as to improve model accuracy while fulfilling privacy guarantee. PrivateDL features on: (i) sampling-based sensitivity estimation for local noise calibration and (ii) combining large batch sizes and critical data identification in global training. We implement PrivateDL on the popular Laplace/Gaussian DP mechanisms and demonstrate its effectiveness using Intel BigDL workloads, i.e., considerably improving model accuracy by up to 5X when comparing against existing DP frameworks.

This paper is concerned with slicing a radio access network (RAN) for simultaneously serving two 5G-and-Beyond typical use cases, i.e., enhanced mobile broadband (eMBB) and ultra-reliable and low-latency communications (URLLC). Although many researches have been conducted to tackle this issue, few of them have considered the impact of bursty URLLC. The bursty characteristic of URLLC traffic may significantly increase the difficulty of RAN slicing in terms of ensuring an ultra-low packet blocking probability. To reduce the probability, we re-visit the structure of physical resource blocks orchestrated for URLLC traffic based on theoretical results. Meanwhile, we formulate the problem of slicing a RAN enabling coordinated multi-point (CoMP) transmissions for multicast eMBB and bursty URLLC service multiplexing as a multi-timescale optimization problem aiming at maximizing eMBB and URLLC slice utilities, subject to physical resource constraints. To mitigate this problem, we transform it into multiple single timescale problems by exploring sample average approximations. An iterative algorithm with provable performance guarantees is developed to obtain solutions to these single timescale problems and aggregate obtained solutions into those of the multi-timescale problem. We also design a CoMP-enabled RAN slicing system prototype and compare the iterative algorithm with the state-of-the-art algorithm to verify its effectiveness.

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks.However, when paired with strong autoregressive decoders, VAE often converges to a degenerated local optimum known as "posterior collapse".Previous approaches consider the Kullback-Leibler divergence (KL) individual for each datapoint.We propose to let the KL follow a distribution across the whole dataset, and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL's distribution positive.Then we propose Batch Normalized-VAE (BN-VAE), a simple but effective approach to set a lower bound of the expectation by regularizing the distribution of the approximate posterior's parameters.Without introducing any new model component or modifying the objective, our approach can avoid the posterior collapse effectively and efficiently.We further show that the proposed BN-VAE can be extended to conditional VAE (CVAE).Empirically, our approach surpasses strong autoregressive baselines on language modeling, text classification and dialogue generation, and rivals more complex approaches while keeping almost the same training time as VAE.

Computer usage behaviour information can be used by anomaly detection algorithms to identify the current user of the computer system for security reasons. However, the data collected in this setup can be binary and very sparse, resulting in poor performance for some widely used anomaly detection methods. In this study, we propose a novel reconstruction criterion inspired by the F1score and the cross-entropy loss, that tackles the class imbalance problem introduced by binary and sparse data distribution with effectively merging reconstruction criterion calculated from vector elements of both positive and negative classes. Our experiments show that the proposed criterion can effectively improve the performance of reconstruction based anomaly detection methods, including both the PCA and the autoencoder.

Unmanned aerial vehicle (UAV) networks are convinced as a significant part of 5G and emerging 6G wireless networks. UAV slicing is a promising proposal of converging different services onto a common UAV network without deploying individual network solution for each type of service. This paper is concerned with UAV slicing for providing energy-efficient and fair service coverage for enhanced mobile broad-band (eMBB) users (UEs). Aiming at physically configuring UAV slices, the UAV slicing problem is formulated as a time-dependent mixed-integer-non-convex programming problem with a goal of maximizing all UEs' data rates while minimizing UAVs' total transmit power. To mitigate this challenging problem, we first decompose the original problem into two time-dependent subproblems using a Lyapunov approach. We then derive the procedure of tackling the non-convexity and the mixed-integer property of the subproblems by exploring a successive convex approximate (SCA) method and an alternative optimization scheme, respectively. Based on the derived results, we develop an algorithm with provable performance guarantees to mitigate the two subproblems repeatedly.

Spatial crowdsourcing (SC) utilizes the potential of a crowd to accomplish certain location based tasks. Although worker scheduling has been well studied recently, most existing works only focus on the static deployment of workers but ignore their temporal movement continuity. In this paper, we explicitly consider the use of unmanned vehicular workers, e.g., drones and driverless cars, which are more controllable and can be deployed in remote or dangerous areas to carry on long-term and hash tasks as a vehicular crowdsourcing (VC) campaign. We propose a novel deep reinforcement learning (DRL) approach for curiosity-driven energy-efficient worker scheduling, called "DRL-CEWS", to achieve an optimal trade-off between maximizing the collected amount of data and coverage fairness, and minimizing the overall energy consumption of workers. Specifically, we first utilize a chief-employee distributed computational architecture to stabilize and facilitate the training process. Then, we propose a spatial curiosity model with a sparse reward mechanism to help derive the optimal policy in large crowdsensing space with unevenly distributed data. Extensive simulation results show that DRL-CEWS outperforms the state-of-the-art methods and baselines, and we also visualize the benefits curiosity model brings and show the impact of two hyperparameters.

Internet of Things (IoT) includes numerous sensing nodes that constitute a large scale-free network. Optimizing the network topology for increased resistance against malicious attacks is an NP-hard problem. Heuristic algorithms, particularly genetic algorithms, can effectively cope with such problems. However, conventional genetic algorithms are prone to falling into premature convergence owing to the lack of global search ability caused by the loss of population diversity during evolution. Although this can be alleviated by increasing population size, additional computational overhead will be incurred. Moreover, after crossover and mutation operations, individual changes in the population are mixed, and loss of optimal individuals may occur, which will slow down the evolution of the population. Therefore, we combine the population state with the evolutionary process and propose an Adaptive Robustness Evolution Algorithm (AREA) with self-competition for scale-free IoT topologies. In AREA, the crossover and mutation operations are dynamically adjusted according to population diversity to ensure global search ability. Moreover, a self-competitive mechanism is used to ensure convergence. The simulation results demonstrate that AREA is more effective in improving the robustness of scale-free IoT networks than several existing methods.

Depth completion aims to estimate dense depth maps from sparse depth measurements. It has become increasingly important in autonomous driving and thus has drawn wide attention. In this paper, we introduce photometric losses in both spatial and time domains to jointly guide self-supervised depth completion. This method performs an accurate end-to-end depth completion of vision tasks by using LiDAR and a monocular camera. In particular, we full utilize the consistent information inside the temporally adjacent frames and the stereo vision to improve the accuracy of depth completion in the model training phase. We design a self-supervised framework to eliminate the negative effects of moving objects and the region with smooth gradients. Experiments are conducted on KITTI. Results indicate that our self-supervised method can attain competitive performance.

Industry 4.0 aims to create a modern industrial system by introducing technologies, such as cloud computing, intelligent robotics, and wireless sensor networks. In this article, we consider the multichannel access and task offloading problem in mobile-edge computing (MEC)-enabled industry 4.0 and describe this problem in multiagent environment. To solve this problem, we propose a novel multiagent deep reinforcement learning (MADRL) scheme. The solution enables edge devices (EDs) to cooperate with each other, which can significantly reduce the computation delay and improve the channel access success rate. Extensive simulation results with different system parameters reveal that the proposed scheme could reduce computation delay by 33.38% and increase the channel access success rate by 14.88% and channel utilization by 3.24% compared to the traditional single-agent reinforcement learning method.

The increasing Internet-of-Things (IoT) devices have produced large volumes of data. A deep learning technique is widely used to analyze the potential value of these data due to its unprecedented performance in both the academic and industrial communities. However, the data generated from the IoT devices are distributed among different users. Directly combining these data to a central server will cause privacy leakage, especially for personal sensitive data. Rather than centralized training by getting access to all these raw data, an alternative is to collaboratively learn a model in a distributed manner. However, there exist two main challenges in a distributed learning setting. The first one is how to preserve the privacy of users. The second one is to reduce the communication burden (e.g., mobile users have limited bandwidth) due to high-frequent data exchange. To address these two challenges, we design a communication efficient and privacy-preserving framework to enable different participants to distributively learn a model with a privacy protection guarantee. In particular, we develop a differentially private approximate mechanism for the distributed deep learning. In addition, we design a new gradient sparsification method to, at the first time, reduce both upload and download communication costs. The performance of the proposed framework is tested under different neural network structures for different data sets including, image classification and mobile sensor data. The experimental results demonstrate that we can reduce the communication up to only 2% compared to the full gradients exchange and achieve up to 16% accuracy increase compared to the previous works.

As a key technology of the Internet of Underwater Things (IoUT), underwater acoustic sensor networks (UASNs) have attracted considerable attention from both academia and industry. Due to specific characteristics of UWSNs, such as high latency, high mobility, and limited bandwidth, it is a challenge to design routing protocols for 3-D UASNs. In order to address these challenges, here, we propose a game-theoretic routing protocol (GTRP) for 3-D UASNs. First, the GTRP defines a forwarding area making the nodes closer to the destination inclined to forward. Then, it estimates the node degree in the forwarding area without broadcasting prior message periodically. Third, GTRP regards the forwarding process as a game. The number of participants in the game is the node degree information in the forwarding area, instead of the number of actual neighbors. To test the effectiveness of the proposed GTRP, we implement it and evaluate its performance in the Aqua-sim. The extensive simulations results indicate that GTRP significantly outperforms various existing protocols used for comparison, in terms of the number of received packets, the packet delivery fraction, and the end-to-end delay.

Unmanned aerial vehicle (UAV) with flexible mobility and low cost has been a promising technology for wireless communication. Thus, it can be used for wireless data collection in Internet of Things (IoT). In this article, we consider millimeter-wave (mmWave) communication on a UAV platform, where the UAV base station (UAV-BS) serves multiple ground users, which generate big sensor data. Both the deployment of the UAV-BS and the beamforming design have essential impact on the throughput of the system. Thus, we formulate a problem to maximize the achievable sum rate of all the users, subject to a minimum rate constraint for each user, a position constraint of the UAV-BS, and a constant-modulus (CM) constraint for the beamforming vector. We solve the nonconvex problem with two steps. First, by introducing the approximate beam pattern, we solve the deployment and beam gain allocation subproblem. Then, we utilize the artificial bee colony (ABC) algorithm to solve the beamforming subproblem. For the global optimization problem, we find the near-optimal position of the UAV-BS and the beamforming vector to steer toward each user, subject to an analog beamforming structure. The simulation results demonstrate that the proposed solution can achieve a more superior performance than the present random steering beamforming strategy in terms of achievable sum rate.

Faster-than-Nyquist signaling (FTNS) is capable of improving the spectral efficiency (SE) of communication systems. However, for conventional single-carrier FTNS (SC-FTNS) in which only symbol interval is reduced, the increase of SE is very limited due to the presence of inter-symbol interference (ISI) introduced by the FTNS. To deal with this problem, this paper proposes a new time-frequency compressed SC-FTNS (TFC-SC-FTNS) scheme that includes the conventional FTNS as a special case, to improve the SE via two dimensions simultaneously: time dimension by stacking symbols closer; frequency dimension by precoding to make the FTN signal spectrum more compact. Further, an optimization subject to a spectral mask constraint is performed on the precoder to suppress the ISI, according to a mean-square-error criterion, but the optimization problem is non-convex. A nontrivial contribution in the new scheme is that the non-convex problem is transformed into a convex one by a change of variable and an addition of admissibility constraint. Simulation results demonstrate that the proposed scheme significantly outperforms the conventional FTNS in terms of achievable SE or, equivalently, reception performance at a given SE. Further, with larger constellations applied, the gains of the TFC-FTNS increase.

As video data are occupying an increasingly more significant portion of global data traffic, video communication has become an indispensable component for most multimedia applications. As an enabling technology of video communication, although video coding is well standardized, the strategy to control video codec is highly customized to applications. The consistency of video quality is being paid more attention in many emerging applications. For example, in video surveillance, the quality of video frames should be stable in order to ensure the performance of machine intelligence algorithm, such as object detection precision. In this paper, we focus on achieving constant objective reconstruction quality in the process of video coding. To achieve certain rate-distortion performance, bit rate and distortion metric are usually modeled as a function of video content and control parameters of codec. For content modeling in existing work, there is still room for improvement, including the design of more efficient content feature, the compensation for assumption about constant RD characteristics among consecutive frames, and the adjustment of Lagrangian multiplier$\lambda $according to content property. The main contributions of this paper are: 1) a robust content adaptive model for residual bit rate modeling based on content statistics called mean absolute partial transformed difference (MAPTD); 2) a content-related header bit rate modeling; 3) preprocessing scheme for robust content feature estimation at scene change; 4) a distortion model consistent with local content; and 5) content adaptive$\lambda $determination. The experimental results show that our constant quality control strategy can achieve superior performance compared with the state-of-the-art algorithms.

The newest generation of video coding standard, high efficiency video coding (HEVC), significantly improves the video compression efficiency by introducing more flexible block partitioning structures and richer coding modes than those of the previous coding standards; however, the encoders suffer from high-computational complexity, which greatly hinders their extensive application. Extensive studies on optimizing the complexity of the HEVC encoders have been conducted. However, most studies do not effectively achieve a trade-off between the rate-distortion (RD) performance loss and complexity during the rate-distortion optimization (RDO). In this paper, we mathematically define the complexity-constrained RDO problem as a constrained optimization problem of subset selection. Next, based on the classification methodology, the derivation process for this optimization problem is simplified to find the adaptive threshold function in the feature space with extremely low complexity. The proposed method is also highly general and is applicable to algorithm design for various coding mode decisions, such as coding unit splitting, prediction unit partitioning and transform unit tree decision, and the global optimum can be achieved. Compared with existing methods, the experimental results show that the proposed method can reduce the coding time by 2-16% with the same RD performance loss and can decrease the BD rate by 0.1-1.2% under the same complexity. In addition, this method is capable of flexibly adjusting the complexity under different rate-distortion complexity trade-off requirements.

Due to the increasing medical data for coronary heart disease (CHD) diagnosis, how to assist doctors to make proper clinical diagnosis has attracted considerable attention. However, it faces many challenges, including personalized diagnosis, high dimensional datasets, clinical privacy concerns and insufficient computing resources. To handle these issues, we propose a novel blockchain-enabled contextual online learning model under local differential privacy for CHD diagnosis in mobile edge computing. Various edge nodes in the network can collaborate with each other to achieve information sharing, which guarantees that CHD diagnosis is suitable and reliable. To support the dynamically increasing dataset, we adopt a top-down tree structure to contain medical records which is partitioned adaptively. Furthermore, we consider patients' contexts (e.g., lifestyle, medical history records, and physical features) to provide more accurate diagnosis. Besides, to protect the privacy of patients and medical transactions without any trusted third party, we utilize the local differential privacy with randomised response mechanism and ensure blockchain-enabled information-sharing authentication under multi-party computation. Based on the theoretical analysis, we confirm that we provide real-time and precious CHD diagnosis for patients with sublinear regret, and achieve efficient privacy protection. The experimental results validate that our algorithm {outperforms} other algorithm benchmarks on running time, error rate and diagnosis accuracy.

Taking photos through a glass window leads to glare or reflection, which might distract the viewer from the scene behind the window. In this paper, we involve user interaction to tackle the ill-posedness of the reflection removal problem. Users are allowed to draw strokes or lassos to indicate the background and reflection layers. Instead of designing hand-crafted features, we propose the edge-aware cascaded networks for reflection removal. The proposed network is a two-stage pipeline. The first stage takes the edge hints converted from user guidance and the image with reflection as input, and then separates the input image into the background and reflection layers. The second stage involves a refinement network to recover the missing details of the background layers. We simulate different types of user guidance, and the networks are trained on simulated data. The cascaded networks are end-to-end and perform with a single feed-forward pass, enabling fast editing. Extensive experimental evaluations demonstrate that the proposed used-guided reflection removal network yields better performance than the state-of-the-art methods on real-world scenarios. Furthermore, we show that novice users can easily generate reflection-free images, and large improvements in reflection removal quality can be obtained in just one minute.

Visual domain adaptation aims to seek an effective transferable model for unlabeled target images by benefiting from the well-labeled source images following different distributions. Many recent efforts focus on extracting domain-invariant image representations via exploring target pseudo labels, predicted by the source classifier, to further mitigate the conditional distribution shift across domains. However, two essential factors are overlooked by most existing methods: 1) the learned transferable features should be not only domain invariant but also category discriminative; and 2) the target pseudo label is a two-edged sword to cross-domain alignment. In other words, the wrongly predicted target labels may hinder the class-wise domain matching. In this article, to address these two issues simultaneously, we propose a discriminative transfer feature and label consistency (DTLC) approach for visual domain adaptation problems, which can naturally unify cross-domain alignment with discriminative information preserved and label consistency of source and target data into one framework. To be specific, DTLC first incorporates class discriminative information by penalizing the maximum distance of data pair in the same class and the minimum distance of data pair sharing the different labels for each data into the distribution alignment of both domains. The target pseudo labels are then refined based on the label consistency within the domains. Thus, the transfer feature learning and coarse-to-fine target labels would be coupled to benefit each other in an iterative way. Comprehensive experiments on several visual cross-domain benchmarks verify that DTLC can gain remarkable margins over state-of-the-art (SOTA) nondeep visual domain adaptation methods and even be comparable to competitive deep domain adaptation ones.

Crowdsourcing uses collective intelligence to finish complicated tasks and is widely applied in many fields. However, the crowdsourcing dilemmas between the task requester and the task completer restrict the efficiency of system severely, e.g., the cooperation dilemma leads to the failure in the interactions and the quality of service dilemma results in the inability of task completer to provide high-quality service. Current research usually focuses on solving only one aforementioned dilemma and fails to integrate perfectly with the service architectural pattern of crowdsourcing systems. In this article, combined with the crowdsourcing interaction phase, we limit the objects that cause dilemma and propose a$\boldsymbol {t}$wo-stage$\boldsymbol {g}$ame$\boldsymbol {p}$ayoff$\boldsymbol {d}$ecision-making scheme (TGPD) to overcome these shortcomings. To solve the cooperation dilemma between the requester and the crowdsourcing platform, we first propose a dynamic payment method based on the reputation-quality rules for the task requester, and then develop a cos-evaluation algorithm to estimate platform’s cost, last design a co-determine algorithm to determine whether the platform adopts a cooperative strategy. To address the quality of service dilemma between the crowdsourcing platform and the workers, we first present an auction-screening method to estimate the reasonable recruitment range of workers which can be optimized by the result of cos-evaluation algorithm, and then use a reward distribution method to motivate workers to complete tasks with high quality and on time. The experimental results indicate that our new scheme successfully increases the worker’s and platforms’ payoffs at the same time, improves the accuracy of screening workers, enhances the worker’s quality of service, and decreases the platform’s cost.

Understanding the statistical latency between two groups of hosts in a period of time is of great significance to a wide variety of Internet applications and services, such as Service-Level Agreement (SLA) compliance monitoring and Virtual Network Function (VNF) placement. However, direct latency measurement methods are not always applicable to large-scale situations while the existing indirect methods often incur extra deployment costs or security problems. To address this challenge, we design an indirect method based on widely-distributed clients calledSSL(Surrogate-based method for large-scale Statistical Latency measurement).SSLestimates the latency between two arbitrary hosts using the measured latencies from several selected clients near one end host, which are called the host's surrogates, to the other end host. To overcome the limited capacity of the volatile clients with unstable CPU, memory, and bandwidth resources, we propose an innovative two-step measurement task assignment mechanism forSSLthat can achieve high accuracy measurement results while satisfying the resource constraints simultaneously. Moreover,SSLadopts a sampling technique to reduce the overhead in large-scale measurements, and a resampling technique to determine the confidence interval. Simulation experiments show thatSSLcan achieve more than 90 percent accuracy in most situations with 10 percent client density and 15 percent sampling rate.

This paper proposes a novel neural architecture — Attentive Tensor Product Learning (ATPL) — to represent grammatical structures of natural language in deep learning models. ATPL exploits Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, to integrate deep learning with explicit natural language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via the TPR-based deep neural network; 2) the use of attention modules to compute TPR; and 3) the integration of TPR with typical deep learning architectures including long short-term memory and feedforward neural networks. The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Our ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a natural language sentence. The experimental results demonstrate the effectiveness of the proposed approach in all these three natural language processing tasks.

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results from both automatic and human evaluations demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline.

Caching has advantages in mitigating the backhaul data traffic and multicast is able to satisfy multiple identical requests by a multicast stream, which are the two most promising technologies to realize tremendous data transmission in 5G networks. However, many studies focus on cooperative caching but ignore the problem that what contents to multicast for a given caching status by cooperation between base stations (BSs). In this paper, we consider the cooperative multicast scheduling problem in cache-enabled 5G networks to satisfy user demands while minimizing the energy consumption. We propose a novel pending request queue model and transform the cooperative multicast scheduling problem into a Lyapunov stochastic optimization problem that can be calculated on-line. By analyzing properties of the problem, we proposed an on-line centralized algorithm to obtain the optimal strategy. Motivated by practical deployment, we further propose a distributed algorithm which has similar performance and lower complexity. Extensive simulations have been conducted to verify that our algorithms have better performance than several state-of-art algorithms, including both energy consumption and delay.

With the development of e-commerce and smart cities, utilizing unmanned vehicles to deliver packages has emerged as one of the most important methods to make customers receive packages efficiently and effectively. Hence, how to reasonably utilize multiple unmanned vehicles at the same time is a problem. Another main challenging issue is how to satisfy customers' personalized need. In this paper, we propose a novel context-aware multi-armed bandit-based online learning algorithm with active partition method for context space. To solve the massive injecting data flow problem, we utilize a tree-based structure expanding from top to bottom to choose different vehicles, which supports ever-increasing big metering datasets with historical and contextual information. We prove that our proposed context-aware online learning algorithm achieves sublinear regret performance. Experiment results show our proposal can enhance customers' satisfaction and reduce space cost tremendously.

In this paper, we are concerned with exploring the theoretically and technically research outcomes for the conflict resolution (CR) of multiple unmanned aerial vehicles (UAVs) by using the Internet of Things technologies. We propose a satisficing algorithm to mitigate the CR problem of multiple UAVs. Specifically, we first formulate the CR problem as a game model and design strategies of the game model based on flight characteristics of UAVs. Next, a satisficing game theory is used to mitigate the formulated problem. Furthermore, required time of arrival, which is a new judgment parameter of the strategy utility, is developed to ensure that the whole system can reach a socially acceptable compromise. Simulation results verify the effectiveness and adaptability of the proposed algorithm under complex environments.

Information-centric networking (ICN) is of high interest to the Internet of Things (IoT) community, since the dissemination of massive data continuously produced by IoT devices can be easily handled by ICN’s data naming scheme and inherent multipath delivery. Providing optimal multipath-oriented transmission control is crucial for ICN-IoT data delivery, but yet remains challenging because of the randomness of request arrival, dynamic link condition, and on-path caching. More prominently, the resource limitation and scalability issues in IoT require the control scheme to be lightweight and distributed. In this paper, we propose a distributed stochastic optimization framework for multipath transmission control in ICN-IoT. The transmission control, including request scheduling and data rate regulation, is formulated as a stochastic concave optimization problem, which aims to accommodate the randomness, unpredictability, and multipath delivery of ICN-IoT and maximize the overall throughput. This problem is linearly separated into two subproblems: 1) a request scheduling problem and 2) a data rate control problem, which can be individually solved per time slot. A distributed alternating descent method (DADM) is designed to optimally control the transmission by solving the aforementioned problems at client sides. DADM enables each client to sequentially update the request schedule and rate regulation via communicating the links and providers they use, which asymptotically converges to optimality while allowing low-complexity and decentralized implementation. Validated by simulations, our DADM significantly improves throughput, delay reduction, and energy efficiency, in comparison with other state-of-the-art solutions.

With the explosion of smart devices and the gradual maturation of mobile systems, mobile crowdsensing (MCS) is playing more and more important roles in our daily life. In traditional MCS with a centralized framework, participants directly send perceived information to the task provider alone. This framework greatly increases the burden of cloud-based servers and cannot make full use of the increasing computation and storage capabilities of Internet of Things devices. To offload the computing and storage burden from traditional MCS architecture, a distributed MCS architecture was proposed in this paper, in which participants exchange sensing information with each other rather than forward it to central servers to complete a task together. Then, a diffusion Kalman filtering algorithm with quantized information exchange (QDKF) was proposed to solve the dynamic real-time estimate problem and limited communication resources in distributed MCS, where nodes exchange their quantized observations with neighbors to reduce the consumption of computing and storage resources. To prove the convergence and stability of the QDKF algorithm, an in-depth analysis of the algorithm uncertainty was reported to completely characterize the proposed solution. Moreover, the proposed algorithm achieves a superior performance by simulation.

As the prevalence of computing-intensive and delay-sensitive Internet of Things (IoT) applications, IoT service providers (SP) begin to deploy micro data centers in the edge and offload functions to them. However, more and more complex IoT applications require an ordered sequence of services across geographically distributed infrastructure to fulfil their functions, which poses grand challenges for IoT SP to deploy applications with low costs and high efficiency. To the best of our knowledge, no existing works have studied the deployment for an application with multilevel services (referred to as application deployment with multilevel services (ADMS) problem). To fill in the gap, we formulate the ADMS problem as an optimization problem with the aim of minimizing the overall deployment cost under the latency/computation/storage/bandwidth requirements and the infrastructure capacity limitations. We design a workflow-based heuristic algorithm called AMS, which can determine how many virtual machines (VMs) should be placed for each type of service and where to place them. AMS supports the services to scale up or scale down on demand in real time. Simulation experiments based on real network measurement demonstrate that AMS can reduce the number of deployed VMs by 28.4% and the deployment cost by 33.9% subject to comparable satisfied user ratio.

We propose a novel context-aware task allocation framework for mobile crowdsensing in the scenario of edge computing to enable the crowdsensing platform effectively and real-timely handle large-scale crowdsensing tasks in smart city. The task allocation performs in both cloud computing layer and edge computing layer. It aims to combine the merits of cloud and edge computing, i.e., diminishing communication latency while guaranteeing overall scheduling. The cloud layer evaluates the participants' task-oriented reputation based on the participants' background information, task context, and historical feedbacks (i.e., rewards) and sends the edge layer the most promising subset of participants. Then the edge layer communicates with the participants for the real-time information and makes optimization based on the task requirement (e.g., maximizing the sensing coverage under the constraint of the task budget). In the cloud layer, we propose a privacy-preserving and contextual online learning algorithm to manage the participants' reputation. The algorithm can adapt the decision-making strategy based on previous performances of participants. In the edge layer, plenty of existing centralized task allocation strategies can be directly applied to optimize based on the participants' real-time information. Theoretical analysis shows that our proposal achieves sublinear regret and differential privacy for both requesters and participants. Experiments results validate that our proposed algorithm supports increasing big dataset while striking a balance between the privacy-preserving level and the prediction accuracy.

Energy-saving (ES) systems developed on the basis of the Internet-of-Things (IoT) by heavily relying on automated understanding of human behaviors and activities recognition is of paramount importance in smart home. However, classic approaches are incapable to understand the relations among users' contexts and ES of appliances very well, and they cannot handle massive metering and time-varying user context datasets. Moreover, privacy concern is thoroughly aroused from both the residential and utility provider sides as to its essentiality. To tackle these problems, we propose a privacy-preserving and residential context-aware online ES (PRCOES) system in an IoT-enabled smart home environment. We model the repeated interaction of ES of appliances and the activity recognition of user context as a contextual multiarmed bandits (CMAB) problem, where the context-aware online learning algorithm can predict appropriate energy offers (EOs) that could meet the users' satisfaction, task completion rate, and ES purposes for appliances. We utilize a tree-based structure expanding from top to bottom to recommend EOs, which supports ever-increasing big metering datasets with user context-awareness. Theoretical analysis shows that our proposal achieves sublinear regret and differential privacy for both residents and utility provider. Experiments results validate that PRCOES could enhance users' experience and prolong users' engagement in everyday ES while guarantee the privacy for both residents and utility provider.

The advent of artificial intelligence and Internet of Things has led to the seamless transition turning the big data into the big knowledge. The deep learning models, which assimilate knowledge from large-scale data, can be regarded as an alternative but promising modality of knowledge for artificial intelligence services. Yet, the compression, storage, and communication of the deep learning models towards better knowledge services, especially over networks, pose a set of challenging problems on both industrial and academic realms. This paper presents the deep learning model communication paradigm based on multiple model compression, which greatly exploits the redundancy among multiple deep learning models in different application scenarios. We analyze the potential and demonstrate the promise of the compression strategy for deep learning model communication through a set of experiments. Moreover, the interoperability in deep learning model communication, which is enabled based on the standardization of compact deep learning model representation, is also discussed and envisioned.

In this paper, we investigate the combination of non-orthogonal multiple access and millimeter-wave communications (mmWave-NOMA). A downlink cellular system is considered, where an analog phased array is equipped at both the base station and users. A joint Tx-Rx beamforming and power allocation problem is formulated to maximize the achievable sum rate (ASR) subject to a minimum rate constraint for each user. As the problem is non-convex, we propose a sub-optimal solution with three stages. In the first stage, the optimal power allocation with a closed form is obtained for an arbitrary fixed Tx-Rx beamforming. In the second stage, the optimal Rx beamforming with a closed form is designed for an arbitrary fixed Tx beamforming. In the third stage, the original joint Tx-Rx beamforming and power allocation problem is reduced to a Tx beamforming problem by using the previous results, and a boundary-compressed particle swarm optimization (BC-PSO) algorithm is proposed to obtain a sub-optimal solution. Extensive performance evaluations are conducted to verify the rational of the proposed solution, and the results show that the proposed sub-optimal solution can achieve a significantly better performance in terms of ASR compared with those of the state-of-the-art schemes and the conventional mmWave orthogonal multiple access (mmWave-OMA) system.

Online video sharing (e.g., via YouTube or YouKu) has emerged as one of the most important services in the current Internet, where billions of videos on the cloud are awaiting exploration. Hence, a personalized video retrieval system is needed to help users find interesting videos from big data content. Two of the main challenges are to process the increasing amount of video big data and resolve the accompanying “cold start” issue efficiently. Another challenge is to satisfy the users’ need for personalized retrieval results, of which the accuracy is unknown. In this paper, we formulate the personalized video big data retrieval problem as an interaction between the user and the system via a stochastic process, not just a similarity matching, accuracy (feedback) model of the retrieval; introduce users’ real-time context into the retrieval system; and propose a general framework for this problem. By using a novelcontextualmultiarmed bandit-based algorithm to balance the accuracy and efficiency, we propose a context-based online big-data-oriented personalized video retrieval system. This system can support datasets that are dynamically increasing in size and has the property of cross-modal retrieval. Our approach provides accurate retrieval results withsublinearregret andlinearstorage complexity and significantly improves the learning speed. Furthermore, by learning for a cluster of similar contexts simultaneously, we can realize sublinear storage complexity with the same regret but slightly poorer performance on the “cold start” issue compared to the previous approach. We validate our theoretical results experimentally on a tremendously large dataset; the results demonstrate that the proposed algorithms outperform existing bandit-based online learning methods in terms of accuracy and efficiency and the adaptation from the bandit framework offers additional benefits.

The explosive growth of multimedia contents (MCs) in today's mobile social networks has pushed edge computing to face severe security and online big data-processing problems. On the one hand, the edge nodes (ENs) should help mobile users find, cache, and share MCs in the presence of an ever-increasing scale of multimedia big data. On the other hand, how to provide secure MC retrieval schemes to excludedishonest-and-maliciousuntrusted ENs and to prevent privacy breaches fromhonest-but-curiousENs and users is a challenging issue. To tackle these problems, we study the privacy-preserving and trustworthy MCs retrieval system to make personalized MC recommendations from ENs to users with big data support. In our framework, each EN is modeled as a distributed context-aware online learner. ENs collaborate to learn users’ preferences based on their contexts and previous behaviors and social intimacy. To support big data analytics, we establish an MC-cluster tree from top to the bottom to handle the dynamically varying cached MC datasets. A differentially private algorithm is proposed to preserve the data privacy among honest-but-curious ENs and users. To guarantee trustworthy edge computing, a trust evaluation mechanism is designed to evaluate the reliability of ENs. We further consider the structure of edge networks to improve the performance of our algorithm. Experimental results validate that our new framework can support increasing multimedia big datasets while striking a balance among privacy-preserving level, Trustworthy level, and caching MC prediction accuracy.

Due to the random delay, local maximum and data congestion in vehicular networks, the design of a routing is really a challenging task especially in the urban environment. In this paper, a distributed routing protocol DGGR is proposed, which comprehensively takes into account sparse and dense environments to make routing decisions. As the guidance of routing selection, a road weight evaluation (RWE) algorithm is presented to assess road segments, the novelty of which lies that each road segment is assigned a weight based on two built delay models via exploiting the real-time link property when connected or historic traffic information when disconnected. With the RWE algorithm, the determined routing path can greatly alleviate the risk of local maximum and data congestion. Specially, in view of the large size of a modern city, the road map is divided into a series of Grid Zones (GZs). Based on the position of the destination, the packets can be forwarded among different GZs instead of the whole city map to reduce the computation complexity, where the best path with the lowest delay within each GZ is determined. The backbone link consisting of a series of selected backbone nodes at intersections and within road segments, is built for data forwarding along the determined path, which can further avoid the MAC contentions. Extensive simulations reveal that compared with some classic routing protocols, DGGR performs best in terms of average transmission delay and packet delivery ratio by varying the packet generating speed and density.

Wireless sensor networks (WSNs) have been the popular targets for cyberattacks these days. One type of network topology for WSNs, the scale-free topology, can effectively withstand random attacks in which the nodes in the topology are randomly selected as targets. However, it is fragile to malicious attacks in which the nodes with high node degrees are selected as targets. Thus, how to improve the robustness of the scale-free topology against malicious attacks becomes a critical issue. To tackle this problem, this paper proposes a Robustness Optimization scheme with multi-population Co-evolution for scale-free wireless sensor networKS (ROCKS) to improve the robustness of the scale-free topology. We build initial scale-free topologies according to the characteristics of WSNs in the real-world environment. Then, we apply our ROCKS with novel crossover operator and mutation operator to optimize the robustness of the scale-free topologies constructed for WSNs. For a scale-free WSNs topology, our proposed algorithm keeps the initial degree of each node unchanged such that the optimized topology remains scale-free. Based on a well-known metric for the robustness against malicious attacks, our experiment results show that ROCKS roughly doubles the robustness of initial scale-free WSNs, and outperforms two existing algorithms by about 16% when the network size is large.

We consider the online shortest path routing (SPR) of a network with stochastically time varying link states under potential adversarial attacks. Due to the denial of service (DoS) attacks, the distributions of link states could be stochastic (benign) or adversarial at different temporal and spatial locations. Without any a priori, designing an adaptive and optimal DoS-proof SPR protocol to thwart all possible adversarial attacks is a very challenging issue. In this paper, we present the first such integral solution based on the multi-armed bandit (MAB) theory, where jamming is the adversarial strategy. By introducing a novel control parameter into the exploration phase for each link, a martingale inequality is applied in our formulated combinatorial adversarial MAB framework. The proposed algorithm could automatically detect the specific jammed and un-jammed links within a unified framework. As a result, the adaptive online SPR strategies with near-optimal learning performance in all possible regimes are obtained. Moreover, we propose the accelerated algorithms by multi-path route probing and cooperative learning among multiple sources, and study their implementation issues. Comparing to existing works, our algorithm has the respective 30.3% and 87.1% improvements of network delay for oblivious jamming and adaptive jamming given a typical learning period and a 81.5% improvement of learning duration under a specified network delay on average, while it enjoys almost the same performance without jamming. Lastly, the accelerated algorithms can achieve a maximal of 150.2% improvement in network delay and a 431.3% improvement in learning duration.

The integration of non-orthogonal multiple access in millimeter-Wave communications (mm Wave-NOMA) can significantly improve the spectrum efficiency and increase the number of users in the fifth-generation (5G) mobile communication and beyond. In this paper, we consider a downlink mm Wave-NOMA cellular system, where the base station is mounted with an analog beamforming phased array, and multiple users are served in the same time-frequency resource block. To guarantee user fairness, we formulate joint beamforming and power allocation problem to maximize the minimal achievable rate among the users, i.e., we adopt the max–min fairness. As the problem is difficult to solve due to the non-convex formulation and high dimension of the optimization variables, we propose a sub-optimal solution, which makes use of the spatial sparsity in the angle domain of the mm Wave channel. In the solution, the closed-form optimal power allocation is obtained first, which reduces the joint optimization problem into an equivalent beamforming problem. Then, an appropriate beamforming vector is designed. The simulation results show that the proposed solution can achieve a near-upper-bound performance in terms of achievable rate, which is significantly better than that of the conventional mm Wave orthogonal multiple access (mm Wave-OMA) system.

This paper investigates the application of non-orthogonal multiple access in millimeter-Wave communications (mmWave-NOMA). Particularly, we consider downlink transmission with a hybrid beamforming structure. A user grouping algorithm is first proposed according to the channel correlations of the users. Whereafter, a joint hybrid beamforming and power allocation problem is formulated to maximize the achievable sum rate, subject to a minimum rate constraint for each user. To solve this non-convex problem with high-dimensional variables, we first obtain the solution of power allocation under arbitrary fixed hybrid beamforming, which is divided into intra-group power allocation and inter-group power allocation. Then, given arbitrary fixed analog beamforming, we utilize the approximate zero-forcing method to design the digital beamforming to minimize the inter-group interference. Finally, the analog beamforming problem with the constant-modulus constraint is solved with a proposed boundary-compressed particle swarm optimization algorithm. The simulation results show that the proposed joint approach, including user grouping, hybrid beamforming and power allocation, outperforms the state-of-the-art schemes and the conventional mmWave orthogonal multiple access system in terms of achievable sum rate, and energy efficiency.

With the advances of artificial intelligence, recent years have witnessed a gradual transition from the big data to the big knowledge. Based on the knowledge-powered deep learning models, the big data such as the vast text, images and videos can be efficiently analyzed. As such, in addition to data, the communication of knowledge implied in the deep learning models is also strongly desired. As a specific example regarding the concept of knowledge creation and communication in the context of Knowledge Centric Networking (KCN), we investigate the deep learning model compression and demonstrate its promise use through a set of experiments. In particular, towards future KCN, we introduce efficient transmission of deep learning models in terms of both single model compression and multiple model prediction. The necessity, importance and open problems regarding the standardization of deep learning models, which enables the interoperability with the standardized compact model representation bitstream syntax, are also discussed.

Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Wu. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

We study in this paper the problems of both image captioning and text-to-image generation, and present a novel turbo learning approach to jointly training an image-to-text generator (a.k.a. CaptionBot) and a text-to-image generator (a.k.a. DrawingBot). The key idea behind the joint training is that image-to-text generation and text-to-image generation as dual problems can form a closed loop to provide informative feedback to each other. Based on such feedback, we introduce a new loss metric by comparing the original input with the output produced by the closed loop. In addition to the old loss metrics used in CaptionBot and DrawingBot, this extra loss metric makes the jointly trained CaptionBot and DrawingBot better than the separately trained CaptionBot and DrawingBot. Furthermore, the turbo-learning approach enables semi-supervised learning since the closed loop can provide peudo-labels for unlabeled samples. Experimental results on the COCO dataset demonstrate that the proposed turbo learning can significantly improve the performance of both CaptionBot and DrawingBot by a large margin.

With the increasing quality of service (QoS) demands for indoor multimedia applications, millimeter wave (mmWave) communications are emerging as a promising candidate for the wireless personal area networks (WPANs). On the one hand, it has the advantage of providing several-Gbps transmission rate. However, due to the unique characteristics in 60-GHz frequency band, such as high propagation loss, beamforming is fully exploited for mmWave links to achieve directional transmission and reception. In this paper, we propose a novel QoS aware scheduling algorithm for concurrent transmission in mmWave WPANs based on coalition game. First, we formulate the problem of concurrent transmission scheduling into a non-convex integer programming problem. Then, we propose a coalition game based algorithm to maximize the number of flows satisfying the corresponding QoS requirements, while improving the network resource utilization effectively. Besides, our proposed algorithm converges to a Nash-stable equilibrium with greatly reduced complexity. Through extensive simulations under various system parameters, we demonstrate our scheme achieves better network performance in terms of the throughput and the number of flows scheduled successfully, compared with existed protocols.

With the prevalence of smart mobile devices and surveillance cameras, the traffic load within the Internet of Things (IoT) has shifted away from nonmultimedia data to multimedia traffics, particularly, the video content. However, the explosive demand for real-time video communication over wireless networks in IoT is constantly challenging both video coding and communication research communities. The state-of-the-art answer to this challenge is sliding-window-based delay-aware fountain (DAF) codes, which combine the channel-adaptive feature in rateless coding and the delay-aware feature in video coding. However, the high computational cost and large delay make it impractical for real-time streaming. To address this issue, we integrate the model predictive control (MPC) technique into DAF codes, so the complexity is lowered to an affordable level so that real-time video encoding is supported. Two schemes are developed in this paper: 1) DAF-S, the smallhorizon DAF codes and 2) DAF-O, the MPC-based DAF using video bit rate prediction. The advantages of both designs are validated through theoretical analysis and comprehensive experiments. The results of simulation experiments show that the decoding ratio of DAF-S is close to the global optimum in DAF codes, and higher than the other existing schemes; DAF-O outperforms the state-of-the-art real-time video communication algorithms.

This paper is concerned with path planning for unmanned aerial vehicles (UAVs) flying through low altitude urban environment. Although many different path planning algorithms have been proposed to find optimal or near-optimal collision-free paths for UAVs, most of them either do not consider dynamic obstacle avoidance or do not incorporate multiple objectives. In this paper, we propose a multiobjective path planning (MOPP) framework to explore a suitable path for a UAV operating in a dynamic urban environment, where safety level is considered in the proposed framework to guarantee the safety of UAV in addition to travel time. To this aim, two types of safety index maps (SIMs) are developed first to capture static obstacles in the geography map and unexpected obstacles that are unavailable in the geography map. Then an MOPP method is proposed by jointly using offline and online search, where the offline search is based on the static SIM and helps shorten the travel time and avoid static obstacles, while the online search is based on the dynamic SIM of unexpected obstacles and helps bypass unexpected obstacles quickly. Extensive experimental results verify the effectiveness of the proposed framework under the dynamic urban environment.

Welcome to the IEEE JSAC special issue onAirborne Communication Networks. The goal of this special issue is to disseminate the contributions in the field of airborne communication networks.

Owing to the explosive growth of requirements of rapid emergency communication response and accurate observation services, airborne communication networks (ACNs) have received much attention from both industry and academia. ACNs are subject to heterogeneous networks that are engineered to utilize satellites, high-altitude platforms (HAPs), and low-altitude platforms (LAPs) to build communication access platforms. Compared to terrestrial wireless networks, ACNs are characterized by frequently changed network topologies and more vulnerable communication connections. Furthermore, ACNs have the demand for the seamless integration of heterogeneous networks such that the network quality-of-service (QoS) can be improved. Thus, designing mechanisms and protocols for ACNs poses many challenges. To solve these challenges, extensive research has been conducted. The objective of this special issue is to disseminate the contributions in the field of ACNs. To present this special issue with the necessary background and offer an overall view of this field, three key areas of ACNs are covered. Specifically, this paper covers LAP-based communication networks, HAP-based communication networks, and integrated ACNs. For each area, this paper addresses the particular issues and reviews major mechanisms. This paper also points out future research directions and challenges.

The backpressure scheduling scheme has been applied in Internet of Things, which can control the network congestion effectively and increase the network throughput. However, in large-scale Emergency Internet of Things (EIoT), emergency packets may exist because of the urgent events or situations. The traditional backpressure scheduling scheme will explore all the possible routes between the source and destination nodes that cause a superfluous long path for packets. Therefore, the end-to-end delay increases and the real-time performance of emergency packets cannot be guaranteed. To address this shortcoming, this paper proposes EABS, an event-aware backpressure scheduling scheme for EIoT. A backpressure queue model with emergency packets is first devised based on the analysis of the arrival process of different packets. Meanwhile, EABS combines the shortest path with backpressure scheme in the process of next-hop node selecting. The emergency packets are forwarded in the shortest path and avoid the network congestion according to the queue backlog difference. The extensive experiment results verify that EABS can reduce the average end-to-end delay and increase the average forwarding percentage. For the emergency packets, the real-time performance is guaranteed. Moreover, we compare EABS with two existing backpressure scheduling schemes, showing that EABS outperforms both of them.

In this paper we consider the time-varying characteristics of practical wireless networks and propose a joint dynamic rate allocation and transmission scheduling optimization scheme for scalable video multirate multicast based on opportunistic routing (OR) and network coding. With OR the decision of optimal routes for scalable video coding layered streaming is integrated into the joint optimization formulation. The network throughput is also increased by taking advantage of the broadcast nature of the wireless shared medium and by network coding operations in intermediate nodes. To maximize the overall video reception quality among all destinations the proposed scheme can jointly optimize the video reception rate the associated routes to different destinations and the time fraction scheduling of transmitter sets that are concurrently transmitting in the shared wireless medium. By using dual decomposition and primal-dual update approach we develop a cross-layer algorithm in a fully distributed manner. Simulation results demonstrate significant network multicast throughput improvement and adaptation to dynamic network changes relative to existing optimization schemes.

High-dimensional data present in the real world is often corrupted by noise and gross outliers. Principal component analysis (PCA) fails to learn the true low-dimensional subspace in such cases. This is the reason why robust versions of PCA, which put a penalty on arbitrarily large outlying entries, are preferred to perform dimension reduction. In this paper, we argue that it is necessary to study the presence of outliers not only in the observed data matrix but also in the orthogonal complement subspace of the authentic principal subspace. In fact, the latter can seriously skew the estimation of the principal components. A reinforced robustification of principal component pursuit is designed in order to cater to the problem of finding out both types of outliers and eliminate their influence on the final subspace estimation. Simulation results under different design situations clearly show the superiority of our proposed method as compared with other popular implementations of robust PCA. This paper also showcases possible applications of our method in critically tough scenarios of face recognition and video background subtraction. Along with approximating a usable low-dimensional subspace from real-world data sets, the technique can capture semantically meaningful outliers.

In this paper, we investigate the combination of two key enabling technologies for the fifth generation wireless mobile communication, namely millimeter-wave (mm-wave) communications and non-orthogonal multiple access (NOMA). In particular, we consider a typical two-user uplink mm-wave-NOMA system, where the base station equips an analog beamforming structure with a single radio-frequency chain and serves two NOMA users. An optimization problem is formulated to maximize the achievable sum rate of the two users while ensuring a minimal rate constraint for each user. The problem turns to be a joint power control and beamforming problem, i.e., we need to find the beamforming vectors to steer to the two users simultaneously subject to an analog beamforming structure, and meanwhile control appropriate power on them. As direct search for the optimal solution of the non-convex problem is too complicated, we propose decomposing the original problem into two sub-problems that are relatively easy to solve: one is a power control and beam gain allocation problem, and the other is an analog beamforming problem under a constant-modulus constraint. The rationale of the proposed solution is verified by extensive simulations, and the performance evaluation results show that the proposed sub-optimal solution achieves a close-to-bound uplink sum-rate performance.

Recently, the forward error correction (FEC) codes are gaining popularity in video transmission community because of its capability of recovering lost packets in lossy wireless networks. The state-of-the-art scheme for FEC video transmission are the delay-aware fountain codes (DAF), which combine the ratelessness of fountain codes with the property of video coding. However, DAF assumes that all the data in the video has the same importance, thus every packet should have the equal chance to be decoded. In this work, in order to further adapt DAF to real-world video coding, we propose a method to integrate the unequal error protection (UEP) into DAF to provide additional protection for important bits. Different from the existing schemes, the proposed scheme does not impose any restriction on the importance profile, and it does not rely on any specific video coding standard. Most importantly, the proposed scheme is designed within the framework of DAF, so it neither requires any change on the DAF decoder or the protocol, nor any additional coordination between encoder and decoder. Simulation experiments show the proposed system achieves higher decoding ratios and PSNR compared to equal error protection (EEP) under the same network conditions.

This paper is concerned with the design of routing protocol capable of congestion mitigation for drone-cells communication networks where drone-cells remain stationary in the sky as relays. All of the (distance or hop-count based) existing routing protocols can perform well when the network is lightly loaded. Once the network is heavily loaded, a large number of packets might be backlogged in queues of network nodes since these protocols can not be aware of the network congestion condition. In this paper, we propose a queuing delay and transmission delay based routing protocol (QDTD) to relieve the network congestion caused by heavily loaded traffic. First, QDTD designs a novel ForWard-Back (FWB) queue architecture that significantly reduces the number of queues maintained at each network node. Second, both queuing delay and transmission delay are leveraged as a routing metric to enhance the performance of QDTD. Experimental results show that QDTD can effectively relieve the network congestion and reduce the overall network delay and achieve high throughput.

Wireless backhauling is a promising technology for Ultra-Dense Networks (UDN). Resource management for access and backhaul is a key issue. Different from conventional resource allocation approaches, we partition radio resources for access and backhaul, taking into account the impacts of cooperative transmission modes. This problem is formulated to maximize the area throughput of UDN to obtain the optimal resource partition and power allocation. It includes two coupling problems and thus is difficult to solve. Firstly we prove the power allocation problem i.e. beamforming problem can be equally decoupled from original problem. And then, the resource partition problem can be converted to a convex optimization problem. Finally, we can get the Pareto optimal solution to the original problem. Simulation results show the gains of the proposed approach.

In High Efficiency Video Coding (HEVC), a rate control module usually relies on a bitrate model (representing the bitrate as a function of video content statistics and control parameters of the codec) to control the encoder to achieve the target bitrate. Existing bitrate models are not accurate due to their sensitivity to dynamic change of video content. To address this limitation, this paper proposes a new bitrate model, which represents the bit rate of motion-compensated residual as a function of the statistics of Mean Absolute Partial Transformed Difference (MAPTD) of video content and Lagrange multiplier λ specifically, we observe that at the coefficient group level, the relationship between the bitrate and MAPT-D is stable against the variation of coding unit (CU) size, transform unit (TU) size, image resolution and content. Experimental results show that our model can achieve superior performance in frame-level residue-bit-rate estimation, compared with state-of-the-art bitrate models.

Millimeter wave MIMO systems have been proposed to achieve higher spectral efficiency via the hybrid beamforming structure, which consists of analog beamforming and digital beamforming. In analog beamforming, each antenna subarray generates a codebook based directional beam, which determines the equivalent MIMO channel. Then digital beamforming can be applied to fully exploit the spatial multiplexing gain of MIMO channels. In this paper, we propose a low complexity analog beam selection scheme to achieve near-optimal spectral efficiency. The core of our scheme is the beam selection criterion, which is derived from capacity analysis. Through simulations under different channel conditions, the near-optimal performance of our scheme is demonstrated, and our scheme is able to achieve good enough performance with a small number of candidate beam combinations.

In Video Coding, the Rate Distortion Optimization (RDO) is the key technique to choose the most efficient coded representation of raw video. Specifically, encoder selects an optimal combination of coding parameters from a fixed and discrete candidate set in the rate-distortion sense. As this process is computation intensive essentially, its practicality can be limited especially for real-time applications. Thus, it is worthwhile to reduce the complexity while still preserve its accuracy. To achieve this goal, we propose an efficient and low-complexity model to estimate the rate and distortion information. A CG level content-adaptive rate model is proposed to ensure the bit rate estimation is accurate and stable against the change of coding parameters and video content. For distortion modeling, an efficient quantization-free estimator is proposed. Extensive experimental results demonstrate that our method significantly reduces in average 34.6% of encoder complexity than existing works with marginal RD performance loss.

In order to prolong the lifetime of wireless sensor networks (WSNs), a low-duty-cycle mode is widely used to save the energy for sensor nodes. Under this mode, sensor nodes switch between active and dormant states, which incurs a high latency for traditional routing algorithms. To mitigate this, in this paper, the data collection problem in low-duty-cycle WSNs is formulated as a delay optimization problem of traffic flow with consideration of both congestion and collision, which is solved by a distributed algorithm based on network utility maximization. Our proposed distributed routing algorithm achieves a better tradeoff between latency and energy conservation than existing schemes, and our schemes can find a nearly global-optimal-path to achieve almost minimum average end-to-end (E2E) delay with less energy consumption. The computation complexity and energy consumption of the distributed algorithm are analyzed and evaluated in detail. The simulation results show that the proposed algorithm can achieve almost the same average E2E delay performance as the global optimal algorithm with less energy, and reduce the average E2E delay by about 30% than the shortest path algorithm when the data generation rate is high.

For large-scale Internet of Things (IoT), which located in the hostile environment where exists malicious nodes (MNs), the security of time synchronization is a critical and challenging issue. The malicious sensor nodes could decrease the accuracy of the whole network by broadcasting fake timestamp messages. In this paper, we propose a secure time synchronization model for large-scale IoT. In this model, a node utilizes its father node and grandfather node to detect the MN. By employing the model, a spanning tree topology which synchronizes to the reference nodes can be constructed hop by hop. Then a secure time synchronization protocol is developed to against fake timestamps, which adopts the secure model. We use NS2 as the simulation tool to evaluate our protocol, and compare the impact of fake timestamps in various circumstances with the pervious protocols TPSN and STETS. The experiment results show that our protocol is effective to prevent attacks from MNs.

Thanks to the rapid development of information technology, the size of a wireless network is becoming larger and larger, which makes spectrum resources more precious than ever before. To improve the efficiency of spectrum utilization, game theory has been applied to study efficient spectrum sharing for a long time. However, the scale of wireless networks in existing studies is relatively small. In this paper, we introduce a novel game called aggregative game and use it to model spectrum sharing in large-scale, heterogeneous, and dynamic networks. Meanwhile, the massive usage of the spectrum leads to easier divulgence of privacy of spectrum users, which calls for privacy and truthfulness guarantees. In a large decentralized scenario, each user has no priori about other users’ channel access decisions, which forms an incomplete information game. A “weak mediator,” e.g., the base station or licensed spectrum regulator, is introduced and it turns the incomplete spectrum sharing game into a complete one. This is essential in reaching a Nash equilibrium (NE). By utilizing past channel access experience, we propose an online learning algorithm to improve the utility of each user. We show that the learning algorithm achieves an NE over time and provides no regret guarantee for each user. Specifically, our mechanism admits an approximateex-postNE, and is joint differentially private and incentive-compatible. Efficiency of the approximate NE is evaluated, and innovative scaling law results are disclosed. We also provide simulation results to verify our analysis.

With the tremendous development of data science, using unstructured documents to analyze marketing dynamics is attracting a great deal of attention. In this letter, we propose an iterative scheme to extract the new words, which is often a bottleneck for Chinese natural language processing (NLP) in financial markets analysis. In contrast to existing static features, the key novelty is the proposed dynamic features that characterize the similarity of context patterns. Via iteration, distinguishable seed context patterns are extracted. Tested on a 203 MB corpus, 19 291 words representing emerging industries, entities, projects, and products were extracted with a precision of 89.8% and recall of 88.9%, which outperforms most competitor methods.

It is challenging to quantitatively assess image quality in real time without a reference image while achieving human-level perception performance. In this paper, we present a no-reference (NR) image quality assessment (IQA) method called BNB (an acronym for blurriness, noisiness, and blockiness). Our BNB method quantifies the blurriness, noisiness, and blockiness of a given image, which are considered as three critical factors affecting users' quality of experience. This method is rooted in the observation that for any image, the difference between any two adjacent pixel values follows a generalized Laplace distribution with zero mean. This Laplace distribution changes differently when the image experiences various types of artifacts, i.e., blurriness, noisiness, and blockiness. To construct a metric for each BNB artifact, we first extract features for each type of artifacting from the changing Laplace distribution and then identify the quantitative relationship between the feature value and the variation of the artifact. Given human perception scores of a popular image database, we use the k-nearest neighbor algorithm to map our three BNB metrics of an image to a human perception score. Experimental results reveal that the image quality score obtained from our BNB method has higher correlation with human perceptual scores in addition to requiring notably less computation compared with existing NR IQA methods.

This paper studies the problem of jamming-resistant spectrum aggregation and access (SAA) for energy-efficiency (EE) cognitive radio communications. We consider various jamming behaviors, where jammers may attack all available channels with arbitrarily changing strategies over time, attack a subset of the channels at certain time slots, or have different intelligence, i.e., oblivious or adaptive adversary, and so on. Without any priori knowledge about the channels and jammers, it is very challenging to design an efficient and practical jamming-resistant SAA algorithm to reach the optimal EE goal. In this paper, we utilize the advanced martingale concentration inequalities in an multi-armed bandits-based online learning framework to facilitate the optimal detection of various jamming behaviors. We first define a novel EE model for discontiguous orthogonal frequency division multiplexing to facilitate scalable SAA over distributed spectrum pools in practice. Then, the jamming-resistant dynamic channel access problem is formulated as a regret minimization problem. Meanwhile, an online stochastic gradient descent with bandit feedback procedure is adopted to allocate the transmit power. The proposed algorithm can autonomously detect the environmental features and find a near-optimal solution in each attacking scenario. Our algorithm is implemented with low complexity and with multiple users under some practical jamming scenarios. Extensive numerical studies show that under some practical jamming scenarios, our algorithm has an EE improvement of 45.3% over a fixed learning period, and an improvement of 82.5% in terms of learning duration compared with existing approaches.

This paper is concerned with providing radio access network (RAN) elements (supply) for flash crowd traffic demands. The concept of multi-tier cells [heterogeneous networks (HetNets)] has been introduced in 5G network proposals to alleviate the erratic supply–demand mismatch. However, since the locations of the RAN elements are determined mainly based on the long-term traffic behavior in 5G networks, even the HetNet architecture will have difficulty in coping up with the cell overload induced by flash crowd traffic. In this paper, we propose a proactive drone-cell deployment framework to alleviate overload conditions caused by flash crowd traffic in 5G networks. First, a hybrid distribution and three kinds of flash crowd traffic are developed in this framework. Second, we propose a prediction scheme and an operation control scheme to solve the deployment problem of drone cells according to the information collected from the sensor network. Third, the software-defined networking technology is employed to seamlessly integrate and disintegrate drone cells by reconfiguring the network. Our experimental results have shown that the proposed framework can effectively address the overload caused by flash crowd traffic.

This paper presents a hopless networking paradigm. Incorporating recent techniques of rateless codes, senders break packets into rateless information streams and each single stream automatically adapts to diverse channel qualities at all potential receivers, regardless of their hop distances. The receivers are capable of accumulating rateless information pieces from different senders and jointly decoding the packet, largely improving throughput. We develop a practical protocol, called HOPE, which instantiates the hopless networking paradigm. Compared with the existing opportunistic routing protocol family, HOPE best exploits the wireless channel diversity and takes full advantage of the wireless broadcast effect. HOPE incurs minimum protocol overhead and serves general networking applications. We extensively evaluate the performance of HOPE with indoor network traces collected from USRP N210s and Intel 5300 NICs. The results show that HOPE achieves 1.7× and 1.3× goodput gain over EXOR and MIXIT, respectively. We further implement HOPE on a sensor network testbed, achieving the goodput gains over CTP.

Due to the recent proliferation of cyber-attacks, improving the robustness of wireless sensor networks (WSNs), so that they can withstand node failures has become a critical issue. Scale-free WSNs are important, because they tolerate random attacks very well; however, they can be vulnerable to malicious attacks, which particularly target certain important nodes. To address this shortcoming, this paper first presents a new modeling strategy to generate scale-free network topologies, which considers the constraints in WSNs, such as the communication range and the threshold on the maximum node degree. Then, ROSE, a novel robustness enhancing algorithm for scale-free WSNs, is proposed. Given a scale-free topology, ROSE exploits the position and degree information of nodes to rearrange the edges to resemble an onion-like structure, which has been proven to be robust against malicious attacks. Meanwhile, ROSE keeps the degree of each node in the topology unchanged such that the resulting topology remains scale-free. The extensive experimental results verify that our new modeling strategy indeed generates scale-free network topologies for WSNs, and ROSE can significantly improve the robustness of the network topologies generated by our modeling strategy. Moreover, we compare ROSE with two existing robustness enhancing algorithms, showing that ROSE outperforms both.

Spreading a large file consisting of many packets over a mobile network is challenging due to the short meeting duration for each transmission. Moreover, two typical causes of inefficient file spreading are duplicate packet reception at the destination nodes and excessive overhead exchanges. We propose to employ fountain codes at the source node to jointly addresses the three issues: 1) each coded packet can be small enough to fit into the meeting duration; 2) duplicate packet reception is significantly reduced since each coded packet is innovative; and 3) overhead is greatly saved by using file-level ACK instead of packet-level ACK. We conduct performance analysis in terms of the source-to-destination file delay and source-to-destination file spreading time in both non-relaying and relaying scenarios. While packet duplication can be eliminated in the former scenario, there is still a non-trivial duplication probability if relaying is allowed. Therefore, we propose a fountain-coded two-hop relaying (FTTR) protocol to further reduce the packet duplication ratio so that the spreading performance does not degrade with network size. The file spreading time and packet duplication ratio of FTTR are derived in closed form and verified through simulations.

The explosive demand for live video streaming over wireless networks is constantly calling for innovations in both video coding and wireless communities. The state-of-the-art answer to this challenge are sliding-window-based Delay-Aware Fountain (DAF) codes, which combine the channel-adaptive feature in rateless coding and the delay-aware feature in video coding. However, a high computational cost is incurred during the per-window optimization of sampling pattern, making DAF codes impractical for live streaming. To solve this issue, we propose a novel online algorithm for DAF codes. By integrating the Model Predictive Control (MPC) technique into DAF codes, a finite length of horizon is imposed on the optimization algorithm. As a result, the complexity is lowered to an affordable level such that real-time video encoding is supported. Two schemes are developed in this paper: (i) DAF-M, the MPC-based DAF codes, and (ii) DAF-O, the online variant of DAF-M based on video bit rate prediction. The advantages of both designs are validated through comprehensive experiments. The results of simulation experiments show that the decoding ratio of DAF-M is close to the global optimum in DAF codes, and higher than the other existing schemes; DAF-O outperforms the state-of-the-art live streaming algorithms.

With the explosive growth of mobile data demand, small cells densely deployed underlying the homogeneous macro-cells are emerging as a promising candidate for the fifth generation (5G) mobile network. The backhaul communication for small cells poses a significant challenge, and with huge bandwidth available in the mmWave band, the wireless backhaul at mmWave frequencies can be a promising backhaul solution for small cells. In this paper, we propose the Maximum QoS-aware Independent Set (MQIS) based scheduling algorithm for the mmWave backhaul network of small cells to maximize the number of flows with their QoS requirements satisfied. In the algorithm, concurrent transmissions and the QoS aware priority are exploited to achieve more successfully scheduled flows and higher network throughput. Simulations in the 73 GHz band are conducted to demonstrate the superior performance of our algorithm in terms of the number of successfully scheduled flows and the system throughput compared with other existing schemes.

We propose a new security paradigm that makes cross-layer personalization a premier component in the design of security solutions for computer infrastructure and situational awareness. This paradigm is based on the observation that computer systems have a personalized usage profile that depends on the user and his activities. Further, it spans the various layers of abstraction that make up a computer system, as if the user embedded his own DNA into the computer system. To realize such a paradigm, we discuss the design of a comprehensive and cross-layer profiling approach, which can be adopted to boost the effectiveness of various security solutions, e.g., malware detection, insider attacker prevention and continuous authentication. The current state-of-the-art in computer infrastructure defense solutions focuses on one layer of operation with deployments coming in a "one size fits all" format, without taking into account the unique way people use their computers. The key novelty of our proposal is the cross-layer personalization, where we derive the distinguishable behaviors from the intelligence of three layers of abstraction. First, we combine intelligence from: a) the user layer, (e.g., mouse click patterns); b) the operating system layer; c) the network layer. Second, we develop cross-layer personalized profiles for system usage. We will limit our scope to companies and organizations, where computers are used in a more routine and one-on-one style, before we expand our research to personally owned computers. Our preliminary results show that just the time accesses in user web logs are already sufficient to distinguish users from each other,with users of the same demographics showing similarities in their profiles. Our goal is to challenge today's paradigm for anomaly detection that seems to follow a monoculture and treat each layer in isolation. We also discuss deployment, performance overhead, and privacy issues raised by our paradigm.

We consider the shortest path routing (SPR) problem of a network with time varying link metrics in unknown environments. Due to potential denial of service attacks, the distributions of link states could be stochastic (benign or i.i.d.), contaminated or adversarial (non-i.i.d.) at different temporal and spatial locations. Without any a priori, designing an adaptive SPR protocol to cope with all possible situations in practice optimally is a very challenging issue. In this paper, we present the first solution by formulating it as a multi-armed bandit problem. By introducing novel control parameters to explore link conditions, our proposed algorithms could automatically detect features of the environment within a unified framework and find the optimal SPR strategies with almost optimal learning performance in all possible cases over time. Moreover, we study important issues related to the practical implementation, such as decoupling route selection with multi-path route probing, cooperative learning among multiple sources, the cold-start issue and delayed feedback of our algorithm. Nonetheless, the proposed SPR algorithms can be implemented with low complexity and they are proved to scale very well with the network size. The efficacy of the proposed solutions is verified by simulations from the real tracedriven datasets. Comparing to existing approaches in a typical network scenario, our algorithm has a 65.3 percent improvement of network delay given a learning period and a 81.5 percent improvement of learning duration under a specified network delay.

60‐GHz millimetre‐wave (mm‐wave) communication is gradually becoming a promising candidate for the next generation wireless system to meet the demands of mobile applications. To compensate for high path loss, directional links are established in mm‐wave communication system, which adds opportunity for spatial reuse. As one of its most promising protocols for commercial production, IEEE 802.11ad standard provides a mechanism to support space‐time division multiple access (STDMA) within a single network. However, the interference level among different co‐channel networks is much lower than that inside a network, which provides greater potential for spatial reuse. In this study, based on the architecture and timing structure of IEEE 802.11ad, the authors propose a spatial reuse strategy among multiple co‐channel networks. They formulate the problem as a mixed‐integer non‐linear programming problem, and then propose an inter‐network STDMA scheduling algorithm, which considers clustering frame structure in IEEE 802.11ad, and combines greedy principle and mutual interference avoidance strategy. Extensive simulation results have shown that the proposed scheme enlarges total throughput in comparison with STDMA inside each network, as well as non‐STDMA scheme. Meanwhile, it achieves the lowest packet loss rate under heavy traffic load.

The papers in this special issue focus on cloud computing-based video processing and content sharing. With the rapid growth of IPTV and mobile video applications and driven by urgent demands from industry and users, video processing and content sharing technologies have received significant research attention in recent years. Cloud-based video processing and content sharing networks are promising technologies to orchestrate large-scale and efficient video distribution between mobile clients and multimedia cloud systems. The objective of this special issue is to identify and promote advancements in media cloud-based video processing and content sharing technologies to advance current and enable future anywhere and anytime video processing and streaming applications.

With the rapid growth in multimedia services and the enormous offers of video content in online social networks, users have difficulty in obtaining their interests. Therefore, various personalized recommendation systems have been proposed. However, they ignore that the accelerated proliferation of social media data has led to the big data era, which has greatly impeded the process of video recommendation. In addition, none of them has considered both the privacy of users' contexts (e.g., social status, ages, and hobbies) and video service vendors' repositories, which are extremely sensitive and of significant commercial value. To handle these problems, we propose a cloud-assisted differentially private video recommendation system based on distributed online learning. In our framework, service vendors are modeled as distributed cooperative learners, recommending videos according to user's context, while simultaneously adapting the video-selection strategy based on user-click feedback to maximize total user clicks (reward). Considering the sparsity and heterogeneity of big social media data, we also propose a novel geometric differentially private model, which can greatly reduce the performance loss. Our simulation shows the proposed algorithms outperform other existing methods and keep a delicate balance between the total reward and privacy preserving level.

Deep hierarchical representations of the data have been found out to provide better informative features for several machine learning applications. In addition, multilayer neural networks surprisingly tend to achieve better performance when they are subject to an unsupervised pretraining. The booming of deep learning motivates researchers to identify the factors that contribute to its success. One possible reason identified is the flattening of manifold-shaped data in higher layers of neural networks. However, it is not clear how to measure the flattening of such manifold-shaped data and what amount of flattening a deep neural network can achieve. For the first time, this paper provides quantitative evidence to validate the flattening hypothesis. To achieve this, we propose a few quantities for measuring manifold entanglement under certain assumptions and conduct experiments with both synthetic and real-world data. Our experimental results validate the proposition and lead to new insights on deep learning.

Joint FoUntain coding and Network coding (FUN) is proposed to boost information spreading over multi-hop lossy networks. The novelty of our FUN approach lies in combining the best features of fountain coding, intra-session network coding, and cross-next-hop network coding. This paper provides an in-depth study of FUN codes. First, we theoretically analyze the throughput of FUN codes. Second, we identify several practical issues that may undermine the actual performance, such as buffer overflow, and quantify the resulting throughput degradation. Finally, we propose a systematic design to overcome these issues. Simulation results in TDMA multi-hop networks show that our methods yield near-optimal throughput and are significantly better than fountain codes and existing network coding schemes.

Abstract Millimeter wave (mmWave) communications in 60 GHz band have become a hot topic in wireless communications. New medium access control (MAC) protocols are needed because of the fundamental differences between mmWave communications and existing other communication systems. In mmWave wireless personal area networks, the channel transmission rates of links vary significantly because of the difference in the distance between nodes, the accuracy of beamforming, and the existence of obstructions. Owning to the directivity of mmWave links, spatial reuse should be exploited to improve network capacity. In this paper, we develop a channel transmission rate aware directional MAC protocol, termed RDMAC, in which both the multirate capability of links and spatial reuse are exploited to improve network performance. RDMAC has two stages. The first stage measures the channel transmission rates of links, and a heuristic algorithm is proposed to compute near‐optimal measurement schedules with respect to the total number of measurements. The second stage accommodates the traffic demand of links, and a heuristic transmission scheduling algorithm is proposed to compute near‐optimal transmission schedules with respect to the total transmission time. Simulations under various traffic modes show that compared with existing protocols, RDMAC has lower network latency, higher network throughput, and also a good fairness performance. Copyright © 2014 John Wiley & Sons, Ltd.

The relay scheme and the corresponding rate performance are considered for a half-duplex relay channel in which the source can only transmit information with fixed power. As different relay strategies result in different rate performance, we first present a decision criterion for selecting between Decode-and-Forward (DF) and Compress-and-Forward (CF) strategies by thoroughly analyzing their achievable rate. Based on the analysis result, the maximum of the DF rate and CF rate can be achieved by strategy selection procedure. To further obtain a larger rate, we put forward a hybrid DF-CF scheme in which the strategy selection between DF and CF is combined with active relay power allocation efficiently. It is shown that the concave envelope of the maximum of DF rate and CF rate is achievable via our new developed hybrid scheme. For the convenience of implementation, we also present a suboptimal setting for the hybrid DF-CF scheme. Numerical results show that the suboptimal setting can achieve a rate approaching the maximal rate.

An economic motion and texture aware denosing framework is proposed to facilitate parallel hardware design. The denoising framework performs on a block basis and features a spatial and temporal predictor and then a linear denoising filter optimal in the Minimum Mean Square Error (MMSE) sense. We first analyze the texture and motion strength around the neighborhood of a noisy pixel and then produce an effective predictor to correlate with the pixel of interest. Both the predictor and the noisy pixel are input into the linear denoiser to finally remove the noise. This framework only refers the information of the neighborhood of a noisy pixel and explores the best spatial and temporal denoising ratio adaptive to its local characteristics. Experiments show that the proposed framework outperforms the traditional block based denoising method by 1–3 dB of PSNR in denoising quality and also achieves a 1–3 dB gain when using it in HEVC encoder.

This paper presents a hopless networking paradigm. Incorporating recent techniques of rateless codes, senders break packets into rateless information streams and each single stream automatically adapts to diverse channel qualities at all potential receivers, regardless of their hop distances. The receivers are capable of accumulating rateless information pieces from different senders and jointly decoding the packet, largely improving throughput. We develop a practical protocol, called HOPE, which instantiates the hopless networking paradigm. Compared with the existing opportunistic routing protocol family, HOPE best exploits the wireless channel diversity and takes full advantage of the wireless broadcast effect. HOPE incurs minimum protocol overhead and serves general networking applications. We extensively evaluate the performance of HOPE with indoor network traces collected from USRP N210s and Intel 5300 NICs. The results show that HOPE achieves 1.7x and 1.3x goodput gain over ExOR and MIXIT, respectively.

In fading channels, power allocation over channel state may bring a rate increment compared to the fixed constant power mode. Such a rate increment is referred to power allocation gain. It is expected that the power allocation gain varies for different relay protocols. In this paper, Decode-and-Forward (DF) and Compress-and-Forward (CF) protocols are considered. We first establish a general framework for relay power allocation of DF and CF over channel state in half-duplex relay channels and present the optimal solution for relay power allocation with auxiliary parameters, respectively. Then, we reconsider the power allocation problem for one hybrid scheme which always selects the better one between DF and CF and obtain a near optimal solution for the hybrid scheme by introducing an auxiliary rate function as well as avoiding the non-concave rate optimization problem. Simulation results show that the developed power allocation solutions bring significant rate gains in various fading relay channels compared to constant power allocation mode.

With the increased use of smart phones and mobile tablets, video encoding and streaming over wireless networks become a big concern. Real-time video service requires low end-to-end delay, which mainly consists of video encoding delay, queuing delay, and transmission delay. Previous works either assume video encoding delay to be constant or infinite and neglect it from end-to-end delay. However, encoding time has an effective impact on encoding rate (R) and distortion (D). Hence, the optimal R-D performance based on the assumption of infinite encoding time is neither accurate nor realistic. To achieve the optimal end-to-end performance under low delay constraint, we extend the traditional R-D model to a novel delay-rate-distortion (d-R-D) model, which quantifies the relationship among source coding time, rate, and distortion for IPPPP coding mode in H.264/Advanced Video Coding (AVC). On the other hand, a delay insensitive video communication application can afford hierarchical bidirectional prediction mode that introduces extra encoding delay than IPPPP mode in H.264/AVC, as it achieves higher encoding efficiency when delay is not a top priority. However, coding efficiency does not always increase with delay, and delay is not unlimited as well. How to maximize coding efficiency in hierarchical B mode with limited encoding time constraint is not a well-addressed problem. With the proposed d-R-D model, we can mathematically formulate this problem and provide a practical solution for the first time.

To address the problem of segmenting an image into sizeable homogeneous regions, this paper proposes an efficient agglomerative algorithm on the basis of modularity optimization. Given an oversegmented image that consists of many small regions, our algorithm automatically merges those neighboring regions that produce the largest increase in modularity index. When the modularity of the segmented image is maximized, the algorithm stops merging and produces the final segmented image. To preserve the repetitive patterns in a homogeneous region, we propose a feature on the basis of the histogram of states of image gradients and use it together with the color feature to characterize the similarity of two regions. By constructing the similarity matrix in an adaptive manner, the oversegmentation problem can be effectively avoided. Our algorithm is tested on the publicly available Berkeley Segmentation Data Set as well as the semantic segmentation data set and compared with other popular algorithms. Experimental results have demonstrated that our algorithm produces sizable segmentation, preserves repetitive patterns with appealing time complexity, and achieves object-level segmentation to some extent.

In addition to the rate-distortion (R-D) behavior, in a real-time wireless video communication system, the end-to-end delay would also significantly affect the overall video reception quality. To analyze, control, and optimize the R-D behavior under the end-to-end delay constraint, in this paper we extend the traditional R-D optimization (RDO) for the wireless video communication system and formulate a novel delay-RDO-based rate control problem, by investigating the allocation of end-to-end delay to different delay components. It aims at minimizing the average total end-to-end distortion under the transmission rate and end-to-end delay constraints, by a joint selection of both the source coding and the channel coding parameters. The wireless channel is represented by a finite-state Markov channel model characterizing the time-varying process and predicting the future channel condition. As applicable solutions, a practical algorithm based on the Lagrange multiplier approaches, Karush-Kuhn-Tucker conditions, and sequential quadratic programming methods is developed. The experimental results demonstrate the superiority of the proposed algorithm over the existing schemes.

This paper investigates collaborative task execution between a mobile device and a cloud clone for mobile applications under a stochastic wireless channel. A mobile application is modeled as a sequence of tasks that can be executed on the mobile device or on the cloud clone. We aim to minimize the energy consumption on the mobile device while meeting a time deadline, by strategically offloading tasks to the cloud. We formulate the collaborative task execution as a constrained shortest path problem. We derive a one-climb policy by characterizing the optimal solution and then propose an enumeration algorithm for the collaborative task execution in polynomial time. Further, we apply the LARAC algorithm to solving the optimization problem approximately, which has lower complexity than the enumeration algorithm. Simulation results show that the approximate solution of the LARAC algorithm is close to the optimal solution of the enumeration algorithm. In addition, we consider a probabilistic time deadline, which is transformed to hard deadline by Markov inequality. Moreover, compared to the local execution and the remote execution, the collaborative task execution can significantly save the energy consumption on the mobile device, prolonging its battery life.

Abstract Wireless sensor networks (WSNs) have been widely investigated in the past decades because of its applicability in various extreme environments. As sensors use battery, most works on WSNs focus on energy efficiency issues (e.g., local energy balancing problems) in statically deployed WSNs. Few works have paid attention to the global energy balancing problem for the scenario that mobile sensor nodes can move freely. In this paper, we propose a new routing protocol called global energy balancing routing protocol (GEBRP) based on an active network framework and node relocation in mobile sensor networks. This protocol achieves global energy efficiency by repairing coverage holes and replacing invalid nodes dynamically. Simulation and experiment results demonstrate that the proposed GEBRP achieves superior performance over the existing scheme. In addition, we analyze the delay performance of GEBRP and study how the delay performance is affected by various system parameters.Copyright © 2013 John Wiley & Sons, Ltd.

The capacity region of wireless networks with per-destination PD queueing model has been studied extensively in the literature. However, the PD queueing structure is not scalable because the number of queues in a node can be as large as the number of all possible source-destination pairs. In this work, we study the capacity region of wireless networks with per-link PL queueing model. The advantage of the PL queueing structure is that the number of queues in a node can be reduced significantly to the number of its neighboring nodes. In this paper, the capacity region of a wireless network with PL queueing structure is characterized, and a dynamic routing and power control policy, namely, DRPC-PL, is proposed to stabilize the network whenever the input rate is within the capacity region. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract In this paper, we propose a cross‐layer optimized geographic node‐disjoint multipath routing algorithm, that is, two‐phase geographic greedy forwarding plus. To optimize the system as a whole, our algorithm is designed on the basis of multiple layers' interactions, taking into account the following. First is the physical layer, where sensor nodes are developed to scavenge the energy from environment, that is, node rechargeable operation (a kind of idle charging process to nodes). Each node can adjust its transmission power depending on its current energy level (the main object for nodes with energy harvesting is to avoid the routing hole when implementing the routing algorithm). Second is the sleep scheduling layer, where an energy‐balanced sleep scheduling scheme, that is, duty cycle (a kind of node sleep schedule that aims at putting the idle listening nodes in the network into sleep state such that the nodes will be awake only when they are needed), and energy‐consumption‐based connectedk‐neighborhood is applied to allow sensor nodes to have enough time to recharge energy, which takes nodes' current energy level as the parameter to dynamically schedule nodes to be active or asleep. Third is the routing layer, in which a forwarding node chooses the next‐hop node based on 2‐hop neighbor information rather than 1‐hop. Performance of two‐phase geographic greedy forwarding plus algorithm is evaluated under three different forwarding policies, to meet different application requirements. Our extensive simulations show that by cross‐layer optimization, more shorter paths are found, resulting in shorter average path length, yet without causing much energy consumption. On top of these, a considerable increase of the network sleep rate is achieved. Copyright © 2014 John Wiley & Sons, Ltd.

Abstract In the hybrid simulation research, we investigate a new approach to build software virtual networks (SVNs) that are indistinguishable from their equivalent real live networks (LNs). We define the concept of ‘Network's Interactive Turing Test' based on the similar concept used in the artificial intelligence areas. Our goal is to actualize the interactive and indistinguishablereal–virtual interface pair(RVIP) for large‐scale computer network simulations. By RVIP's support, a single SVN is indistinguishable from its equivalent LN. In the entire hybrid system, multiple LNs and multiple SVNs are connected using many RVIPs in an arbitrary topology and at real time. To actualize RVIP, the following necessary conditions must be satisfied: (i) the performance of the underlying simulation platform must be faster than real time; (ii) all needed changes incurred by introducing any SVN into an LN scenario are put on the simulation's side. To interact with an SVN, RVIP requires that no change is made on any live node; (iii) an SVN doesnotexchange simulation events with LNs, that is, only standard IP protocol interactions between SVN and LN are allowed. (iv) Any LN can be dynamically plugged into the hybrid scenario at real time, just like being plugged into an equivalent purely LN. Compared with existing hybrid simulation efforts on NS‐3, QualNet's EXata and OPNET's system‐in‐the‐loop, in this paper, we use the actual RVIP implementation to show that RVIP is a better candidate to pass the Network's Interactive Turing Test owing to the following two advantages: (i) an interactive network tester can easily distinguish the existing hybrid networks from the LNs by using a live topology thatcannotbe simulated, for example, by including the entire live Internet. But RVIP is not vulnerable to such tests. RVIP can support hybrid scenarios with multiple SVNs and multiple LNs connected by an arbitrary network topology, and with the LNs on and off at anytime. (ii) Performance‐wise, our studies show that RVIP provides more efficient support in terms of common metrics such as larger throughput limit and smaller extra latency; thus, the simulated SVNs are more indistinguishable from their live counterparts. Copyright © 2014 John Wiley & Sons, Ltd.

Abstract With their proliferation and increasing capabilities, mobile devices with local wireless interfaces can be organized into delay‐tolerant networks (DTNs) that exploit communication opportunities arising out of the movement of their users. As the mobile devices are usually carried by people, these DTNs can also be viewed as social networks. Unfortunately, most existing routing algorithms for DTNs rely on relatively simple mobility models that rarely consider these social network characteristics, and therefore, the mobility models in these algorithms cannot accurately describe users’ real mobility traces. In this paper, we propose two predict and spread (PreS) message routing algorithms for DTNs. We employ an adapted Markov chain to model a node's mobility pattern and capture its social characteristics. A comparison with state‐of‐the‐art algorithms demonstrates that PreS can yield better performance in terms of delivery ratio and delivery latency, and it can provide a comparable performance with the epidemic routing algorithm with lower resource consumption. Copyright © 2013 John Wiley & Sons, Ltd.

In full-duplex Gaussian relay channels, neither Decode-and-Forward (DF) nor Compress-and-Forward (CF) can achieve a larger rate than the other for all the channel gain combinations. Combining DF and CF strategies, we show that a new achievable rate, which is the concave envelop of the maximal rate achieved by DF and CF with respect to the source power, is achievable. To this end, we actively adjust the transmission power of the source for different time and switch the transmission strategy between DF and CF according to the source power. It is proved that when the signal to noise ratio (SNR) of the source-destination link falls into a certain range, the new achievable rate is strictly larger than that achieved by pure DF and pure CF. The optimal power allocation and corresponding time proportions are also obtained. Numerical results show that the new achievable rate is also competitive with the rate achieved by superposing CF on DF. As strategy switching avoids complex codeword constructions, it is more practical than superposition structures to be implemented in relay systems.

In this paper, we extend the traditional rate-distortion optimization (RDO) for the end-to-end wireless video communication system and develop a novel delay-rate-distortion optimization (dRDO) based rate control (RC) algorithm, by investigating the allocation of end-to-end delay to different delay components. Tradeoffs regarding, respectively, source coding delay versus buffering delay and available source coding rate versus redundant rate incurred by channel coding, are coupled in the proposed dRDO algorithm. It targets at minimizing the average total end-to-end distortion under the transmission rate and end-to-end delay constraints, by joint selection of search range and quantization step size in source coding and channel code rate in channel coding. Experimental results demonstrate the superiority of the proposed dRDO algorithm over existing schemes.

The ever increasing traffic demand becomes a serious concern of mobile network operators. To solve this traffic explosion problem, there have been many efforts to offload the traffic from cellular links to direct communications among users. In this paper, we propose the framework of Traffic Offloading assisted by Social network services (SNS) via opportunistic Sharing in mobile social networks, TOSS, to offload SNS-based cellular traffic by user-to-user sharing. First we select a subset of users who are to receive the same content as initial seeds depending on their content spreading impacts in online SNSs and their mobility patterns in offline mobile social networks (MSNs). Then users share the content via opportunistic local connectivity (e.g., Bluetooth, Wi-Fi Direct, Device-to-device in LTE) with each other. The observation of SNS user activities reveals that individual users have distinct access patterns, which allows TOSS to exploit the user-dependent access delay between the content generation time and each user's access time for traffic offloading purposes. We model and analyze the traffic offloading and content spreading among users by taking into account various options in linking SNS and MSN trace data. The trace-driven evaluation demonstrates that TOSS can reduce up to 86.5% of the cellular traffic while satisfying the access delay requirements of all users.

Two user Gaussian interference channel (GIC) consists of two source-destination pairs which transmit independent messages and interfere with each other. The best achievable rate region, referred to HK sum rate bound, requires the sources to split the information into public messages and private messages. As Gaussian signaling holds the potential of approaching the capacity, finding the HK sum rate achieved by Gaussian signaling is of great importance. However, The optimal power allocation over messages for Gaussian signaling are not known yet This work clearly describes the optimal power allocation and corresponding sum rate achieved by Gaussian signaling without time sharing (TS) in closed form. It lays a foundation for finding the TS strategy achieving the optimal sum rate. The obtained power allocation indicates that without TS, message splitting may not be always necessary. Besides, the conditions for using and not using message splitting are also characterized in detail.

To address the problem of information spreading over lossy communication channels, this paper proposes a joint FoUntain coding and Network coding (FUN) approach. Different from the Transmission Control Protocol (TCP), our FUN approach is a mechanism of Forward Error Correction (FEC), which does not use retransmission for recovery of lost packets. The novelty of our FUN approach lies in combining the best features of fountain coding, intra-session network coding, and cross-next-hop network coding. As such, our FUN approach is capable of achieving unprecedented high throughput over lossy channels. Experimental results demonstrate that our FUN approach achieves higher throughput than the existing schemes for multihop wireless networks.

Vector quantisation provides better rate‐distortion performance over scalar quantisation even for a random vector with independent dimensions. However, the design and implementation complexity of vector quantisers is much higher than that of scalar quantisers. To reduce the complexity while achieving performance close to optimal vector quantisation or better than scalar quantisation, the authors propose a new quantisation scheme, which consists of transformation and scalar quantisation. The transformation is to decorrelate and raise the dimensionality of the input data, for example, to convert a two‐axis representation in two‐dimensional into a tri‐axis representation; then scalar quantisation is applied to each of the raised dimensions, for example, along three axes. The proposed quantiser is asymptotically optimal/suboptimal for low/high rate quantisation, especially for the quantisation with certain prime number of quantisation levels. The proposed quantiser has O ( N 2 ) design complexity, whereas the design complexity of VQ is O ( N !), where N is the number of quantisation levels per dimension. The experimental results show that the average bit‐rate achieves 0.4–24.5% lower than restricted/unrestricted polar quantisers and rectangular quantisers for signals of circular and elliptical Gaussian and Laplace distributions. It holds the potential of improving the performance of the existing image and video coding schemes.

ABSTRACT Detecting distributed abnormal events has become an increasingly significant task for efficient network management and operation. However, it is still challenging to uncover these distributed behaviors in backbone networks because of the voluminous amount of noisy, high‐dimensional traffic data. In this paper, we present a novel system for detecting distributed abnormal events in backbone networks. The proposed system emphasizes on detecting distributed correlated abnormal events, which are caused by the same reason. In contrast, existing methods are not able to distinguish correlated abnormal events from the independent abnormal events. In our proposed system, a set of data mining techniques is used for modeling and detecting distributed correlated abnormal events by analyzing the traffic features. Specifically, traffic behavior representation is constructed to define and select traffic features for describing the traffic behaviors of interest, feature clustering is performed to group together similar transformations in each feature, behavioral data mining is employed to discover the most significant patterns in network interactions with respect to typical behavior, and behavior classification is used to expose the behaviors of interest. Experiment results using real traffic data present the effectiveness of our proposed methods for detecting distributed correlated abnormal events in the backbone network. Copyright © 2013 John Wiley & Sons, Ltd.

Smart mobile phones are capable of performing video coding and streaming over wireless networks, but are often constrained by the end-to-end delay requirement and energy supply. To achieve optimal performance under the delay and energy constraints, in this paper we extend the traditional rate-distortion (R-D) model and the previously proposed delay R-D model to a novel delay-power-rate-distortion (d-P-R-D) model by including another two dimensions (the encoding time and encoder power consumption), which quantifies the relationship among source encoding delay, rate, distortion, and power consumption for IPPPP coding mode in H.264/AVC. We have verified the accuracy of our proposed d-P-R-D model through experiments. Based on the proposed d-P-R-D model, we develop a novel rate-control (RC) algorithm, which minimizes the encoding distortion under the constraints of rate, delay, and power. The experimental results demonstrate the superiority of the proposed RC algorithm over the existing scheme. Therefore, the d-P-R-D model and the model-based RC provide a theoretical basis and a practical guideline for the cross-layer system design and performance optimization in wireless video communication under delay and energy constraints.

Mobile video traffic, owing to the rapid adoption of smartphones and tablets, has been growing exponentially in recent years and started to dominate the mobile Internet. In reality, mobile video applications commonly adopt buffering techniques to handle bandwidth fluctuation and minimize the impact of stochastic wireless channels on user experiences. However, recent measurement work reveals that mobile users tend to abort more frequently than PC users during viewing videos. Such a high abortion rate results in a significant wastage of buffered video data, which is directly translated into monetary and energy cost for mobile users. In this paper, we propose an intelligent buffer management strategy called CBM (Cost-aware Buffer Management), for mobile video streaming applications. Our purpose is to minimize cost induced by un-consumed video data while respecting certain user experience requirements. To this objective, we formulate the problem into a constrained stochastic optimization problem, and apply the Lyapunov optimization theory to derive the corresponding online strategy for cost minimization. Different from conventional heuristic-based strategies, our proposed CBM strategy can provide provably performance guarantee with explicit bounds. We also conduct extensive simulations to validate the effectiveness of our proposed strategy and our experimental results show that CBM achieves significant gains over existing schemes.

Motivated by various applications in mobile ad-hoc networks (MANETs) that require nodes to share their individual information to each other, we study the multi-message dissemination problem in a MANET, which is to distribute multiple messages to all mobile nodes in the network in parallel. The objective is to minimize the stopping time, i.e., the time taking for all nodes to receive a copy of the whole messages. We consider an intrinsically one-sided protocol based on random linear network coding (RLNC), where all packets forwarded are in the form of random linear combinations of packets received so far. Its supreme performance is demonstrated theoretically for two cases, low mobility and high mobility, according to the node velocity. In particular, we show that, under general settings, our derived upper bounds of the stopping time match the established lower bound in both cases, although the effects of mobility in the two cases are significantly different. Thus, we conclude that RLNC achieves order optimality for fast information dissemination in MANETs.

Cloud is becoming a dominant computing platform. Naturally, a question that arises is whether we can beat notorious DDoS attacks in a cloud environment. Researchers have demonstrated that the essential issue of DDoS attack and defense is resource competition between defenders and attackers. A cloud usually possesses profound resources and has full control and dynamic allocation capability of its resources. Therefore, cloud offers us the potential to overcome DDoS attacks. However, individual cloud hosted servers are still vulnerable to DDoS attacks if they still run in the traditional way. In this paper, we propose a dynamic resource allocation strategy to counter DDoS attacks against individual cloud customers. When a DDoS attack occurs, we employ the idle resources of the cloud to clone sufficient intrusion prevention servers for the victim in order to quickly filter out attack packets and guarantee the quality of the service for benign users simultaneously. We establish a mathematical model to approximate the needs of our resource investment based on queueing theory. Through careful system analysis and real-world data set experiments, we conclude that we can defeat DDoS attacks in a cloud environment.

ABSTRACT The growing popularity of mobile devices in our daily life demands higher throughput of wireless networks. The new communication standard 802.11n has significantly improved throughput because of the use of advanced technologies such as the multiple‐input multiple‐output communication technique. Because mobile devices are usually battery‐operated, power efficiency is critical; on the other hand, delay performance can be improved by transmitting at high power. To address the conflicting requirement of power saving and small delay, power scheduling is needed. In the past, many approaches to power scheduling have been proposed for real‐time applications, but few of them have considered complicated modes of channel state information(CSI) in multiple‐input multiple‐output. In this paper, we study this and classify the CSI into four types, namely, constant, slow fading, fast fading, and unknown. For known CSI, we propose an optimal algorithm for power scheduling. For unknown CSI, we propose an approximate algorithm based on some heuristics. To improve resource utilization, a stochastic delay‐bound method is proposed for fast‐fading condition. Simulation results demonstrate that the performance achieved by the optimal and heuristic algorithms agrees well with the analysis. Copyright © 2012 John Wiley & Sons, Ltd.

In this paper, we study the performance limit of a wireless communication system over a fading channel. The system under study consists of 1) a finite-buffer discrete-time queueing system on the link layer; and 2) a rate-adaptive channel coding system on the physical layer. The objective of this paper is to analyze the relationship among data rate (R), packet error probability (E), and delay bound (D) under the interaction between the link layer and the physical layer. In our analysis, we consider three types of packet errors; that is, 1) packet drop due to full buffer; 2) packet drop due to delay bound violation; and 3) packet decoding error due to channel noise. We obtain an upper bound on the packet error probability. Furthermore, by minimizing the packet error probability over the transmission rate, we obtain an optimal rate control policy that guarantees the user-specified data rate and delay bound. In the case of constant arrival, the optimal rate control policy results in a rate-error-delay triplet; then, by varying data rate and delay bound, we obtain rate-error-delay Pareto-optimal surface, which serves as the performance limit of the system under study. Copyright © 2012 John Wiley & Sons, Ltd.

Owing to the uncertainty of transmission opportunities between mobile nodes, the routing in delay tolerant networks (DTNs) exploits the mechanism of store-carry-and-forward. In this routing mechanism, mobility plays an important role, and we need to control the mobility of nodes around the network to help with carrying messages from the source to the destination. This is a difficult problem because the nodes in the network may move arbitrarily and it is difficult for us to determine when the nodes should move faster to help the data transmission while considering the complicated energy consumption in such a network. At the same time, for most DTNs, the system energy is limited, and energy efficient algorithms are crucial to maximizing the message delivery probability while reducing the delivery cost. In this paper, we investigate the problem of energy efficient mobility speed control in epidemic routing of DTN. We model the message dissemination process under variable mobility speed by a continuous-time Markov model. With this model, we then formulate the optimization problem of the optimal mobility control for epidemic routing and obtain the optimal policy from the solution of this optimization problem. Furthermore, extensive numerical results demonstrate that the proposed optimal policy significantly outperforms the static policy with constant speed, in terms of energy saving. Copyright © 2012 John Wiley & Sons, Ltd.

ABSTRACT To evaluate mobile communication systems, it is important to develop accurate and concise fading channel models. However, fading encountered in mobile communication is usually non‐stationary, and the existing methods can only model quasi‐stationary or piecewise‐stationary fading instead of general non‐stationary fading. To address this, this paper proposes an evolutionary spectrum (ES)‐based approach to modeling non‐stationary fading channels. Our ES approach is more general than the existing piecewise‐stationary models and is capable of characterizing a general non‐stationary fading channel that has an arbitrary ES (or time‐varying power spectral density); our ES approach is parsimonious and is also able to generate stationary fading processes. As an example, we show how to apply our ES approach to generating stationary and non‐stationary correlated Nakagami‐mfading channel processes. Simulation results show that the ES of the channel gain process produced by our ES‐based channel model agrees well with the user‐specified ES, indicating the accuracy of our ES‐based channel model. Copyright © 2011 John Wiley & Sons, Ltd.

Modeling of wireless channels, especially non-stationary fading channels, is important for design and performance analysis of wireless communication systems. Recently, we proposed a new approach to modeling non-stationary fading channels, based on the theory of evolutionary spectrum ES. In this paper, we develop a time-varying autoregressive AR model for a non-stationary flat fading channel; specifically, we develop a method to determine the time-varying coefficients of the AR channel model, given the ES of a non-stationary process. Furthermore, with the ES theory, we develop a trace-driven time-varying AR channel simulator to generate a non-stationary flat fading process. Simulation results show that the ES of the channel gain process produced by our joint ES-and-AR-based channel model agrees well with the user-specified ES, indicating the accuracy of our joint ES-and-AR-based channel model. Copyright © 2012 John Wiley & Sons, Ltd.

In mobile ad hoc networks (MANETs), it is important to understand the throughput-delay trade-off (TD trade-off) problem in large-scale scenarios. In the literature, the TD tradeoff problem has been studied extensively and many of them are based on the independent and identically distributed (i.i.d.) mobility model, in which each node can randomly move to any place in the network, after every time slot. Although the i.i.d. model has been widely used, it cannot fully represent MANETs in which nodes change positions less frequently. To characterize such MANETs, in this paper, we propose a generalized i.i.d. (g.i.i.d.) mobility model, in which each node moves once after every 1/f (0 < f ≤ 1) time slots, and remains static between two moves. To investigate the TD trade-off under the g.i.i.d. model, we develop a novel multi-relay multi-hop (MRMH) scheme that exploits the opportunities of multi-hop transmissions when the network is static. Furthermore, to enable the multi-hop transmissions, we construct a new percolation highway system, which has not been used in the TD trade-off analysis for MANETs. Using the proposed MRMH scheme, we develop and prove constructive bounds for throughput and delay in MANETs with different scales of f. Our constructive bound is asymptotically optimal for f = 1 (i.e., the i.i.d. model).

Assume that a set of Demand Response Switch (DRS) devices are deployed in smart meters for autonomous demand side management within one house. The DRS devices are able to sense and control the activity of each appliance. We propose a set of appliance scheduling algorithms to 1) minimize the peak power consumption under a fixed delay requirement, and 2) minimize the delay under a fixed peak demand constraint. For both problems, we first prove that they are NP-Hard. Then we propose a set of approximation algorithms with constant approximation ratios. We conduct extensive simulations using both real-life appliance energy consumption data trace and synthetic data to evaluate the performance of our algorithms. Extensive evaluations verify that the schedules obtained by our methods significantly reduce the peak demand or delay compared with naive greedy algorithm or randomized algorithm.

In this paper, we investigate the scheduling policy for collaborative execution in mobile cloud computing. A mobile application is represented by a sequence of fine-grained tasks formulating a linear topology, and each of them is executed either on the mobile device or offloaded onto the cloud side for execution. The design objective is to minimize the energy consumed by the mobile device, while meeting a time deadline. We formulate this minimum-energy task scheduling problem as a constrained shortest path problem on a directed acyclic graph, and adapt the canonical “LARAC” algorithm to solving this problem approximately. Numerical simulation suggests that a one-climb offloading policy is energy efficient for the Markovian stochastic channel, in which at most one migration from mobile device to the cloud is taken place for the collaborative task execution. Moreover, compared to standalone mobile execution and cloud execution, the optimal collaborative execution strategy can significantly save the energy consumed on the mobile device.

The popularity of GPS-enabled smartphones enables a wide variety of new location-based or location-aware services and applications. However, the GPS module in a smartphone produces inaccurate position estimates and incurs high energy consumption, which inhibits the wide use of location-aware applications. To address this, we propose a social-aided cooperative location optimization (Coloc) scheme, which is capable of improving positioning accuracy and achieving low energy consumption. Specifically, our scheme enhances positioning accuracy by fusing the GPS positions of multiple co-located smartphones in a social network, or by neighborhood-based weighted least-squares estimation when relative distances between smartphones are available. The energy efficiency is achieved by sharing location information among co-located users and lower the update rate of the GPS module without sacrificing the accuracy. To validate our proposed approach, we conduct experiments in stationary and moving scenarios. Experimental results show that our proposed cooperative localization scheme can achieve sufficient performance gains in both indoor and outdoor environments.

In this paper, we address the problem of large population speaker identification under noisy conditions. Major techniques for speaker identification is based on Mel-Frequency Cepstral Coefficients (MFCC), Gaussian Mixture Model (GMM) and Universal Background Model (UBM) which we call MFCC+GMM and MFCC+GMM+UBM. The approaches are known to perform very well for small population identification under low-noise conditions. However, the increase of population size can cause performance degradation of these schemes under noisy conditions. To mitigate this limitation, we propose a fuzzy-clustering-based decision tree approach. The key idea of our approach is to 1) use a decision tree to hierarchically partition the whole population into groups of small size, and determine which speaker group at the leaf node a speaker under test belongs to, and 2) apply MFCC+GMM to the selected speaker group for speaker identification. The advantage of our approach is that we use features that are independent from MFCC to partition speakers into groups and only apply MFCC+GMM to speaker groups at the leaf level. The key challenge in our design is how to achieve a low error probability of decision-tree-based classification. To address this, we adopt fuzzy clustering in constructing the tree for population partitioning, i.e., at each level, a speaker may belong to multiple groups. Such redundancy increases the probability of classifying a speaker under test into a correct group/node on the tree. Another novelty of this paper is that we use pitch and five vocal source features to construct a six-level decision tree. Experimental results demonstrate that our approach outperforms MFCC+ GMM and MFCC+ GMM+ UBM with higher accuracy and lower complexity for large population identification under additive white Gaussian noise (AWGN) conditions.

Online social network is emerging as a promising alternative for users to directly access video contents. By allowing users to import videos and re-share them through the social connections, a large number of videos are available to users in the online social network. The rapid growth of the user-generated videos provides enormous potential for users to find the ones that interest them; while the convergence of online social network service and online video sharing service makes it possible to perform recommendation using social factors and content factors jointly. In this paper, we design a joint social-content recommendation framework to suggest users which videos to import or re-share in the online social network. In this framework, we first propose a user-content matrix update approach which updates and fills in cold user-video entries to provide the foundations for the recommendation. Then, based on the updated user-content matrix, we construct a joint social-content space to measure the relevance between users and videos, which can provide a high accuracy for video importing and re-sharing recommendation. We conduct experiments using real traces from Tencent Weibo and Youku to verify our algorithm and evaluate its performance. The results demonstrate the effectiveness of our approach and show that our approach can substantially improve the recommendation accuracy.

Effective media server placement strategies are critical for the quality and cost of multimedia services. Existing studies have primarily focused on optimization-based algorithms to select server locations from a small pool of candidates based on the entire topological information and thus these algorithms are not scalable due to unavailability of the small pool of candidates and low-efficiency of gathering the topological information in large-scale networks. To overcome this limitation, a novel scalable framework called NetClust is proposed in this paper. NetClust takes advantage of the latest network coordinate technique to reduce the workloads when obtaining the global network information for server placement, adopts a new$K$-means-clustering-based algorithm to select server locations and identify the optimal matching between clients and servers. The key contribution of this paper is that the proposed framework optimizes the trade-off between the service delay performance and the deployment cost under the constraints of client location distribution and the computing/storage/bandwidth capacity of each server simultaneously. To evaluate the performance of the proposed framework, a prototype system is developed and deployed in a real-world large-scale Internet. Experimental results demonstrate that 1) NetClust achieves the lower deployment cost and lower delay compared to the traditional server selection method; and 2) NetClust offers a practical and feasible solution for multimedia service providers.

This paper provides a theoretical framework of energy-optimal mobile cloud computing under stochastic wireless channel. Our objective is to conserve energy for the mobile device, by optimally executing mobile applications in the mobile device (i.e., mobile execution) or offloading to the cloud (i.e., cloud execution). One can, in the former case sequentially reconfigure the CPU frequency; or in the latter case dynamically vary the data transmission rate to the cloud, in response to the stochastic channel condition. We formulate both scheduling problems as constrained optimization problems, and obtain closed-form solutions for optimal scheduling policies. Furthermore, for the energy-optimal execution strategy of applications with small output data (e.g., CloudAV), we derive a threshold policy, which states that the data consumption rate, defined as the ratio between the data size (L) and the delay constraint (T), is compared to a threshold which depends on both the energy consumption model and the wireless channel model. Finally, numerical results suggest that a significant amount of energy can be saved for the mobile device by optimally offloading mobile applications to the cloud in some cases. Our theoretical framework and numerical investigations will shed lights on system implementation of mobile cloud computing under stochastic wireless channel.

ABSTRACT A recursive maximum likelihood carrier frequency offset (CFO) estimator is proposed in this work, where redundancy information contained in the cyclic prefix of multiple consecutive orthogonal frequency‐division multiplexing (OFDM) symbols is exploited in an efficient recursive fashion. Because the estimator is based on multiple OFDM symbols, the time‐varying CFO must be considered. We investigate the effect of time‐varying CFO on the performance of the estimator and the trade‐off between fast tracking ability and low estimation variance. We show that, without channel noise, the mean squared error (MSE) of estimation due to CFO estimation variation increases approximately quadratically withn, wherenis the number of OFDM symbols used for CFO estimation (estimation window size), whereas the MSE due to channel noise decreases proportionally to 1/n(approximately) if the CFO is constant. A closed‐form expression of the optimal estimation window size (approximately) is derived by minimizing the MSE caused by both time‐varying CFO and channel noise. For wireless systems with time‐varying rate of change for CFO, the proposed estimator can be implemented adaptively. In addition, typical optimal estimation window sizes for WiMAX, DVB‐SH and MediaFLO systems are evaluated as an example. Copyright © 2011 John Wiley & Sons, Ltd.

ABSTRACT It is well known that orthogonal frequency division multiplexing (OFDM) is sensitive to carrier frequency offset (CFO) and suffers from a high peak‐to‐average ratio. In addition, the performance of OFDM is severely affected by strong co‐channel interference and strong narrowband interference. To mitigate the limitations of OFDM, we propose a new multi‐carrier transceiver based on frequency‐shift filter. A frequency‐shift filter can separate spectrally overlapping sub‐carrier signals by exploiting the spectral correlation inherent in the cyclostationary modulated signals. To increase spectral efficiency, we increase the percentage of spectral overlap between two adjacent sub‐channels. We derive an upper bound and a lower bound on the bit error rate performance of the proposed multi‐carrier transceiver in additive white Gaussian noise channel and frequency‐nonselective Rayleigh fading channel, respectively. Compared with OFDM, our simulation results show that the proposed multi‐carrier transceiver is much less sensitive to CFO and has a lower peak‐to‐average ratio; moreover, without any additional interference suppression technique, the proposed transceiver has the advantage of being able to mitigate strong co‐channel interference with CFO from the intended multi‐carrier signal and mitigate strong narrowband interference in additive white Gaussian noise channel and in Rayleigh fading channel in which a large CFO between the transmitted signal and the received signal often occurs. Copyright © 2011 John Wiley & Sons, Ltd.

ABSTRACT We analyze the performance of joint space‐frequency pre‐filtering and equalization techniques for downlink multi‐carrier code division multiple access in terms of average bit error rate performance. Several linear power allocation strategies combined with single‐user equalization schemes are compared with a joint pre‐filtering with an equal power constraint at the base station and maximal ratio combining at the mobile terminals. Our bit error rate analysis obtained in this paper facilitates predicting the performance of various space‐frequency pre‐filtering schemes without massive simulations. Copyright © 2011 John Wiley & Sons, Ltd.

ABSTRACT Secure transmission of information over wireless channels in the presence of an eavesdropper has attracted much attention recently. Previous work assumes that a transmitter has perfect knowledge of the channel side information (CSI) of the legitimate channel and the eavesdropper's channel. To loosen this strong requirement, this paper considers the case where a transmitter has perfect knowledge of the CSI of the legitimate channel and only the average channel gain of the eavesdropper's channel. In this case, some information may be leaked to the eavesdropper because the eavesdropper's channel may have a higher gain than the legitimate channel. Hence, we propose, for the first time, to study leakage‐probability‐constrained secrecy capacity of a fading channel, that is, secrecy capacity under the constraint on leakage probability. We also propose an optimal power allocation strategy that maximizes leakage‐probability‐constrained secrecy capacity under average power constraint. Moreover, we study the impact of the bias of the average gain estimate of the eavesdropper's channel on leakage‐probability‐constrained secrecy capacity. Copyright © 2011 John Wiley & Sons, Ltd.

Abstract In this paper, we address the speech‐based gender identification problem. Mel‐Frequency Cepstral Coefficients (MFCC) of voice samples are typically used as the features for gender identification. However, MFCC‐based classification incurs high complexity. This paper proposes a novel pitch‐based gender identification system with a two‐stage classifier to ensure accurate identification and low complexity. The first stage of the classifier identifies and labels all the speakers whose pitch clearly indicates the gender of the speaker; the complexity of this stage is very low since only threshold‐based decision rule on a scalar (i.e., pitch) is used. The ambiguous voice samples from all the other speakers (which cannot be classified with high accuracy by the first stage, and can be regarded as suspicious speakers or difficult cases) are forwarded to the second‐stage for finer examination; the second‐stage of our classifier uses Gaussian Mixture Model to accurately isolate voice samples based on gender. Experiment results show that our system is speech language/content independent, microphone independent, and robust against noisy recording conditions. Our system is extremely accurate with probability of correct classification of 98.65%, and very efficient with about 5 s required for feature extraction and classification. Copyright © 2011 John Wiley & Sons, Ltd.

ABSTRACT With the development of computers and the Internet, digital multimedia can be distributed and pirated easily. Watermarking is a useful technique for multimedia copyright protection. In this paper, we develop a robust video watermarking system. It consists of two components, that is, watermarking embedder and watermarking detector. In the embedder, we insert a watermark pattern into video frames according to a watermark payload. The watermark pattern is generated from a pseudo‐random noise sequence generator using the spread spectrum technique. User and copyright information are mapped to a binary sequence and then encrypted with advanced encryption standard and encoded/protected by convolutional error correction code to produce a watermark payload. The watermark pattern is weighted and embedded to each frame to meet perceptual requirements. In addition, the video is slightly geometrically manipulated in order to defend possible collusion attacks. The detector extracts the watermark from the candidate video. Kanade–Lucas–Tomasi feature tracker is used to register the candidate video with respect to the original video to enhance the correlation with the reference. The cross‐correlation sequence is binarized, error correction code decoded, and decrypted. The experimental results show that the proposed video watermark system is very robust to not only geometric attack but also collusion attacks, and that it is perceptually invisible to human vision system. Copyright © 2011 John Wiley & Sons, Ltd.

ABSTRACT Digital multimedia makes fabricating and copying much easier than ever before. Therefore, it demands efficient and automatic techniques to identify and verify the content of digital multimedia. Image authentication is such a technique to automatically identify whether the query image is a fabrication or a simple copy of the original one. In this paper, we propose a perceptual image authentication technique based on clustering and matching of feature points of images. Feature points are first extracted from images with the k‐largest local total variations and clustered using Fuzzy C‐means clustering algorithm. Then, feature points in the query image and the anchor image are matched into pairs in zigzag ordering along the diagonals of the images cluster by cluster. In the mean time, the outliers of feature points are removed. Then, the system decisions about the authenticity of images are determined by the majority vote of whether three types of distance between matched feature point pairs are larger than their respective thresholds. The three types of distance include the following: (i) histogram‐weighted distance, which is proposed in this paper; (ii) the normalized Euclidean distance; and (iii) the Hausdorff distance. The geometric transform between the query image and the anchor image is estimated, and the query image is registered. The possible tampered image blocks are detected, and the percentage of the tampered area is roughly estimated. The experimental results show the effectiveness and robustness of the proposed image authentication system. Copyright © 2011 John Wiley & Sons, Ltd.

In this letter, we consider the problem of clustering, given the similarity matrix of a set of data points or nodes; this problem is a.k.a. graph clustering. Spectral clustering techniques are typically used to solve this problem. The performance of the existing spectral clustering techniques is not satisfactory for many applications. To improve the performance, we take a bio-inspired approach to the graph clustering problem and enable fictitious queues with self-organizing capability to group similar nodes into the same cluster; we call the resulting scheme, Self-Organizing-Queue (SOQ) clustering scheme. Experimental results have demonstrated the superiority of our SOQ scheme over the existing spectral clustering techniques and K-means algorithm.

This paper presents an improved technique for estimating the end-to-end distortion, which includes both a quantization error after encoding and a random transmission error, after transmission in video communication systems. The proposed technique mainly differs from most existing techniques in that it takes into account filtering operations, e.g., interpolation in subpixel motion compensation, as introduced in advanced video codecs. The distortion estimation for pixels or subpixels under filtering operations requires the computation of the second moment of a weighted sum of random variables. In this paper, we prove a proposition for calculating the second moment of a weighted sum of correlated random variables without requiring knowledge of their probability distribution. Then, we apply the proposition to extend our previous error-resilient algorithm for prediction mode decision without significantly increasing complexity. Experimental results using an H.264/AVC codec show that our new algorithm provides an improvement in both rate-distortion performance and subjective quality over existing algorithms. Our algorithm can also be applied in the upcoming high-efficiency video coding standard, where additional filtering techniques are under consideration.

A wireless video communication system can be designed based on the rate-distortion (R-D) criterion, i.e., minimizing the end-to-end distortion (which includes quantization distortion and transmission distortion) subject to the transmission bit-rate constraint. The minimization can be achieved by adjusting the source encoding parameters and channel encoding parameters. This rate-distortion optimization (RDO) is usually done for each video frame individually in a real-time video communication system, e.g., video calls or videoconferencing. To achieve this, an accurate bit-rate model and distortion model for each frame can be used to reduce the RDO complexity. In this paper, we derive a source bit-rate model and quantization distortion model; we also improve the performance bound for channel coding under a convolutional code and a Viterbi decoder, and derive its performance bound under a Rayleigh block fading channel. Given the instantaneous channel condition, e.g., signal-to-noise ratio and transmission bit-rate constraint, we design an R-D optimized cross-layer rate control (CLRC) algorithm by jointly choosing quantization step size in source coding and code rate in channel coding. Experimental results show that our proposed R-D models are more accurate than the existing R-D models. Experimental results also showed that the rate control under our models has more stable R-D performance than the existing rate control algorithms; using the channel estimation, CLRC can further achieve remarkable R-D performance gain over that without channel estimation. Another important result is that the subjective quality of our CLRC algorithm is much better than the existing algorithms due to its intelligent reference frame selection.

For the video retargeting problem which adjusts video content into a smaller display device, it is not clear how to balance the three conflicting design objectives: 1) visual interestingness preservation; 2) temporal retargeting consistency; and 3) nondeformation. To understand their perceptual importance, we first identify that the latter two play a dominating role in making the retargeting results appealing. Then a statistical study on human response to the targeting scale is carried out, suggesting that the global preservation of contents pursued by most existing approaches is not necessary. Based on the newly prioritized objectives and the statistical findings, we design a video retargeting system which, as a refined homogeneous approach, addresses the temporal consistency issue holistically and is still capable of preserving high degree of visual interestingness. In particular, we propose a volume retargeting cost metric to jointly consider the retargeting objectives and formulate video retargeting as an optimization problem in graph representation. A dynamic programming solution is then given. In addition, we introduce a nonlinear fusion based attention model to measure the visual interestingness distribution. The experiment results from both image rendering and subjective tests indicate that our proposed attention modeling and video retargeting system outperform their conventional methods, respectively.

Transmitting video over wireless is a challenging problem since video may be seriously distorted due to packet errors caused by wireless channels. The capability of predicting transmission distortion (i.e., video distortion caused by packet errors) can assist in designing video encoding and transmission schemes that achieve maximum video quality or minimum end-to-end video distortion. This paper is aimed at deriving formulas for predicting transmission distortion. The contribution of this paper is twofold. First, we identify the governing law that describes how the transmission distortion process evolves over time and analytically derive the transmission distortion formula as a closed-form function of video frame statistics, channel error statistics, and system parameters. Second, we identify, for the first time, two important properties of transmission distortion. The first property is that the clipping noise, which is produced by nonlinear clipping, causes decay of propagated error. The second property is that the correlation between motion-vector concealment error and propagated error is negative and has dominant impact on transmission distortion, compared with other correlations. Due to these two properties and elegant error/distortion decomposition, our formula provides not only more accurate prediction but also lower complexity than the existing methods.

Abstract In this paper, we study efficient power control schemes for delay sensitive communication over fading channels. Our objective is to find a power control law that optimizes the link layer performance, specifically, minimizes the packet drop probability, subject to a long‐term average power constraint. We assume the buffer at the transmitter is finite; hence packet drop happens when the buffer is full. The fading channel under our study has a continuous state, e.g., Rayleigh fading. Since the channel state space is continuous, dynamic programming is not applicable for power control. In this paper, we propose a sub‐optimal power control law based on a parametric approach. The proposed power control scheme tries to minimize the packet drop probability by considering the queue length, i.e., reducing the probability of those queue‐length states that will cause full buffer. Simulation results show that our proposed power control scheme reduces the packet drop probability by one or two orders of magnitude, compared to the time domain water filling (TDWF) and the truncated channel inversion (TCI) power control. Copyright © 2010 John Wiley & Sons, Ltd.

Abstract In this paper, we develop new bounds for the first order Marcum Q‐function, which are extremely tight and tighter than any of the existing bounds to the best of our knowledge. The key idea of our approach is to derive refined approximations for the 0th order modified Bessel function in the integration region of the Marcum Q‐function. The new bounds are very tight and can serve as an effective means in bit error rate (BER) performance analysis for non‐coherent demodulation in digital communication. Copyright © 2010 John Wiley & Sons, Ltd.

ABSTRACT The grail of next‐generation wireless networks is providing real‐time services for delay‐sensitive applications, which require that the wireless networks provide QoS guarantees. The effective capacity (EC) proposed by Wu and Negi provides a powerful tool for design of QoS provisioning mechanisms. In this paper, we intend to generalize their formula for the effective capacity of a correlated Rayleigh fading channel; specifically, we derive a closed form approximate EC formula for a special correlated Nakagami‐m fading channel, for which the inverse of the correlation coefficient matrix is tridiagonal. To verify its accuracy via simulation, we develop a Green‐matrix based approach, which allows us to analytically obtain the effective capacity (given the joint probability density function of a correlated Nakagami‐m fading channel) while being able to simulate the corresponding channel gain process. Simulation results show that our EC formula is accurate. Furthermore, to facilitate the application of the EC theory to the design of practical QoS provisioning mechanisms, we propose a simple algorithm for estimating the EC of an arbitrary correlated Nakagami‐m fading channel, given channel measurements; simulation results demonstrate the accuracy of our proposed EC estimation algorithm showing its suitability in practice. Copyright © 2011 John Wiley & Sons, Ltd.

In a hybrid video encoder, the DCT transform or integer transform are adopted to de correlate the residual correlation among neighboring pixels. However, different transform coefficients have very different variances. For example, in a 4x4 integer transform, the 16 coefficients show a decreasing variance in the well-known zigzag scan order as used in H.264. As a result, the coefficients of higher frequency have higher probability of being zeroes after quantization. On the other hand, the coefficients of lower frequency have larger variances after quantization. Such characteristics are exploited by the run-level mapping after zigzag scan to further increase the coding efficiency of entropy coding.

Electricity consumption comprises a significant fraction of total operating cost in data centers. System operators are required to reduce electricity bill as much as possible. In this paper, we consider utilizing available energy storage capability in data centers to reduce electricity bill under real- time electricity market. Laypunov optimization technique is applied to design an algorithm that achieves an explicit tradeoff between cost saving and energy storage capacity. As far as we know, our work is the first to explore the problem of electricity cost saving using energy storage in multiple data centers by considering both time- diversity and location-diversity of electricity price.

In the paper, we consider the end-to-end routing and link scheduling problem for multi-hop wireless sensor networks. The efficient link scheduler under our consideration is intended to assign time slots to different users so as to minimize channel usage subject to constraints on data rate, delay bound, and delay bound violation probability. We also present a coupled robust multi-path routing structure satisfying the restriction of flows over fading channels based on an SINR-based interference model. Here the effective capacity (EC) model is used and then the joint routing and link scheduling can be formulated as a mixed integer optimization problem. Moreover, because the mixed integer optimization problem is NP-complete, we propose a computationally feasible EC-based Column-Generation-Algorithm (EC-CGA) to search for a sub-optimal solution. Simulation results are given to evaluate the performance of our proposed scheme.

In this paper, we propose a classified quadtree-based adaptive loop filter (CQALF) in video coding. Pixels in a picture are classified into two categories by considering the impact of the deblocking filter, the pixels that are modified and the pixels that are not modified by the deblocking filter. A wiener filter is carefully designed for each category and the filter coefficients are transmitted to decoder. For the pixels that are modified by the deblocking filter, the filter is estimated at encoder by minimizing the mean square error between the original input frame and a combined frame which is a weighted average of the reconstructed frames before and after the deblocking filter. For pixels that the deblocking filter does not modify, the filter is estimated by minimizing the mean square error between the original frame and the reconstructed frame. The proposed algorithm is implemented on top of KTA software and compatible with the quadtree-based adaptive loop filter. Compared with kta2.6rl anchor, the proposed CQALF achieves 10.05%, 7.55%, and 6.19% BD bitrate reduction in average for intra only, IPPP, and HB coding structures respectively.

A compelling video summarization should allow viewers to understand the summary content and recover the original plot correctly. To this end, we materialize the abstract elements that are cognitively informative for viewers as concepts. They implicitly convey the semantic structure and are instantiated by semantically redundant instances. Then we analyze that a good summary should i) keep various concepts complete and balanced so as to give viewers comparable cognitive clues from a complete perspective ii) pursue the most saliency so that the rendered summary is attractive to human perception. We then formulate video summarization as an integer programming problem and give a ranking based solution. We also propose a novel method to discover the latent concepts by spectral clustering of bag-of-words features. Experiment results on human evaluation scores demonstrate that our summarization approach performs well in terms of the informativeness, enjoyability and scalibility.

Abstract In this paper, we propose a video hash scheme that utilizes image hash and spatio‐temporal information contained in video to generate video hash. A video clip is firstly segmented to shots, and video hash is derived in unit of shot. We notice that for video hash applications in identification and verification, reference video and suspected video always appear in pair. Therefore, we propose to derive the shot hash in a pairwise manner. For both reference and suspected shot, we apply 2‐Dimensional Discrete Cosine Transform (2D‐DCT) to each frame in the shot, quantize the Discrete Cosine Transform (DCT) coefficient, and record the temporal occurrence of the co‐located coefficient. We then choose a pair of the closet value as the DCT coefficient for every collocated entry, inverse transform to the spatial domain, and derive image hashes from two feature frames by hash based on Radial projections (Radial hASH). Experiment results show that the proposed 2D‐DCT temporal maximum occurrence (2D‐DCT TMO) scheme successfully derives shot hash that represents the content, and is very robust in video identification, authentication, and verification. Copyright © 2010 John Wiley & Sons, Ltd.

Abstract Voice and video over IP are becoming increasingly popular and represent the largest source of profits as consumer interest in online voice and video services increases, and as broadband deployments proliferate. In order to tap the potential profits that VoIP and IPTV offer, carrier networks have to efficiently and accurately manage and track the delivery of IP services. The traditional approach of using port numbers to classify traffic is infeasible due to the usage of dynamic port number. In this paper, we focus on a statistical pattern classification technique to identify multimedia traffic. Based on the intuitions that voice and video data streams show strong regularities in the packet inter‐arrival times (IATs) and the associated packet sizes when combined together in one single stochastic process, we propose a system, called VOVClassifier, for voice and video traffic classification. VOVClassifier is an automated self‐learning system that classifies traffic data by extracting features from frequency domain using Power Spectral Density (PSD) analysis and grouping features using Subspace Decomposition. We applied VOVClassifier to real packet traces collected from different network scenarios. Results demonstrate the effectiveness and robustness of our approach that is capable of achieving a detection rate of up to 100% for voice and 96.5% for video while keeping the false positive rate close to 0%. Copyright © 2009 John Wiley & Sons, Ltd.

Abstract Easily processing, storing, and propagating of digital images demand efficient and automatic techniques to identify and verify image contents. Image hashing is such a promising technique to represent and authenticate images without changing the content of images. The new robust image feature we use is the Morlet wavelet coefficients at feature points with thek‐largest local total variations in images. The Morlet wavelet coefficients are pseudo randomly permutated such that image hashes have a small collision rate and are difficult to analyze by attackers. The Morlet wavelet coefficients are further quantized using companding technique and binarily coded using Gray code to form the final hash. Experimental results show the effectiveness and robustness of our method. The proposed image hash could have applications in image authentication and video signature. Copyright © 2010 John Wiley & Sons, Ltd.

In this paper, the problem of optimal power control for delay-constrained communication over fading channels is studied. The objective is to find a power control law that optimizes the link layer performance, specifically, minimizes delay bound violation probability (or equivalently, the packet drop probability), subject to constraints on average power, arrival rate and delay bound. The transmission buffer size is assumed to be finite; hence, when the buffer is full, there will be packet drop. The fading channel under study has a continuous state, e.g., Rayleigh fading. Since directly solving the power control problem (which optimizes the link layer performance) is particularly challenging, the problem is decomposed into three subproblems and the three subproblems are solved iteratively; the resulting scheme is called joint queue length aware (JQLA) power control, which produces a local optimal solution to the three subproblems. It is proved that the solution that simultaneously solves the three subproblems is also an optimal solution to the optimal power control problem. Simulation results show that the JQLA scheme achieves superior performance over the time domain water filling and the truncated channel inversion power control.

Abstract In this paper, we study the power allocation scheme for a single user, multi‐channel system, e.g., orthogonal frequency‐division multiplexing (OFDM) systems, under time‐variant wireless fading channels. We assume the receiver feeds back perfectly estimated channel state information (CSI) to the transmitter after a processing delay. The objective of the power allocation is to maximize throughput subject to quality‐of‐service (QoS) constraint. The QoS measure of our consideration is a triplet of data rate, delay, and delay bound violation probability. A two‐step sub‐optimal power allocation scheme is proposed to address the impact of outdated CSI. In the first step, the total transmission power that can be used within one block is determined according to the summation of the channel gains of all the channels. In the second step, the total transmission power is allocated among all the channels. The proposed power control scheme is less sensitive to the feedback delay. Compared to the optimal power allocation scheme designed for the perfect CSI scenario, it has lower computational complexity while achieving comparable capacity. Copyright © 2010 John Wiley & Sons, Ltd.

Abstract We consider the problem of optimal power control for quality‐of‐service‐assured wireless communication. The quality of service (QoS) measures of our consideration are a triplet of data rate, delay, and delay bound violation probability (DBVP). Our target is to develop power control laws that can provide delay guarantees for real‐time applications over wireless networks. The power control laws that aim at optimizing certain physical‐layer performance measures, usually adapt the transmission power based on the channel gain; we call these “channel‐gain‐based” (CGB) power control (PC). In this paper, we show that CGB‐PC laws achieve poor link‐layer delay performance. To improve the performance, we propose a novel scheme called hierarchical queue‐length‐aware (HQLA) power control. The key idea is to combine the best features of the two PC laws, i.e., a given CGB‐PC law and the clear‐queue (CQ) PC law; here, the CQ‐PC is defined as a PC law that uses a transmission power just enough to empty the queue at the link layer. We analyze our proposed HQLA‐PC scheme by the matrix‐geometric method. The analysis agrees well with the simulation results. More importantly, our results show that the proposed HQLA power control scheme is superior to the corresponding CGB‐PC in both average power consumption and effective capacity. Copyright © 2010 John Wiley & Sons, Ltd.

Abstract The next generation wireless networks call for quality of service (QoS) support. The effective capacity (EC) proposed by Wu and Negi provides a powerful tool for the design of QoS provisioning mechanisms. In their previous work, Wu and Negi derived a formula for effective capacity of a Rayleigh fading channel with arbitrary Doppler spectrum. However, their paper did not provide simulation results to verify the accuracy of the EC formula derived in their paper. This is due to difficulty in simulating a Rayleigh fading channel with a Doppler spectrum of continuous frequency, required by the EC formula. To address this difficulty, we develop a verification methodology based on a new discrete‐frequency EC formula; different from the EC formula developed by Wu and Negi, our new discrete‐frequency EC formula can be used in practice. Through simulation, we verify that the EC formula developed by Wu and Negi is accurate. Furthermore, to facilitate the application of the EC theory to the design of practical QoS provisioning mechanisms in wireless networks, we propose a spectral‐estimation‐based algorithm to estimate the EC function, given channel measurements; we also analyze the effect of spectral estimation error on the accuracy of EC estimation. Simulation results show that our proposed spectral‐estimation‐based EC estimation algorithm is accurate, indicating the excellent practicality of our algorithm. Copyright © 2010 John Wiley & Sons, Ltd.

The secure transmission of information over wireless systems in the presence of an eavesdropper has attracted much attention. In this paper, we consider the case that full CSI of the legitimate user but only the average channel gain of the eavesdropper is known at the transmitter. In such setting, some information will be inevitably leaked to the eavesdropper from the information-theoretic view and this was not quantitatively evaluated before. A secrecy transmission framework with leakage threshold is thereby proposed. The secrecy capacity satisfying this leakage probability constraints is derived along with an optimal power allocation strategy. For Rayleigh and Nakagami-m fading channels, numerical results indicate that our framework can work well with transmitter knowledge of only average channel gain of the eavesdropper.

In this paper, we consider the joint problem of congestion control and scheduling with multi-class Quality of Service (QoS) requirements. Generally, the joint problem is formulated as a Network Utility Maximization (NUM) problem and can be decomposed into a congestion control problem and a scheduling problem. Usually, the congestion control problem can be solved in a distributed manner by tracking per-destination-queue for every flow, which requires that every node should maintain many queues, each corresponding to one destination. With QoS constraints imposed on the congestion control problem, it is hard to obtain an explicit distributed solution. To address this, we propose 1) using per-next-hop-queue instead of per-destination-queue, which considerably reduces queuing overhead, 2) a Sliding Mode (SM) approach to designing a distributed controller for the congestion control problem while satisfying multi-class QoS requirements in the multi-path and multi-hop scenario. We also prove the optimality and convergence of the SM based solution to the NUM problem.

Video retargeting (resolution adaptation) is a challenging problem for its highly subjective nature. In this paper, a nonlinear saliency fusing approach, that considers human perceptual characteristics for automatic video retargeting, is being proposed. First, we incorporate features from phase spectrum of quaternion Fourier Transform (PQFT) in spatial domain and global motion residual based on matched feature points by the Kanade-Lucas-Tomasi (KLT) tracker in temporal domain. In addition, under a cropping-and-scaling retargeting framework, we propose content-aware information loss metrics and a hierarchical search to find optimal cropping window parameters. Results show the success of our approach on detecting saliency regions and retargeting on images and videos.

Video retargeting is the task of fitting standard-sized video into arbitrary screen. A compelling retargeting attempts to preserve most visual information of original video as well as deliver a temporally consistent retargeted view. To handle long video sequences, we perform the task on a shot/subshot basis. For each frame, a crop pane is determined to optimally select a region of interest as the retargeted frame in two stages: i.e. minimizing visual information loss (intra-frame consideration) to yield source and destination crop pane parameters at boundary frames and minimizing visual information loss accumulation under the visual inertness (inter-frame consideration) constraints to search for a smooth transition of crop pane across interior frames. The second minimization process is remodeled as the shortest-path problem in graph theory and the parametric transition of crop panes is solved by dynamic programming. Experiments demonstrate our approach preserves salient regions of original video whilst offering eye-friendly visual consistency.

In this work, we establish a general framework for investigating statistical QoS provisioning in mobile ad hoc networks. Though the throughput and average delay in wireless ad hoc works have been has been intensively studied in the literature, statistical delay guarantee provisioning in large scale ad hoc networks has not received enough attention. A realtime application, e.g., interactive game and realtime video, requires stringent delay (delay bound) but may allow a small probability of outage (deadline violation probability). This motivates us to study the relationship among throughput, delay bound and deadline violation probability. We propose to use a triplet (T, B, R), where T, B, R denote throughput, delay bound and deadline violation probability (or, equivalently, the reliability index) respectively, to describe the delay constrained performance of a mobile ad hoc network. Both i.i.d. mobility model and random walk model are adopted to illustrate the tradeoffs among these performance metrics. Since the relation between delay bound and deadline violation probability can be interpreted as a description of the reliability of delay-sensitive communications, our results provide insights into understanding the delay constrained performance of large scale wireless ad hoc networks. Index Terms-Ad hoc networks.

Current image representation schemes have limited capability of representing 2D singularities (e.g., edges in an image). Wavelet transform has better performance in representing 1D singularities than Fourier transform. Recently invented ridgelet and curvelet transform achieve better performance in resolving 2D singularities than wavelet transform. To further improve the capability of representing 2D singularities, this paper proposes a new transform called ripplet transform Type II (ripplet-II). The new transform is able to capture 2D singularities along a family of curves in images. In fact, ridgelet transform is a special case of ripplet-II transform with degree 1. Ripplet-II transform can be used for feature extraction due to its efficiency in representing edges and textures. Experiments in texture classification and image retrieval demonstrate that the ripplet-II transform based scheme outperforms wavelet and ridgelet transform based approaches.

Abstract Secure transmission of information over hostile wireless environments is desired by both military and civilian parties. Direct‐sequence spread‐spectrum (DS‐SS) is such a covert technique resistant to interference, interception, and multipath fading. Identifying spread‐spectrum signals or cracking DS‐SS systems by an unintended receiver (or eavesdropper) withouta prioriknowledge is a challenging problem. To address this problem, we first search for the start position of data symbols in the spread signal (for symbol synchronization); our method is based on maximizing the spectral norm of a sample covariance matrix, which achieves smaller estimation error than the existing method of maximizing the Frobenius norm. After synchronization, we remove a spread sequence by a cross‐correlation based method, and identify the spread sequence by a matched filter. The proposed identification method is less expensive and more accurate than the existing methods. We also propose a zigzag searching method to identify a generator polynomial that reduces memory requirement and is capable of correcting polarity errors existing in the previous methods. In addition, we analyze the bit error performance of our proposed method. The simulation results agree well with our analytical results, indicating the accuracy of our analysis in additive white Gaussian noise (AWGN) channel. By simulation, we also demonstrate the performance improvement of our proposed schemes over the existing methods. Copyright © 2009 John Wiley & Sons, Ltd.

Future wireless networks are expected to provide quality of service (QoS) guarantees. QoS requirements at the networking layers include data rate, delay bound, and packet error probability. However, these QoS requirements pose significant challenges since wireless fading channels may cause severe QoS violations. To mitigate fading effects, adaptive schemes such as transmission rate control and power control are usually used. In this paper, we study a wireless communication system that adapts the transmission rate; we assume that the channel state information (CSI) is available at the transmitter side, and the transmission power is fixed. The system under study consists of (1) a discrete-time queueing system on the link layer, and (2) a channel coding system on the physical layer. The objective of this paper is to analyze the relationship among packet error probability, data rate, delay bound, and buffer size. In our analysis, we consider three types of packet errors, i.e., (1) packet drop due to full buffer, (2) packet drop due to delay bound violation, and (3) packet decoding error due to channel noise. We derive packet drop probability and decoding error probability for our system, and obtain an upper bound on the packet error probability. Furthermore, by minimizing the packet error probability over the transmission rate, we obtain an optimal rate control law that guarantees the user-specified data rate and delay bound. Our results show that our analysis agrees well with simulation.

In this paper, we study the power allocation scheme for a single user, multi-channel system, e.g. orthogonal frequency- division multiplexing (OFDM) systems, under time-variant wireless fading channels. We assume the receiver feeds back perfectly estimated channel state information (CSI) to the transmitter after a processing delay. The objective of the power allocation is to maximize physical (PHY) layer throughput under quality-of- service (QoS) constraint. The QoS measure of our consideration is a triplet of data rate, delay, and delay bound violation probability. A two-step suboptimal power allocation scheme is proposed which addresses the imperfect CSI issue. In the first step, the total transmission power that can be used by one block is determined according to the summation of the channel gains of all the channels. In the second step, the total transmission power is allocated to all the channels. Compared to the optimal power allocation scheme designed for the perfect CSI scenario, the proposed power allocation scheme reduces the computation complexity significantly while achieves comparable performance.

This paper considers minimum-energy routing problem in Poisson random ad-hoc networks with Nakagami-m fading channels. We first formulate an analytical model for the transmission power, subject to a certain packet reception probability, under the assumption that the users employ proper power control and slotted ALOHA protocol. Based on this, we consider five routing strategies and compare their energy performances. Our results show that, long-hop routing in Nakagami-m networks can be more energy efficient than short-hop routing in certain scenarios, especially under light traffic and significant channel fading. When the interference can not be neglected, short-hop routing is typically better. It is also observed that when the path loss exponent is small, intelligent MAC mechanisms are critical for the energy efficiencies of routing strategies.

In the last years, many sparsity based denoising approaches for image/video denoising have been proposed. Most of them exploit the image/video sparsity model under certain overcomplete basis. In this paper, we unify three sparsity-based denoising techniques and apply them to the problem of video compression artifacts removal. We compare and analyze the three techniques from the aspects of operation atom, transform dimensionality, and quantization impact. Based on the provided analysis, the paper may serve as a guideline to apply sparsity-based denoising techniques to related problems.

In this paper, we propose an efficient multi-party signature scheme for wireless networks where a given number of signees can jointly sign a document, and it can be verified by any entity who possesses the certified group public key. Our scheme is based on an efficient threshold key generation scheme which is able to defend against both static and adaptive adversaries. Specifically, our key generation method employs the bit commitment technique to achieve efficiency in key generation and share refreshing; our share refreshing method provides proactive protection to long-lasting secret and allows a new signee to join a signing group. We demonstrate that previous known approaches are not efficient in wireless networks, and the proposed multi-party signature scheme is flexible, efficient, and achieves strong security for low-power devices in wireless networks.

This paper addresses the image representation problem in visual sensor networks. We propose a new image representation scheme based on compressive sensing (CS) because compressive sensing is capable of reducing computational complexity of an image/video encoder. In our scheme, the encoder first decomposes the input image into two components, i.e., dense and sparse components; then the dense component is encoded by the traditional approach while the sparse component is encoded by a CS technique. To improve the rate distortion performance, we leverage the strong correlation between dense and sparse components. Given the measurements and the prediction of the sparse component, we use projection onto convex set (POCS) to reconstruct the sparse component. Our method considerably reduces the number of random measurements needed and decoding computational complexity, compared to the existing CS methods.

RELIEF is considered one of the most successful algorithms for assessing the quality of features due to its simplicity and effectiveness. It has been recently proved that RELIEF is an online algorithm that solves a convex optimization problem with a margin-based objective function. Starting from this mathematical interpretation, we propose a novel feature extraction algorithm, referred to as LFE, as a natural generalization of RELIEF. LFE collects discriminant information through local learning, and is solved as an eigenvalue decomposition problem with a closed-form solution. A fast implementation is also derived. Experiments on synthetic and real-world data are presented. The results demonstrate that LFE performs significantly better than other feature extraction algorithms in terms of both computational efficiency and accuracy.

Abstract Despite the rapid advance in networking technologies, detection of network anomalies at high‐speed switches/routers is still far from maturity. To push the frontier, two major technologies need to be addressed. The first one is efficient feature‐extraction algorithms/hardware that can match a line rate in the order of Gb/second; the second one is fast and effective anomaly detection schemes. In this paper, we focus on design of efficient data structure and algorithms for feature extraction. Specifically, we propose a novel data structure that extracts the so‐called two‐directional (2D) matching features, which are shown to be effective indicators of network anomalies. Our key idea is to use a Bloom filter array (BFA) to trade‐off a small amount of accuracy in feature extraction, for much less space and time complexity, so that our data structure can catch up with a line rate in the order of Gb/second. Different from the existing work, our data structure has the following properties: (1) it dynamic Bloom filter, (2) combination of a it sliding window with Bloom filter, and (3) using an insertion–removal pair to enhance Bloom filter with a removal operation. Our analysis and simulation demonstrate that the proposed data structure has a better space/time trade‐off than conventional algorithms. For example, for a fixed time complexity, the conventional algorithm (i.e., hash table [1—8]) requires a memory of 1.01 Gbits while our data structure requires a memory of only 62.9 Mbits, at the cost of losing 1% accuracy in feature extraction. Copyright © 2008 John Wiley & Sons, Ltd.

In this paper, we present a new decoding algorithm for the Wyner-Ziv (WZ) video coding scheme based on turbo codes. In this scheme, a video frame is encoded using a turbo code, and only a subset of the parity bits are sent to the decoder. At the decoder, the temporal correlation of the video sequence is exploited by using the previous frame as noisy side information (SI) for the current frame. However, there is a mismatch between the SI, which is available as pixel values, and the binary code bits. Previous implementations of the decoder use suboptimal approaches that convert pixel values to soft information for code bits. We present a new decoding algorithm for this application based on decoding on a hyper-trellis, in which multiple states of the original code trellis are combined. We show that this approach significantly improves performance without changing the complexity of the decoder. We also introduce a new technique for the WZ decoder to exploit the spatial correlation within a frame without requiring transform-domain encoding at the encoder, thereby reducing its complexity. Simulation results for fixed-rate transmission show a 9-10-dB improvement in the peak signal-to-noise ratio when compared to a WZ video codec that does bitwise decoding and utilizes only the temporal correlation.

To effectively address the explosive growth of multimedia applications over the Internet, a large-scale media streaming system has to fully take into account the issues of security, quality of service (QoS), scalability, and heterogeneity. However, current streaming solutions do not address all these challenges simultaneously. To address this limitation, this paper proposes a secure and high-performance streaming system called TrustStream, which combines the best features of scalable coding, content distribution network (CDN) and peer-to-peer (P2P) networks to achieve unprecedented security, scalability, heterogeneity, and certain QoS simultaneously under a unified architecture. In this architecture, raw video is encoded into two layers, namely, the base layer, which contains the most critical media content and is transmitted through a CDN-featured single-source multi-receiver (S-M) P2P network to guarantee a minimal level of quality, and the enhancement layer, which is transmitted in a pure multisource multi-receiver (M-M) P2P framework to achieve maximum scalability and bandwidth utilization. Heterogeneity is therefore addressed by delivering only the layers that a receiver is able to manage. Security is provided by combining our key distribution mechanism and key-embedding scheme under our proposed S-M P2P topology. We have implemented TrustStream system over the Internet. Deployed by ChinaCache, the largest CDN provider in China, TrustStream has broadcasted several popular live video programs over the Internet. The experimental results demonstrate the advantages and effectiveness of our architecture and system.

The H.264 video coding standard achieves significantly improved video compression efficiency and finds important applications in digital video broadcast. To enable H.264 video encoding for digital TV broadcast and maximize its broadcast efficiency, there are two important issues that need to be adequately addressed. First, we need to understand the complex coding mechanism of an H.264 video encoder and develop a model to analyze and control its rate-distortion (R-D) behavior in an accurate and robust manner. Second, the R-D behaviors of individual channels in the broadcast system should be jointly controlled and optimized under bandwidth and buffer constraints so as to maximize the overall broadcast quality. In this paper, we develop a linear rate model and a linear rate control scheme for H.264 video coding. We develop an optimum statistical multiplexing system to allocate bits across video programs (each being encoded by an H.264 encoder) and video frames so that the overall video broadcast quality is maximized. We study the bandwidth and buffer constraints in video broadcast and formulate the optimum statistical multiplexing into a constrained mathematical optimization problem. Realizing that it is impossible to find a close-form solution for global optima, we propose a simple yet efficient algorithm to find a near-optimum solution for joint rate allocation under buffer constraints. Our extensive simulation results demonstrate that the proposed statistical multiplexing system achieves about 40–50% saving in bandwidth, provides a smooth video quality change across programs and frames, and maintains robust decoder buffer control.

With the widespread use of mobile devices, the privacy of mobile location information becomes an important issue. In this paper, we present the requirements on protecting mobile privacy in wireless networks, and identify the privacy weakness of the third generation partnership project - authentication and key agreement (3GPP-AKA) by showing a practical attack to it. We then propose a scheme that meets these requirements, and this scheme does not introduce security vulnerability to the underlying authentication scheme. Another feature of the proposed scheme is that on each use of wireless channel, it uses a one-time alias to conceal the real identity of the mobile station with respect to both eavesdroppers and visited (honest or false) location registers. Moreover, the proposed scheme achieves this goal of identity concealment without sacrificing authentication efficiency.

This paper proposes an efficient authentication scheme, which is suitable for low-power mobile devices. It uses an elliptic-curve-eryptosystem based trust delegation mechanism to generate a delegation passcode for mobile station authentication, and it can effectively defend all known attacks to mobile networks including the denial-of-service attack. Moreover, the mobile station only needs to receive one message and send one message to authenticate itself to a visitor's location register, and the scheme only requires a single elliptic-curve scalar point multiplication on a mobile device. Therefore, this scheme enjoys both computation efficiency and communication efficiency as compared to known mobile authentication schemes.

Abstract The next‐generation packet‐based wireless cellular network will provide real‐time services for delay‐sensitive applications. To make the next‐generation cellular network successful, it is critical that the network utilizes the resource efficiently while satisfying quality of service (QoS) requirements of real‐time users. In this paper, we consider the problem of power control and dynamic channel allocation for the downlink of a multi‐channel, multi‐user wireless cellular network. We assume that the transmitter (the base‐station) has the perfect knowledge of the channel gain. At each transmission slot, a scheduler allots the transmission power and channel access for all the users based on the instantaneous channel gains and QoS requirements of users. We propose three schemes for power control and dynamic channel allocation, which utilize multi‐user diversity and frequency diversity. Our results show that compared to the benchmark scheme, which does not utilize multi‐user diversity and power control, our proposed schemes substantially reduce the resource usage while explicitly guaranteeing the users' QoS requirements. Copyright © 2007 John Wiley & Sons, Ltd.

Abstract Providing quality of service (QoS) guarantees is important in the third generation (3G) and the fourth generation (4G) cellular networks. However, large‐scale fading and non‐stationary small‐scale fading can cause severe QoS violations. To address this issue, we design QoS provisioning schemes, which are robust against time‐varying large scale path loss, shadowing, non‐stationary small scale fading, and very low mobility. In our design, we utilize our recently developed effective capacity technique and the time‐diversity dependent power control proposed in this paper. The key elements of our QoS provisioning schemes are channel estimation, power control, dynamic channel allocation, and adaptive transmission. The advantages of our QoS provisioning schemes are (1) power efficiency, (2) simplicity in QoS provisioning, (3) robustness against large‐scale fading and non‐stationary small‐scale fading. Simulation results demonstrate that the proposed algorithms are effective in providing QoS guarantees under various channel conditions. Copyright © 2006 John Wiley & Sons, Ltd.

We draw an analogy of biological cyanide poisoning to security attacks in self-organizing mobile ad hoc networks. When a circulatory system is treated as an enclosed network space, a hemoglobin is treated as a mobile node, and a hemoglobin binding with cyanide ion is treated as a compromised node (which cannot bind with oxygen to furnish its oxygen-transport function), we show how cyanide poisoning can reduce the probability of oxygen/message delivery to a "negligible" quantity. Like modern cryptography, security problem in our network-centric model is defined on the complexity-theoretic concept of "negligible", which is asymptotically sub-polynomial with respect to a pre-defined system parameter x. Intuitively, the parameter x is the key length n in modern cryptography, but is changed to the network scale, or the number of network nodes N, in our model. Based on this new analytic model, we show that RP (n-runs) complexity class with a virtual oracle can formally model the cyanide poisoning phenomenon and similar network threats. This new analytic approach leads to a new view of biological threats from the perspective of network security and complexity theoretic study.

With the rapid growth of wireless networks and increasing popularity of portable video devices, wireless video communication is poised to become the enabling technology for many multimedia applications over wireless networks. Real-time wireless video transmission typically has requirements on quality of service (QoS). However, wireless channels are unreliable and the channel capacities are time-varying, which may cause severe degradation to video presentation quality. In addition, for portable devices, video compression and wireless transmission are tightly coupled through the constraints on data rate, power, and delay. These issues make it particularly challenging to design an efficient real-time video compression and wireless transmission system on a portable device. In this paper, we take a cross-layer approach to this problem; our objective is to maximize the video quality under the constraints of resource and delay. Specifically, we minimize the end-to-end video distortion under the constraints of resource and delay, over the parameters in physical, link, and application (video) layers. This formulation is general and capable of capturing the fundamental aspects of the design of wireless video communication systems. Based on this formulation, we study how the resources could be intelligently allocated to maximize the video quality and analyze the performance limits of the wireless video communication system under resource constraints.

The 19 papers in this special issue focus on cross-layer optimized wireless multimedia communications. The papers are organized into four sections: quality of service support for wireless networks; system architecture for multimedia over wireless networks; resource allocation in wireless multimedia communications, and multimedia coding and scheduling issues in wireless networks.

In this paper, a non-interactive zero-knowledge proof scheme is proposed for secure identification in wireless networks, and it uses a timed oblivious transfer technique to enable a single verifier to identify multiple provers. The verifier and the prover do not need to be synchronized in this scheme. This scheme also enjoys the distance-bounding property which makes the proposed scheme invulnerable to the relay attack. We propose to use the order statistic for the detection of relay attackers. We show that it is optimal in terms of minimum variance. Finally, we shed some light on implementation issues of our proposed scheme.

Wireless LANs with multi-beam directional antennas have received intensive attention lately due to the potential gain in throughput performance. However, when the multi-beam directional antennas are introduced in this system, the ever popular contention-based medium access control protocol such as IEEE 802.11 MAC is no longer effective, and many challenging problems, such as beam-synchronization problem, beam-overlapping problem, mobility and receiver blocking problem (deafness problem), need to be resolved. In this paper, we propose a novel MAC protocol to carefully address these problems. In addition to improving communication efficiency, we also consider the backward compatibility in our design, whereby an IEEE 802.11 terminal can transparently access a multi-beam access point. Furthermore, we present an analytical model to evaluate the performance of multi-beam wireless LANs. Extensive simulation studies are used to validate the analytical model and show that our scheme can significantly improve the throughput performance

Abstract We consider the motion estimation problem in video coding. In our previous work, we proposed a new motion estimation method where motion estimation is formulated as an optimization problem and an adaptive system under the minimum error entropy (MEE) criterion is used for motion estimation. In this paper, we develop an adaptive system under the criterion of maximum mutual information to address the motion estimation problem. Our proposed motion estimation algorithms have very low encoding complexity and hence are ideally suited for wireless video sensor networks where limited bandwidth, restricted computational capability, and limited battery power supply impose stringent constraints on the video encoding system. Copyright © 2007 John Wiley & Sons, Ltd.

Despite the rapid advance in networking technologies, detection of network anomalies at high-speed switches/routers is still far from maturity. To push the frontier, two major technologies need to be addressed. The first one is efficient feature-extraction algorithms/hardware that can match a line rate in the order of Gb/s; the second one is fast and effective anomaly detection schemes. In this paper, we focus on design of efficient data structure and algorithms for feature extraction. Specifically, we propose a novel data structure that extracts so-called two-directional (2D) matching features, which are shown to be effective indicators of network anomalies. Our key idea is to use a Bloom filter array to trade off a small amount of accuracy in feature extraction, for much less space and time complexity, so that our data structure can catch up with a line rate in the order of Gb/s. Different from the existing work, our data structure has the following properties: 1) dynamic Bloom filter, 2) combination of a sliding window with the Bloom filter, and 3) using an insertion-removal pair to enhance the Bloom filter with a removal operation. Our analysis and simulation demonstrate that the proposed data structure has a better space/time trade-off than conventional algorithms. For example, for a fixed time complexity, the conventional algorithm (i.e., hash table [1]) requires a memory of 1.01G bits while our data structure requires a memory of only 62.9M bits, at the cost of losing 1% accuracy in feature extraction.

In this paper, we propose a novel nonlinear transform scheme to reduce the Peak-to-Average Power Ratio (PAPR) in multi-carrier modulation (MCM) systems. The key idea of the proposed scheme is to transform the original MCM signals such that the amplitude or the power of the companded signals follows uniform distribution. In this manner, the proposed scheme can effectively reduce the PAPR for different modulation formats and sub-carrier sizes without increasing the system complexity and signal bandwidth. Extensive simulation results show that the proposed schemes can significantly improve the performance of MCM systems.

The next-generation packet-based wireless cellular network will provide real-time services for delay-sensitive applications. To make the next-generation cellular network successful, it is critical that the network utilizes the resource efficiently while satisfying quality of service (QoS) requirements of realtime users. In this paper, we consider the problem of power control and dynamic channel allocation for the downlink of a multi-channel, multi-user wireless cellular network. We assume that the transmitter (the base-station) has the perfect knowledge of the channel gain. At each transmission slot, a scheduler allots the transmission power and channel access for all the users based on the instantaneous channel gains and QoS requirements of users. We propose three schemes for power control and dynamic channel allocation, which utilize multiuser diversity and frequency diversity. Our results show that compared to the benchmark scheme, which does not utilize multiuser diversity and power control, our proposed schemes substantially reduce the resource usage while explicitly guaranteeing the users' QoS requirements.

In this paper, we propose a proactive share refreshing scheme for secret share in a distributed system. It enjoys a strong secrecy property against both static and adaptive adversaries. It employs bit commitment technique to make the refreshing process efficient, and the key refreshing cost is less than 50% of the key generation time with key length at 163 bits while the public key is kept intact after share refreshing, which is a nice features of our scheme.

In this paper, a non-interactive zero-knowledge proof scheme is proposed for secure identification in wireless networks, and it uses a timed oblivious transfer technique to enable a single verifier to identify multiple provers. The verifier and the prover do not need to be synchronized in this scheme. This scheme also enjoys the distance bounding property which makes the proposed scheme invulnerable to the relay attack. We propose to use the order statistic for the detection of relay attackers. We show that it is optimal in terms of minimum variance. Finally, we will shed some light on implementation issues of our proposed scheme.

Flow-level traffic measurement is important for network management. The widely used centralized per-flow measurement faces a great challenge due to the demanding requirement on both memory bandwidth and memory size within a single traffic monitor. This paper addresses the issue of deploying a Distributed Passive Measurement System (DPMS) in a large scale network; specifically, we study how to optimally place traffic monitors and sample stochastic traffic flows, so that the probability of a packet being sampled (a.k.a. measurement coverage) is maximized. We formulate this problem as a Stochastic Chance Constrained Optimization (SCCO) problem; and we propose a Hybrid Intelligent (HI) algorithm to solve this problem. The HI algorithm consists of two major components, namely, uncertain function approximation and genetic algorithm. Equipped with the HI algorithm, we are able to address the optimal tradeoff between measurement coverage and deployment cost for networks with random traffic, which has not been studied before. Our simulations and experiments demonstrate the effectiveness of our algorithm, i.e., a small deployment cost or a small number of monitors are sufficient to maintain a high level of measurement coverage.

Channel characterization and modeling is essential to the wireless communication system design. A model that optimally represents a fading channel with a variable length Markov chain (VLMC) is proposed in this work. VLMC offers a general class of Markov chains whose structure has a variable order and a parsimonious number of transition probabilities. The proposed model consists of two main components: 1) the optimal fading partition under the constraint of a transmission policy and 2) the derivation of the best VLMC representation. The fading partition is used to discretize a continuous fading channel gain. The optimal discretization criterion is developed based on the cost function of fading channel statistics and the transmission policy used in the system. Once a continuous fading channel gain is discretized, a VLMC is then used to model the channel. To obtain the optimal VLMC representation, we use the Kullback-Liebler (K-L) distance as the optimization criterion. Finally, we show simulation results that demonstrate the accuracy of the proposed fading channel representation in modeling the Rayleigh fading as well as the log-normal fading.

With the advance of wireless technology, wireless devices are capable of adjusting transmit power and physical (PHY) layer data-rate. In this paper, we investigate the problem of how to adjust the power level and the PHY rate in order to maximize the network throughput in wireless ad hoc networks. Solving this problem can help compute the network capacity of ad hoc networks, which has drawn a lot of attention recently. In our study, we find that there exist intertwined relationships among maximum network throughput, power, and PHY rate. These intertwined relationships make computing the maximum network throughput a difficult problem. To get around the coupled relationships among power, PHY rate and network throughput, we take a simulation-based optimization approach, i.e., use a recursive randomized algorithm to find the solution. We study the convergence and complexity of our algorithm. Our results show that our algorithm always converges and the computation complexity is polynomial. The simulations also show that our algorithm can iteratively improve the network throughput, given an initial feasible power and rate setting.

Abstract — Opportunistic spectrum access and adaptive power management are effective techniques to improve throughput, delay performance, and energy efficiency for wireless networks. In this paper, we consider the joint design of opportunistic spectrum access and adaptive power management under the setting of multi-radio nodes and multi-channel wireless local area networks (WLANs) under the distributed coordination function (DCF) mode. This design problem is particularly challenging due to the conflicting nature of the multi-radio capability of a node, i.e., multiple radios improve throughput and delay performance at the cost of increased energy consumption. To address this problem, we propose a power-saving multi-channel MAC protocol (PSM-MMAC), which is capable of reducing the collision probability and the waiting time in the ‘awake ’ state of a node, resulting in improved throughput, delay performance, and energy efficiency. The key ideas of PSM-MMAC are the following: we first estimate the number of active links; given this estimation as well as queue lengths and channel conditions, we appropriately select channels, radios, and power states (i.e., awake or doze state); then we optimize the medium access probability in p-persistent CSMA used in the data exchange. Another contribution of this paper is an analytical model that characterizes the throughput performance. Simulation results validate the accuracy of our analytical model and show that our proposed protocol is able to significantly improve both throughput and energy efficiency. I.

Ultra-wideband (UWB) is a promising technology that can support high data rate communication for future Wireless Personal Area Networks (WPANs). To provide high throughput in UWB networks, we proposed a general framework for CSMA/CA based MAC protocol previously [17]. In this framework, multiple upper layer packets can be assembled into a single burst frame at the MAC layer, which can significantly improve the throughput performance by reducing overheads. Nevertheless, the burst assembly procedure may introduce extra packet delay, which is undesirable for some applications. In this paper, we address the performance issue in the burst-frame-based MAC protocol. In particular, we develop an analytical model to evaluate the delay performance of the burst-frame-based MAC protocol under unsaturated conditions. Our delay analysis is unique in that we consider the end-to-end packet delay, which is the duration from the epoch that a packet enters the queue at the MAC layer of the transmitter side to the epoch that the packet is successfully received at the receiver side. The analytical results give excellent agreement with the simulation results, which represents the accuracy of our analytical model. The results also provide important guideline on how to set the parameters of the burst assembly policy. Based on these results, we develop an efficient adaptive burst assembly policy so as to optimize the throughput and delay performance of the burst-frame-based CSMA/CA protocol.

In this paper we study the problem of using the rate adaptation technique to achieve energy efficiency in an IEEE 802.11-based multi-hop network. Specifically, we formulate it as an optimization problem, i.e., minimizing the total transmission power over transmission data rates, subject to the traffic requirements of all the nodes in a multi-hop network. Interestingly, we can show that this problem is actually a well-known multiple-choice knapsack problem, which is proven to be an NP-hard problem. So, instead of finding an optimal solution, which is NP-hard, we seek a sub-optimal solution. Our key technique to attack this problem is distributed cooperative rate adaptation. Here, we promote node cooperation due to our observation that the inequality in non-cooperative channel contention among nodes caused by hidden terminal phenomenon in a multi-hop network tends to result in energy inefficiency. Under this design philosophy, we propose a distributed cooperative rate adaptation (CRA) scheme and prove that it converges. Simulation results show that our CRA scheme can reduce the power consumption up to 86% as compared to the existing (non-cooperative) algorithm.

In this paper, we propose a theoretical framework to analyze the performance of upper layer algorithms and protocols such as scheduling disciplines which exploit the gain of multi-user diversity to optimize the utilization of wireless communication systems while supporting service differentiation between different users.

The recent Federal Communications Commission regulations for ultra-wideband (UWB) transmission systems have sparked a surge of research interests in the UWB technology. One of the important application areas of UWB is wireless sensor networks. The proper operations of many UWB sensor networks rely on the knowledge of physical sensor locations. However, most existing localization algorithms developed for sensor networks are vulnerable to attacks in hostile environments. As a result, attackers can easily subvert the normal functionalities of location-dependent sensor networks by exploiting the weakness of localization algorithms. In this paper, we first analyze the security of existing localization techniques. We then develop a mobility-assisted secure localization scheme for UWB sensor networks. In addition, we propose a location-based scheme to enable secure authentication in UWB sensor networks.

Wireless video sensor networks (WVSNs) have been envisioned for a wide range of important applications, including battlefield intelligence, security monitoring, emergency response, and environmental tracking. Compared to traditional communication system, the WVSN operates under a set of unique resource constraints, including limitations with respect to energy supply, on-board computational capability, and transmission bandwidth. The objective of this paper is to study the resource utilization behavior of a wireless video sensor and analyze its performance under the resource constraints. More specifically, we develop an analytic power-rate-distortion (P-R-D) model to characterize the inherent relationship between the power consumption of a video encoder and its rate-distortion performance. Based on the P-R-D analysis and a simplified model for wireless transmission power, we study the optimum power allocation between video encoding and wireless transmission and introduce a measure called achievable minimum distortion to quantify the distortion under a total power constraint. We consider two scenarios in wireless video sensing, small-delay wireless video monitoring and large-delay wireless video surveillance, and analyze the performance limit of the wireless video sensor in each scenario. The analysis and results obtained in this paper provide an important guideline for practical wireless video sensor design.

One of the most promising approaches to improving communication efficiency in wireless communication systems is the use of multiuser diversity. Although it has been widely investigated and shown feasible and efficient in cellular networks, there is little work for the ad hoc networks, especially in real protocol and algorithm design. In this paper, we propose a novel scheme, namely, the Opportunistic Medium Access and Auto Rate (OMAR), to efficiently utilize the shared medium in IEEE 802.11-based ad hoc networks by taking advantage of diversity, distributed scheduling, and adaptivity. In an ad hoc network, especially in a heterogeneous ad hoc network or a mesh network, some nodes may need to communicate with multiple one-hop nodes. We allow such a node with a certain number of links to function as a clusterhead to locally coordinate multiuser communications. We introduce a CDF-based (Cumulative Distribution Function) K-ary opportunistic splitting algorithm and a distributed stochastic scheduling algorithm to resolve intra and intercluster collisions, respectively. Fairness is formulated and solved in terms of social optimality within and across clusters. Analytical and simulation results show that our scheme can significantly improve communication efficiency while providing social fairness.

Abstract In an ad hoc network, intermediate nodes on a communication path are expected to forward packets of other nodes so that the mobile nodes can communicate beyond their wireless transmission range. However, because wireless mobile nodes are usually constrained by limited power and computation resources, a selfish node may be unwilling to spend its resources in forwarding packets which are not of its direct interest, even though it expects other nodes to forward its packets to the destination. It has been shown that the presence of such selfish nodes degrades the overall performance of a non‐cooperative ad hoc network. To address this problem, we propose a secure and objective reputation‐based incentive (SORI) architecture to encourage packet forwarding and discipline selfish behavior. Different from existing schemes, under our architecture, the reputation of a node is quantified by objective measures; the propagation of reputation is efficiently secured by a one‐way‐hash‐chain‐based authentication scheme; and secure routing is in place. Armed with the reputation‐based mechanism, we design a punishment scheme to penalize selfish nodes. The experimental results show that the proposed scheme can successfully identify selfish nodes and punish them accordingly. Copyright © 2006 John Wiley & Sons, Ltd.

Efficient routing is very important for mobile ad hoc networks (MANETs). Most of the existing routing protocols consider homogeneous ad hoc networks, in which all nodes are of the same type, i.e., they have the same communication capabilities and characteristics. Although a homogeneous network model is simple and easy to analyze, it misses important characteristics of many realistic MANETs such as military battlefield networks. In addition, a homogeneous ad hoc network suffers from poor scalability. In many ad hoc networks, multiple types of nodes do co-exist; and nodes having larger transmission power, higher transmission data rate, and better processing capability, are more reliable and robust than other nodes. Hence, a heterogeneous network model is more realistic and provides many advantages for designing more efficient routing protocols. In this paper, we present a new routing protocol called multi-class (MC) routing, which is specifically designed for heterogeneous MANETs. Extensive simulation results demonstrate that the MC routing has very good performance, and out performs a popular routing protocol AODV (ad hoc on demand distance vector), in terms of reliability, scalability, route discovery latency, overhead, as well as packet delay and throughput.

A new approach to design video coding schemes for wireless video applications has emerged recently. Schemes using this approach are based on the principle of distributed source coding, and they exploit the correlation in the frames of the video sequence at the decoder. One such scheme models the correlation between frames as a Laplacian channel, and uses a turbo code to correct errors occurring in this pseudo-channel. Existing implementations use a sub-optimal approximation to compute the channel likelihoods in the BCJR algorithm in the turbo decoder. To resolve this sub-optimality, we propose applying the BCJR algorithm on a trellis-structure with parallel transitions. This trellis structure is called a hyper-trellis. The BCJR maximum a posteriori algorithm is modified to use the hyper-trellis, and computation of the channel-likelihoods are shown to be optimal on the hyper-trellis. Simulation results show that the hyper-trellis approach can yield a 5 dB improvement in peak signal-to-noise ratio.

Wireless video sensor networks (WVSN) have been envisioned for a wide range of important applications, including battlefield intelligence, security monitoring, and environmental tracking. Compared to traditional communication systems, the WVSN operates under a set of unique resource constraints, including limitations with respect to energy supply, on-board computational capability, and transmission bandwidth. The objective of this work is to study the resource utilization behavior of a wireless video sensor and analyze its performance under these resource constraints. More specifically, we develop an analytic power-rate-distortion (P-R-D) model to characterize the inherent relationship between the power consumption of a video encoder and its rate-distortion performance. Based on the P-R-D analysis and a simplified model for wireless transmission power, we study the optimum power allocation between video encoding and wireless transmission. We consider an important scenario in wireless video sensing - wireless video surveillance, and analyze the performance limit of the wireless video sensor. The analysis and results obtained in this paper provide an important guideline for practical wireless video sensor design.

We consider the CSMA/CA based uplink medium access control (MAC) protocol design for a wireless local area network (WLAN) with the use of multi-beam directional antennas at the access point. Our MAC protocol intends to fully utilize the spatial reuse by allowing as many parallel uplink data transmissions as possible. Since all nodes including the access point run in the contention-based MAC protocol, it is not easy to realize multiple collision-free parallel data transmissions while preserving the ad hoc nature of CSMA/CA based MAC. In addition to improving channel efficiency, we also consider the backward compatibility in our design, whereby a 802.11 limited node can transparently access a multi-beam access point. Our simulation results show that our scheme can improve throughput significantly.

IEEE 802.11 is the most important standard for wireless local area networks (WLANs). In IEEE 802.11, the fundamental medium access control (MAC) scheme is distributed coordination function (DCF), whose performance has been studied analytically in the literature. However, to the best of the authors' knowledge, there is no accurate model that takes into account both the incoming traffic loads and the effect of bit transmission errors, which, in addition to collision, can also result in unsuccessful packet delivery. In this paper, we address this issue and provide a new analytical model to evaluate the performance of DCF in binary symmetric channels (BSCs). In our study, we consider the impact of different factors together, including the binary exponential backoff mechanism in DCF, various incoming traffic loads, distribution of incoming packet size, queueing system at the MAC layer, and the packet transmission errors, which has never been done before. Extensive simulation and analysis results show that our analytical model can accurately predict the delay and throughput performance of IEEE 802.11 DCF under different traffic and transmission error conditions.

A wireless video sensor network (WVSN) is a system of spatially distributed video sensors which gather and transmit video information over a wireless ad hoc network. To measure, control and optimize the system performance, the following key research problems need to be addressed: 1) how to measure the amount of visual information collected by the video sensor within its operational lifetime; 2) how to quantitatively compare the information sensing efficiency between two video sensors; 3) how to measure the information sensing efficiency of the whole video sensor network; 4) how to control and optimize the information sensing efficiency of the video sensor network. In this work, we introduce the concept of accumulative visual information (AVT), and use it as a measure for the amount of visual information collected the WVSN. Based on the AVI measure and the power-rate-distortion analysis model developed in our previous work, we optimize the efficiency of the WVSN system.

Ultra-wideband (UWB) communication is becoming an important technology for future wireless personal area networks (WPANs). A critical challenge in high data rate UWB system design is that a receiver usually needs tens of micro-seconds or even tens of milliseconds to synchronize with the transmitted signals, known as the timing acquisition problem. Such a long synchronization time will cause significant overhead, since the data rate of UWB systems is expected to be very high. To address the overhead problem, we previously proposed a general framework for MAC protocols in high data rate UWB networks. In this framework, a node can aggregate multiple upper-layer packets into a larger burst frame at the MAC layer. In this paper, we analyze the unsaturated throughput performance of a burst-frame-based MAC protocol within the framework. Numerical results from the analytical method give excellent agreement with the simulation results, indicating the accuracy of our analytical method.

With the explosion of demand for wireless communication services, scarcity of spectrum poses a great challenge to wireless networking. However, recent field measurements show that a significant percentage of spectrum is under-utilized . To address this problem, the research community introduced the concept of real-time secondary markets, where licensees are allowed to temporarily lease the spectrum unused by the primary users to secondary users. To support this new service, an authentication, authorization, and accounting (AAA) mechanism must be in place to enable the licensees and secondary users to trade spectrum in a real-time manner. In this paper, we present an AAA system architecture, and propose a set of mechanisms to authenticate and authorize secondary users, synchronize multiple secondary devices, and manage real-time secondary market services.

In this paper, we present a new interpretation of AdaBoost.ECC and AdaBoost.OC. We show that AdaBoost.ECC performs stage-wise functional gradient descent on a cost function, defined in the domain of margin values, and that AdaBoost.OC is a shrinkage version of AdaBoost.ECC. These findings strictly explain some properties of the two algorithms. The gradient-minimization formulation of AdaBoost.ECC allows us to derive a new algorithm, referred to as AdaBoost.SECC, by explicitly exploiting shrinkage as regularization in AdaBoost.ECC. Experiments on diverse databases confirm our theoretical findings. Empirical results show that AdaBoost.SECC performs significantly better than AdaBoost.ECC and AdaBoost.OC.

Streaming media over networks has gained renewed interest recently due to the emerging IP-TV and mobile TV. The success of commercial media streaming systems critically depends on two important capabilities, namely, 1) scalability in distributing media content to diverse clients, and 2) security management of the media and the systems. However, existing media streaming systems such as content distribution networks (CDN) and Peer-to-Peer (P2P) networks lack either security or scalability. In this paper, we propose a novel secure and scalable media streaming architecture, called TrustStream. Our architecture combines the best features of CDN and P2P networks to achieve unprecedented security, scalability, and certain quality of service simultaneously. Our experimental results demonstrate the advantages of the TrustStream.

To efficiently support quality of service (QoS) in future wireless networks, it is important to model a wireless channel in terms of connection-level QoS metrics such as data rate, delay and delay-violation probability. To achieve this, in D. Wu and R. Negi (2003), we proposed and developed a link-layer channel model termed effective capacity (EC) for flat fading channels. In this paper, we apply the effective capacity technique to modeling frequency selective fading channels. Specifically, we utilize the duality between the distribution of a queue with superposition of N i.i.d. sources, and the distribution of a queue with a frequency-selective fading channel that consists of N i.i.d. sub-channels, to model a frequency selective fading channel. In the proposed model, a frequency selective fading channel is modeled by three EC functions; we also propose a simple and efficient algorithm to estimate these EC functions. Simulation results show that the actual QoS metric is closely approximated by the QoS metric predicted by the proposed EC channel model. The accuracy of the prediction using our model can translate into efficiency in admission control and resource reservation.

A critical challenge in ultra-wideband (UWB) system design is that a receiver usually needs tens of microseconds or even tens of milliseconds to synchronize with transmitted signals; this is known as the timing acquisition problem. Such a long synchronization time causes significant overhead, since the data rate of UWB systems is expected to be very high. We address the timing acquisition problem at the medium access control (MAC) layer, and propose a general framework for medium access control in UWB systems; in this framework, a transmitting node can aggregate multiple upper-layer packets into a larger burst frame at the MAC layer. Furthermore, we design a MAC protocol based on the framework, and analyze its saturation throughput performance. Compared to sending each upper-layer packet individually, which is a typical situation in exiting MAC protocols, the proposed MAC can drastically reduce the synchronization overhead. Numerical and simulation results show that the proposed MAC can significantly improve the performance of UWB networks, in terms of both throughput and end-to-end delay.

Mobile devices performing video coding and streaming over wireless and pervasive communication networks are limited in energy supply. To prolong the operational lifetime of these devices, an embedded video encoding system should be able to adjust its computational complexity and energy consumption as demanded by the situation and its environment. To analyze, control, and optimize the rate-distortion (R-D) behavior of the wireless video communication system under the energy constraint, we develop a power-rate-distortion (P-R-D) analysis framework, which extends the traditional R-D analysis by including another dimension, the power consumption. Specifically, in this paper, we analyze the encoding mechanism of typical video coding systems, and develop a parametric video encoding architecture which is fully scalable in computational complexity. Using dynamic voltage scaling (DVS), an energy consumption management technology recently developed in CMOS circuits design, the complexity scalability can be translated into the energy consumption scalability of the video encoder. We investigate the R-D behavior of the complexity control parameters and establish an analytic P-R-D model. Both theoretically and experimentally, we show that, using this P-R-D model, the video coding system is able to automatically adjust its complexity control parameters to match the available energy supply of the mobile device while maximizing the picture quality. The P-R-D model provides a theoretical guideline for system design and performance optimization in mobile video communication under energy constraints.

Abstract The next‐generation wireless networks such as the fourth generation (4G) cellular systems are targeted at supporting various applications such as voice, data, and multimedia over packet‐switched networks. Providing quality of service (QoS) guarantees for these applications is an important objective in the design of the next‐generation wireless networks. In this paper, we overview the issues and techniques in QoS provisioning for wireless networks, and present some of our recent results in this area. Specifically, we survey the results in five sub‐areas, namely, network services models, traffic specification, packet scheduling for wireless transmission, call admission control in wireless networks, and wireless channel characterization. For each sub‐area, we address the particular issues, review major approaches and mechanisms, and discuss the trade‐offs of the approaches. Copyright © 2005 John Wiley & Sons, Ltd.

An important objective of next-generation wireless networks is to provide quality of service (QoS) guarantees. This requires a simple and efficient wireless channel model that can easily translate into connection-level QoS measures such as data rate, delay, and delay-violation probability. To achieve this, in D. Wu and R. Negi (July 2003), we developed a link-layer channel model termed effective capacity, for the setting of a single hop, constant-bit-rate arrivals, fluid traffic, and wireless channels with negligible propagation delay. In this paper, we apply the effective capacity technique to deriving QoS measures for more general situations, namely: 1) networks with multiple wireless links, 2) variable-bit-rate sources, 3) packetized traffic, and 4) wireless channels with non-negligible propagation delay.

In an ad-hoc network, intermediate nodes on a communication path are expected to forward packets of other nodes so that the mobile nodes can communicate beyond their wireless transmission range. However, because wireless mobile nodes are usually constrained by limited power and computation resources, a selfish node may be unwilling to spend its resources in forwarding packets which are not of its direct interest, even though it expects other nodes to forward its packets to the destination. It has been shown that the presence of such selfish nodes degrades the overall performance of a non-cooperative ad hoc network. To address this problem, we propose a secure and objective reputation-based incentive (SORI) scheme to encourage packet forwarding and discipline selfish behavior. Different from the existing schemes, under our approach, the reputation of a node is quantified by objective measures, and the propagation of reputation is efficiently secured by a one-way-hash-chain-based authentication scheme. Armed with the reputation-based mechanism, we design a punishment scheme to penalize selfish nodes. The experimental results show that the proposed scheme can successfully identify selfish nodes and punish them accordingly.

We consider the problem of quality of service (QoS) provisioning for K users sharing a downlink time-slotted Rayleigh fading channel. We develop simple and efficient schemes for admission control, resource allocation, and scheduling, which can yield substantial capacity gain. The efficiency is achieved by virtue of multiuser diversity. A unique feature of our work is explicit provisioning of statistical QoS, which is characterized by a data rate, delay bound, and delay-bound violation probability triplet. The results show that compared with a fixed-slot assignment scheme, our approach can substantially increase the statistical delay-constrained capacity of a fading channel, when delay requirements are not very tight, while yet guaranteeing QoS at any delay requirement.

To facilitate the efficient support of quality of service (QoS) in next-generation wireless networks, it is essential to model a wireless channel in terms of connection-level QoS metrics such as data rate, delay, and delay-violation probability. However, the existing wireless channel models, i.e., physical-layer channel models, do not explicitly characterize a wireless channel in terms of these QoS metrics. In this paper, we propose and develop a link-layer channel model termed effective capacity (EC). In this approach, we first model a wireless link by two EC functions, namely, the probability of nonempty buffer, and the QoS exponent of a connection. Then, we propose a simple and efficient algorithm to estimate these EC functions. The physical-layer analogs of these two link-layer EC functions are the marginal distribution (e.g., Rayleigh-Ricean distribution) and the Doppler spectrum, respectively. The key advantages of the EC link-layer modeling and estimation are: 1) ease of translation into QoS guarantees, such as delay bounds; 2) simplicity of implementation; and 3) accuracy, and hence, efficiency in admission control and resource reservation. We illustrate the advantage of our approach with a set of simulation experiments, which show that the actual QoS metric is closely approximated by the QoS metric predicted by the EC link-layer model, under a wide range of conditions.

To facilitate the efficient support of quality of service (QoS) in third generation (3G) and fourth generation (4G) wireless networks, it is essential to model a wireless channel in terms of connection-level QoS metrics such as bandwidth, delay and packet loss ratio. However, the existing wireless channel models do not explicitly characterize a wireless channel in terms of these QoS metrics. We propose and develop a wireless channel model termed effective capacity (EC). In this approach, we first model a wireless channel by two EC functions, namely the probability of a non-empty buffer and the QoS exponent of a connection. Then, we design a simple and efficient algorithm to estimate these EC functions. The key advantages of EC channel modeling and estimation are: (1) ease of translation into QoS guarantees, such as delay bounds; (2) simplicity of implementation; (3) accuracy, and hence efficiency, in admission control and resource reservation. We illustrate the advantage of our approach with simulations which show that the actual QoS metric is closely approximated by the QoS metric predicted by the EC channel model.

With the emergence of broadband wireless networks and increasing demand of multimedia information on the Internet, wireless multimedia services are foreseen to become widely deployed in the next decade. Real-time video transmission typically has requirements on quality of service (QoS). However, wireless channels are unreliable and the channel bandwidth varies with time, which may cause severe degradation in video quality. In addition, for video multicast, the heterogeneity of receivers makes it difficult to achieve efficiency and flexibility. To address these issues, three techniques, namely, scalable video coding, network-aware adaptation of end systems, and adaptive QoS support from networks, have been developed. This paper unifies the three techniques and presents an adaptive framework, which specifically addresses video transport over wireless networks. The adaptive framework consists of three basic components: (1) scalable video representations; (2) network-aware end systems; and (3) adaptive services. Under this framework, as wireless channel conditions change, mobile terminals and network elements can scale the video streams and transport the scaled video streams to receivers with a smooth change of perceptual quality. The key advantages of the adaptive framework are: (1) perceptual quality is changed gracefully during periods of QoS fluctuations and hand-offs; and (2) the resources are shared in a fair manner.

Due to the explosive growth of the Internet and increasing demand for multimedia information on the Web, streaming video over the Internet has received tremendous attention from academia and industry. Transmission of real-time video typically has bandwidth, delay, and loss requirements. However, the current best-effort Internet does not offer any quality of service (QoS) guarantees to streaming video. Furthermore, for video multicast, it is difficult to achieve both efficiency and flexibility. Thus, Internet streaming video poses many challenges. In this article we cover six key areas of streaming video. Specifically, we cover video compression, application-layer QoS control, continuous media distribution services, streaming servers, media synchronization mechanisms, and protocols for streaming media. For each area, we address the particular issues and review major approaches and mechanisms. We also discuss the tradeoffs of the approaches and point out future research directions.

This paper presents a network node architecture and several traffic management mechanisms that are capable of achieving QoS provisioning for the guaranteed service (GS), the controlled-load (CL) service, and the best-effort (BE) service under IETF integrated services (IntServ) paradigm. Our architecture offers the attractive feature of in-sequence delivery for all packets, albeit some of which may be out-of-profile. Simulation results show that, once admitted into the network, our architecture and traffic management algorithms provide hard performance guarantees to GS flows under all conditions, consistent (or soft) performance to CL flows under both light load and heavy load conditions, and minimal negative impact to in-profile GS, CL and BE traffic should there be any out-of-profile behavior from some flows.

We present an end-to-end approach to generalize the classical theory of rate distortion (R-D) optimized mode selection for point-to-point video communication. We introduce a notion of global distortion by taking into consideration of both the path characteristics and the receiver behavior, in addition to the source behavior. We derive, for the first time, a set of accurate global distortion metrics for any packetization scheme. Equipped with the global distortion metrics, we design an R-D optimized mode selection algorithm to provide the best trade-off between compression efficiency and error resilience. As an application, we integrate our theory with point-to-point MPEG-4 video conferencing over the Internet. Simulation results conclusively demonstrate that our end-to-end approach offers superior performance over the classical approach for Internet video conferencing.

This paper proposes an adaptive quality-of-service (QoS) control to increase the robustness of MPEG-4 video communication over wireless channels. More specifically, the proposed adaptive QoS control consists of optimal mode selection and delay-constrained hybrid automatic repeat request (ARQ). The optimal mode selection is employed to provide QoS support on the compression layer while delay-constrained hybrid ARQ is used to provide QoS support on the link layer. Simulation results show that the proposed adaptive QoS control achieves satisfactory quality for MPEG-4 video under dynamically changing wireless channel conditions and utilizes network resources efficiently.

The IETF differentiated services (DiffServ) framework achieves scalability by moving complexity out of the core of the network into edge routers which process fewer number of flows. Previously, an end-to-end service called the premium service (PS) has been proposed under the DiffServ model to provide coarse grained guaranteed rate service. This paper presents a buffer management mechanism based on simple FIFO scheduling to support integrated transport of the PS and the traditional best effort (BE) service. A key feature in our buffer management is to perform selective packet discarding from an embedded queue at a shared buffer. We show that such a buffer management mechanism is capable of achieving the following objectives: (1) a core router does not maintain any state information for any flow (i.e., stateless); (2) the bandwidth for an PS flow is guaranteed (in conjunction with a bandwidth broker (BB) for admission control). Simulation results demonstrate that our buffer management mechanism can achieve integrated transport of the PS and the BE services.

There has been great interest in transporting real-time video over wireless IP networks from both industry and academia. Real-time video applications have quality-of-service (QoS) requirements. However, the fluctuations of wireless channel conditions pose many challenges to providing QoS for video transmission over wireless IP networks. It has been shown that scalable video coding and adaptive services are viable solutions under a time-varying wireless environment. We propose an adaptive framework to support quality video communication over wireless IP networks. The adaptive framework includes: (1) scalable video representations, (2) network-aware video applications, and (3) adaptive services. Under this framework, as wireless channel conditions change, the mobile terminal and network elements can scale the video streams and transport the scaled video streams to receivers with acceptable perceptual quality. The key advantages of the adaptive framework are: (1) perceptual quality is degraded gracefully under severe channel conditions; (2) network resources are efficiently utilized; and (3) the resources are shared in a fair manner.

Rate-distortion (R-D) optimized mode selection is a fundamental problem for video communication over packet-switched networks. The classical R-D optimized mode selection only considers quantization distortion at the source. Such an approach is unable to achieve global optimality under the error-prone environment since it does not consider the packetization behavior at the source, the transport path characteristics, and receiver behavior. This paper presents an end-to-end approach to generalize the classical theory of R-D optimized mode selection for point-to-point video communication. We introduce a notion of global distortion by taking into consideration both the path characteristics (i.e., packet loss) and the receiver behavior (i.e., the error concealment scheme), in addition to the source behavior (i.e., quantization distortion and packetization). We derive, for the first time, a set of accurate global distortion metrics for any packetization scheme. Equipped with the global distortion metrics, we design an R-D optimized mode selection algorithm to provide the best tradeoff between compression efficiency and error resilience. The theory developed in this paper is general and is applicable to many video coding standards, including H.261/263 and MPEG-1/2/4. As an application, we integrate our theory with point-to-point MPEG-4 video conferencing over the Internet, where a feedback mechanism is employed to convey the path characteristics (estimated at the receiver) and receiver behavior (error concealment scheme) to the source. Simulation results are discussed.

Delivering real-time video over the Internet is an important component of many Internet multimedia applications. Transmission of real-time video has bandwidth, delay, and loss requirements. However the current Internet does not offer any quality of service (QoS) guarantees to video transmission over the Internet. In addition, the heterogeneity of the networks and end systems makes it difficult to multicast Internet video in an efficient and flexible way. Thus, designing protocols and mechanisms for Internet video transmission poses many challenges. In this paper, we take a holistic approach to these challenges and present solutions from both transport and compression perspectives. With the holistic approach, we design a framework for transporting real-time Internet video, which includes two components, namely, congestion control and error control. Specifically congestion control consists of rate control, rate-adaptive encoding, and rate shaping; error control consists of forward error correction (FEC), retransmission error resilience, and error concealment. For the design of each component in the framework, we classify approaches and summarize representative research work. We point out there exists a design space which can be explored by video application designers and suggest that the synergy of both transport and compression could provide good solutions.

With the success of the Internet and flexibility of MPEG-4, transporting MPEG-4 video over the Internet is expected to be an important component of many multimedia applications in the near future. Video applications typically have delay and loss requirements, which cannot be adequately supported by the current Internet. Thus, it is a challenging problem to design an efficient MPEG-4 video delivery system that can maximize the perceptual quality while achieving high resource utilization. This paper addresses this problem by presenting an end-to-end architecture for transporting MPEG-4 video over the Internet. We present a framework for transporting MPEG-4 video, which includes source rate adaptation, packetization, feedback control, and error control. The main contributions of this paper are: (1) a feedback control algorithm based on the Real Time Protocol (RTP) and the Real Time Control Protocol (RTCP); (2) an adaptive source-encoding algorithm for MPEG-4 video which is able to adjust the output rate of MPEG-4 video to the desired rate; and (3) an efficient and robust packetization algorithm for MPEG video bit-streams at the sync layer for Internet transport. Simulation results show that our end-to-end transport architecture achieves good perceptual picture quality for MPEG-4 video under low bit-rate and varying network conditions and efficiently utilizes network resources.

This paper presents an implementation architecture based on per flow queueing that is capable of achieving QoS provisioning for future integrated services networks consisting of the guaranteed service (GS), the controlled-load (CL), and the best-effort (BE) service classes. We propose several novel traffic management mechanisms, including adaptive rate allocation for controlled-load (ARC), a hybrid model-based and measurement-based admission control algorithm for GS and CL flows, and a quasi-pushout plus (QPO+) packet discarding mechanism. Simulation results show that our architecture and algorithms provide hard QoS guarantees to GS flows under all conditions, consistent (soft) QoS to CL flows under both light and heavy load conditions, and effective control of negative impact from non-conforming CL flows. Our architecture and algorithms also resolve several issues associated with the traditional class-based approach.

It is a challenging problem to design an efficient MPEG-4 video delivery system that can machine the perceptual quality while achieving high resource utilization. This paper addresses this problem by presenting an architecture of transporting MPEG-4 video over the Internet, which includes an end-to-end feedback control algorithm and a source encoding rate control algorithm. Our feedback control algorithm is capable of estimating the available bandwidth in the network based on the feedback information from the receiver, while our source encoding rate control algorithm is able to adjust the encoding rate of MPEG-4 video to the desired rate. Simulation results demonstrate that our architecture achieves good perceptual picture quality under low bit-rate and varying network conditions while efficiently utilizing network resources.

Provision of quality-of-service (QoS) guarantees is an important and challenging issue in the design of asynchronous transfer mode (ATM) networks. call admission control (CAC) is an integral part of the challenge and is closely related to other aspects of network designs such as traffic characterization and QoS specification. Since the usage parameter control (UPC) parameters are the only standardized traffic characterization, developing efficient CAC schemes based on UPC parameters is significant for the implementation of CAC on ATM switches. We develop a CAC algorithm called TAP (derived from tagged probability) as well as two other CAC algorithms using the UPC parameters. These CAC algorithms are based on our observation that the loss-probability-to-overflow-probability ratio tends to decrease as the number of sources increases. By introducing the loss-probability-to-overflow-probability ratio K, we find that this ratio sheds light on increasing resource utilization while still guaranteeing QoS. Analysis, simulation, and numerical results have shown that the TAP algorithm is simple and efficient.