With the rapid development of lunar exploration, devices deployed on the lunar surface will encounter emergency events including meteor impacts and lunar dust storms. Additionally, the extreme lunar environment characterized by intense radiation and the high latency of Earth-based cloud computing pose severe challenges to real-time and reliable task processing. Existing collaborative computing and fault-tolerant schemes are not fully efficient in dynamic radiation environments. To address these challenges, a collaborative computing architecture integrating lunar surface devices and lunar orbit satellites is proposed for lunar emergency tasks. Comprehensive network, radiation, communication and computing models are established to support this architecture. The problem is then formulated as a multi-objective optimization problem and solved by the Radiation-aware hiErarchical collAborative Fault-Tolerant Reinforcement Learning (REAFTRL) algorithm, which integrates radiation-aware, hierarchical decision-making, and fault-tolerant execution with feedback mechanisms. Simulations show the proposed collaborative computing scheme outperforms traditional fault-tolerant strategies in task completion time, completion rate, and error rate, providing a reliable solution for future lunar exploration.

In continuous casting and rolling (CCR) systems, precise billet cutting is critical for ensuring product dimensional accuracy and minimizing material waste. However, conventional rule-based cutting strategies rely on static parameters and heuristic rules, which often fail to adapt to real-time disturbances such as thermal expansion, cross-sectional fluctuations, and trimming losses. These limitations frequently lead to suboptimal control performance and excessive residual lengths. Deep reinforcement learning (DRL), with its dynamic decision-making and self-adaptive capabilities, offers a promising alternative. This study proposes an intelligent billet cutting strategy based on the Proximal Policy Optimization (PPO) algorithm, integrating process disturbances, thermodynamic characteristics, and physical constraints into a unified control framework. Extensive evaluations conducted in a high-fidelity CCR simulation environment demonstrate that the proposed method outperforms both traditional approaches and existing RL-based methods in terms of control accuracy, generalization ability, and robustness to disturbances, highlighting its practical potential in intelligent steel manufacturing systems.

In distribution networks, incipient faults often manifest as faint and transient electrical disturbances before fully developing. Incipient fault detection is challenging due to the weak and non-stationary characteristics of fault signatures. Moreover, fault feeder identification is more difficult, as residuals across feeders tend to appear highly similar. To address these challenges, we present FD-Mamba, a Mamba-based neural state-space model that integrates control-theoretic principles with signal-processing techniques. Specifically, we propose a Kalman-inspired neural correction mechanism that performs residual-driven state updates with learnable gain factors. In addition, we introduce a frequency-momentum updating mechanism that stabilizes frequency tracking under non-stationary perturbations. Experimental results on two datasets show that FD-Mamba outperforms existing methods. It achieves a root mean square error of 0.427 and fault feeder detection accuracy of 98.1% on real-world field dataset.

The proliferation of hidden WiFi cameras has raised serious privacy concerns, making their accurate detection and localization essential for the secure development of future intelligent wireless networks. However, existing solutions often require substantial user involvement, large movement spaces, predefined system parameters, or pre-collected training data, limiting their practicality and scalability. In this paper, we present DiffLoc+, a novel and low-cost system that localizes hidden WiFi cameras by harnessing the fundamental physical principle of electromagnetic diffraction. When an obstacle crosses the line-of-sight path between a transmitter and a receiver, it causes a distinctive signal attenuation pattern. We theoretically analyze the feasibility of exploiting this phenomenon for localization and identify two key conditions for building an unbiased diffraction-based model: symmetry and observability. To satisfy these conditions, DiffLoc+ introduces a controllable diffraction generation mechanism that precisely rotates a small metal plate around a WiFi receiver (e.g. a Raspberry Pi), producing a stable and predictable diffraction “shadowing” effect. We then construct an unbiased localization model that maps this effect to the azimuth of the camera. To ensure the robustness of the theoretical model in real-world applications, DiffLoc+ further introduces two robustness-enhancing mechanisms: (1) an attenuation-region difference-driven subcarrier selection method, which filters subcarriers that reliably reflect the diffraction attenuation pattern by quantifying the signal contrast between diffraction- and reflection-dominated regions; and (2) an uncertainty evaluation framework that integrates result consistency and diffraction signal quality to eliminate unreliable estimates. Implemented entirely with commodity off-the-shelf (COTS) hardware, DiffLoc+ achieves an average angular error of 11.92° across six diverse indoor environments and eleven commercial camera models, demonstrating its effectiveness and robustness.

3D motion magnification aims to enable us to visualize subtle, imperceptible motions by integrating eulerian video magnification with novel view synthesis. Existing method extracts the variation of feature embeddings using Neural Radiance Fields (NeRF) over time. However, this volume rendering technique suffers from two shortcomings for 3D motion magnification: (1) When reconstructing time-varying scenes through volume rendering, spatial-temporal operations between static and dynamic representations often generate noticeable artifacts, leading to blurred magnified frames. (2) When processing high-resolution dynamic scenes, the intrinsically low rendering efficiency of these techniques causes excessive computational latency, preventing real-time visualization. In this work, instead of NeRF, we propose a novelTime-varying Gaussian Splatting for 3D Motion Magnification(TG4MM) that is capable of achieving real-time rendering while effectively handling blurred magnified frames in dynamic 3D motion magnification scenes. Specifically, we propose a motion-space decoupled triplane modeling approach. The space triplane captures major spatial structures from the first frame, while the motion triplane captures subtle motion information from subsequent frames. Furthermore, we develop a phase-based motion magnification module that enhances subtle motions by applying filters within the embedding space and subtle motion triplane. Experimental results demonstrate the effectiveness of our method, showing that it outperforms existing 3D motion magnification techniques and achieves a speed up to 126 FPS.

With the increasing use of electronic devices, online handwriting verification has become crucial for biometricsbased identity authentication. Traditional methods, which rely on content-dependent verification of the writer's name, are vulnerable to forgery. This paper introduces a content-independent handwriting authentication system, Ph-Wri, designed for commodity smartphones. The core innovation is a multi-path attention feature fusion network that combines both static features (image of the handwritten text) and dynamic features (time-dependent properties during writing), to abstract the handwriting style instead of specific content for recognition, enabling robust user authentication. To extract handwriting style from dynamic writing features, we propose a polarity-aware attention strategy during training. This strategy incorporates Style Channel Attention (SCA) to capture direction-sensitive stylistic features, and Trajectory Spatial Attention (TSA) to highlight key handwriting trajectory regions. In the fine-tuning stage, the Correlation-Aware Attention (CAA) module models inter-channel structural correlations, mitigating the influence of content and enhancing style-consistent representations. By linking content-independent handwriting style to user identity, the system achieves accurate authentication. Extensive experiments on both the self-built CIEHD dataset and the public BiosecurID dataset demonstrate exceptional performance, achieving a 99% Verification Accuracy on CIEHD. Compared to state-of-theart methods that utilize only static or dynamic data, Ph-Wri significantly reduces the Equal Error Rate, showcasing the effectiveness and practicality of the proposed approach.

In Vehicular Edge Computing (VEC), load imbalances among edge servers, driven by varying traffic densities and computational demands across geographic areas, can lead to significant delays, decreased efficiency, and potential service disruptions, adversely affecting both user experience and system reliability. This study proposes an innovative adaptive load balancing method that integrates deep reinforcement learning with predictive analytics to optimize resource allocation in VEC. The framework comprises a predictive model called ST-ChebNet, enhanced with Chebyshev polynomials in graph convolutional networks for accurate workload forecasting, and an adaptive model compression strategy utilizing knowledge distillation to dynamically adjust compression ratios based on anticipated workloads. Additionally, the integration of this predictive model with the Soft Actor-Critic (SAC) algorithm, termed GC-SAC, effectively combines graph-based predictive insights with reinforcement learning techniques to tailor resource distribution, minimizing computational delays and enhancing system responsiveness. The simulation results show that the GC-SAC algorithm can significantly reduce the average delay and average energy consumption of vehicular tasks, as well as the workload rate of edge servers.

Generalizable WiFi gesture recognition has gained increasing attention for its contactless operation, ubiquitous infrastructure and enhanced robustness. Among existing methods, source-free domain adaptation (SFDA) stands out by preserving privacy and reducing computational demands without relying on source data. Current methods typically process low-level WiFi signals and their high-level semantic representations from a unified perspective, making temporal semantic learning highly susceptible to low-level signal noise and lacking consistent semantic guidance for cross domain alignment, thereby limiting the effectiveness. In this paper, we propose ViFi, a novel SFDA framework specifically designed for cross-domain WiFi gesture recognition. Unlike prior work, ViFi introduces a viewpoint-hierarchical strategy that explicitly processes cross-domain sensing from two perspectives: the perceptual (signal-level) and the semantic (gesture-level). This separation mitigates the impact of signal noise on high-level semantics while preventing semantic space drift during domain alignment. ViFi operates in two key stages. First, it anchors the perceptual encoder and employs masked signal semantic reconstruction to learn robust high-level temporal semantics. Then, it freezes the semantic encoder and aligns the perceptual encoder across domains, again leveraging masked reconstruction to ensure alignment under a unified and meaningful semantic space. We evaluate ViFi on a public dataset, and experimental results show that our viewpoint-hierarchical method achieves over 15% improvement compared to the baseline and significantly outperforms state-of-the-art approaches.

Gesture recognition plays a vital role in human-computer interaction. Most current gesture recognition systems infer gesture categories directly from raw inputs, often missing the semantic information embedded in the gesture execution process. This paper introduces a novel vision-based gesture semantic understanding system, referred as SEGUS. The goal of this system is to retrieve the symbol and path information contained in gestures. It utilizes a side-mounted camera on a wristband or smartwatch to capture video inputs and performs foreground-background separation of the video. The system extract is symbol and path information form the foreground and the background of T and video, respectively. Then, it achieves gesture recognition by comparing sequences of semantic elements. We evaluate the system through extensive experiments. The results indicate an average improvements from 6.68% to 16.39% in recognition accuracy compared to other end-to-end systems. Additionally, scalability tests show that by reorganizing existing semantic elements, the proposed system can accommodate newly added gestures without the need to re-collect sample data. This significantly reduces system overhead, achieving a 64.10% reduction in training time compared to methods requiring a training set for all gestures, with only a modest average accuracy decrease of 6.39%.

The advancement of Low Earth Orbit (LEO) satellite technology has enabled rapid progress in on-orbit machine learning. However, limited on-board computational resources hinder large-scale model training on individual satellites. Furthermore, the highly dynamic network topology and resource heterogeneity of LEO satellite constellations make collaborative training prone to single-point failures and privacy risks. To address these issues, this paper proposes ConSFL, a lightweight Contrastive learning-driven Split Federated Learning framework. ConSFL enables local feature extraction from unlabeled remote sensing data under resource-constrained conditions, while preserving both model completeness and data privacy. By performing federated learning across heterogeneous submodels, the training of the global model can focus on learning features within specialized semantic dimensions, thereby enhancing overall performance. Additionally, we introduce a spatial attention pooling (SAP) method into ConSFL to aggregate intermediate features with larger feature map sizes from submodel outputs. Simulation results show that ConSFL achieves higher Top-1 accuracy across submodels compared to the best baseline, while SAP enhances ConSFL's ability to capture feature-space information and improves submodel performance under earlyexit mechanisms.

Dynamic Facial Expression Recognition (DFER) plays a critical role in affective computing and human-computer interaction. Although existing methods achieve comparable performance, they inevitably suffer from performance degradation under sample heterogeneity caused by multi-source data and individual expression variability. To address these challenges, we propose a novel framework, called Heterogeneity-aware Distributional Framework (HDF), and design two plug-and-play modules to enhance time-frequency modeling and mitigate optimization imbalance caused by hard samples. Specifically, the Time-Frequency Distributional Attention Module (DAM) captures both temporal consistency and frequency robustness through a dual-branch attention design, improving tolerance to sequence inconsistency and visual style shifts. Then, based on gradient sensitivity and information bottleneck principles, an adaptive optimization module Distribution-aware Scaling Module (DSM) is introduced to dynamically balance classification and contrastive losses, enabling more stable and discriminative representation learning. Extensive experiments on two widely used datasets, DFEW and FERV39k, demonstrate that HDF significantly improves both recognition accuracy and robustness. Our method achieves superior weighted average recall (WAR) and unweighted average recall (UAR) while maintaining strong generalization across diverse and imbalanced scenarios. Codes are released at https://github.com/QIcita/HDF_DFER.

Gaussian splatting video has recently emerged as a promising representation for immersive 6-degree-of-freedom (6DoF) content due to its low-latency rendering, compact data structure, and high visual fidelity. In particular, 4D Gaussian splatting video-which models dynamic scenes as temporally evolving Gaussian splats in 3D space-offers an efficient solution for rendering photorealistic, interactive experiences. However, a systematic understanding of user behavior in such environments, especially head movement, remains largely unexplored due to the absence of dedicated datasets tailored to this format. This lack of data severely limits progress in viewpoint prediction, attention modeling, and video streaming optimization. To address this critical gap, we introduce ViewGauss-the first publicly available dataset that captures full 6DoF head movement during the viewing of 4D Gaussian splatting videos. Our dataset is collected from 35 participants using a high-precision Vive Focus Vision headset in a controlled environment, while they freely watched four reconstructed Gaussian splatting video sequences derived from the HiFi4G dataset. The data are recorded with high temporal resolution using position coordinates and unit quaternions, and organized into structured CSV files with precise timestamps for downstream synchronization and behavioral analysis. To demonstrate the practical value of ViewGauss, we conduct a preliminary viewpoint prediction experiment using the iTransformer model. The results show that head orientation patterns in 4D Gaussian splatting video scenes are not only temporally coherent but also learnable, highlighting the potential of ViewGauss as a benchmark for future behavioral modeling and predictive rendering systems. The dataset is publicly available at: https://github.com/Cedarleigh/ViewGauss-DataSet.

Point cloud is widely used in computer vision and augmented reality for representing 3D information of real-world scenes. However, challenges such as noise, incompleteness, and quality variations, particularly in dynamic environments, hinder effective processing and analysis. These issues are further complicated in human activity scenarios due to motion and changing lighting. To address these challenges, this paper introduces a point cloud video dataset PCVD captured with synchronized Azure Kinect cameras, designed to support tasks like denoising, segmentation, and motion recognition in single and multi-person scenes. It provides high-quality depth and color data from diverse real-world scenes with human actions. We compare it with existing datasets, and the results show its superiority in uniformity and completeness, making it ideal for dynamic environments. We also evaluate the state-of-the-art denoising schemes on this dataset to demonstrate the practicality and sophistication of the dataset. The dataset is publicly available at https://github.com/Atlantichan/PCVD-A-Dataset-of-Point-Cloud-Video-for-Dynamic-Human-Interaction.

In active distribution networks (ADNs), the rapid changes in photovoltaic (PV) generation can easily lead to short-term voltage stability issues. However, achieving real-time voltage control under limited communication resources is a major challenge. This paper addresses this issue by introducing a novel co-scheduling scheme for volt/var control and wireless resources allocation. We model the nonlinear dynamics between PV generation and communication delay into a co-scheduling optimization problem, targeting the minimization of system voltage deviations. To efficiently solve this problem, we propose a multi-agent reinforcement learning (MARL) algorithm, termed Meta-learning Equivalent model-based Hierarchical Reinforcement Learning (MEHRL). This algorithm employs a hierarchical reinforcement learning (HRL) framework to segment the complex action space and incorporates a meta-learning equivalent (ME) model to enhance adaptability during distributed training and decentralized execution (DTDE). Simulation results validate the efficacy of the proposed co-scheduling scheme in ADNs and underscore the advanced capabilities of the MEHRL algorithm in addressing the optimization challenge.

Cloud–edge collaboration and edge intelligence have greatly driven the growth of the Industrial Internet of Things (IIoT). However, the jittery network delay and limited computational resources of edge servers make it difficult to meet the stringent latency requirements in IIoT, and so far there is no good solution to solve this problem. To this end, we introduce scalable neurocomputing, which provides neural networks with different utilities and computation resource requirements, to be deployed on edge servers of cloud–edge IIoT systems. We then optimize such systems by formulating data scheduling and system computational resource allocation as an infinite horizon optimization problem, considering that the data collection from end devices is an infinite long-term process. To solve this hard problem, we design a rolling prediction-optimization framework that transforms the infinite horizon problem into a truncated finite horizon optimization that maximizes the average system utility while satisfying the stringent delay constraints. We have conducted extensive simulations and built a prototype system, which verify the feasibility and performance of our proposed scheme.

Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge. Nonetheless, existing methods deal with continuous data streams in a centralized manner, limiting their applicability in scenarios that prioritize data privacy and security. To this end, this paper introduces federated few-shot class-incremental learning, a decentralized machine learning paradigm tailored to progressively learn new classes from scarce data distributed across multiple clients. In this learning paradigm, clients locally update their models with new classes while preserving data privacy, and then transmit the model updates to a central server where they are aggregated globally. However, this paradigm faces several issues, such as difficulties in few-shot learning, catastrophic forgetting, and data heterogeneity. To address these challenges, we present a synthetic data-driven framework that leverages replay buffer data to maintain existing knowledge and facilitate the acquisition of new knowledge. Within this framework, a noise-aware generative replay module is developed to fine-tune local models with a balance of new and replay data, while generating synthetic data of new classes to further expand the replay buffer for future tasks. Furthermore, a class-specific weighted aggregation strategy is designed to tackle data heterogeneity by adaptively aggregating class-specific parameters based on local models performance on synthetic data. This enables effective global model optimization without direct access to client data. Comprehensive experiments across three widely-used datasets underscore the effectiveness and preeminence of the introduced framework. We will release our code at: https://github.com/XuSiang1/F2SCIL-SDD.

Sensor devices continuously generate large volumes of time series data in the Internet of Things (IoT) environment. These voluminous streams require models that scale to massive data while discerning the intricate, multi-scale patterns embedded in diverse temporal sequences. Transformer models have been widely used for IoT time series analysis due to their strong feature representation and global modeling capability. However, existing architectures struggle to explicitly capture temporal structures and adapt to non-stationary data, limiting classification performance. To address these issues, we propose a novel attention mechanism based on the autocorrelation function, named A2T, which leverages lag characteristics to unify temporal modeling and feature extraction. We further introduce a Parameterized Wavelet Transform Module that learns scale and bandwidth end-to-end and uses an attention gate to fuse multi-resolution coefficients. Building on this, we design a Dual-Channel Time-Frequency Feature Extraction module to improve adaptability to distribution shifts. Integrating these components, we develop A2Tformer for IoT time series classification. Experimental results on the UCR dataset demonstrate that A2Tformer achieves an average accuracy of 84.49% and ranks first on 26 out of all datasets, outperforming state-of-the-art Transformer-based models.

Edge collaboration has emerged as a promising paradigm for Internet of Things (IoT) applications. However, achieving efficient cooperation among these server nodes still faces several critical challenges, including 1) secure node interaction, 2) online task scheduling, and 3) heterogeneous resource management. Unfortunately, most existing solutions address these issues in isolation, lacking an integrated framework that jointly considers security, task scheduling, and resource management. To address these limitations, this paper proposes a blockchain-based online collaboration framework for IoT, where blockchain serves as a trusted top-layer management platform to ensure secure information sharing and resource management. In the proposed framework, we introduce two dynamic queues to effectively manage randomly arriving tasks and develop an online collaboration mechanism tailored for heterogeneous edge servers. Furthermore, we formulate a long-term system utility maximization problem by jointly optimizing collaboration strategies, resource allocation, and block producer selection, subject to queue stability and security constraints. Due to the coupling among decision variables and across time slots, solving the optimization problem directly is challenging. Therefore, we design a novel Lyapunov-based algorithm that integrates convex optimization theory with deep reinforcement learning (DRL), significantly improving the solving efficiency. Extensive simulations demonstrate that the proposed method and algorithm outperform conventional baseline methods and pure DRL-based approaches in terms of system utility, stability, and security performance, making it a promising solution for secure and efficient edge collaboration in dynamic IoT environments.

WiFi channel state information (CSI)-based gesture recognition offers unique advantages, including cost-effectiveness and enhanced privacy protection, and has garnered significant attention in recent years. However, existing WiFi-based gesture recognition solutions exhibit poor generalization ability when deployed in new environment, orientation, or location. Although some methods combine labeled source domain and unlabeled target domain to learn domain-independent features, factors, such as data privacy protection, hinder access to source data during practical environment adaptation. Consequently, we consider realistic scenario where source data is unavailable during adaptation of unlabeled test data, and instead, a trained source domain model is used. In this article, we propose Wi-SFDAGR, a WiFi-based source-free domain adaptation gesture recognition framework. Specifically, we treat cross-domain as an unsupervised clustering problem, aiming to ensure that features within local neighborhoods exhibit similar prediction results while those farther apart display different prediction outcomes in the feature space. We theoretically analyze the effect of enhanced prediction consistency between neighbor points extracted from gestures on generalization error. Furthermore, we employ an attraction-dispersion network to strengthen prediction consistency among closely located features in the feature space while reducing it for distantly located features. To mitigate noise introduced during nearest neighbor sample selection in the feature space (where predictions may not align with the input sample’s prediction), we progressively improve nearby sample feature aggregation by estimating uncertainty to reweight local neighborhood predictions. Finally, extensive experiments are conducted on the Widar 3.0 and XRF55 datasets and the results show our proposed framework outperforms most cross-domain methods.

In modern vehicular networks, the absence of infrastructure support, such as roadside units (RSUs), presents significant challenges for efficient task offloading and allocation. Limited computational capabilities of individual vehicles, combined with task allocation imbalances caused by varying task complexity and vehicle capacities, further complicate the process. Additionally, the formation of vehicular platoons requires accurate future route and destination information to ensure stable collaboration and effective coordination. However, such information can be challenging to obtain due to dynamic and unpredictable road environments, hindering the reliability of platoon formation. To address these challenges, we propose a platoon-based offloading strategy that integrates deep reinforcement learning (DRL) and long short-term memory (LSTM) networks to enhance task allocation efficiency. This approach also leverages the convoy formation algorithm considering future positions (CFA-FPs) to manage platoon constraints effectively. Experimental results demonstrate that our method significantly improves key performance metrics, including total computation cost, latency, and offloading success rate, compared to other task offloading strategies.

Pulmonary function testing is a crucial examination for respiratory diseases. Current medical spirometers are bulky and inconvenient, while available portable spirometers are extremely expensive and often lack accuracy. Furthermore, both devices require direct contact, inevitably increasing the cross-infection risk. To tackle these challenges, we propose Wi-Pulmo, an end-to-end deep learning-based Wireless System that utilizes WiFi channel state information (CSI) to provide contact-free, convenient, cost-effective, and precise pulmonary function testing outside the clinical setting. Based on the analysis of thoracic and abdominal movement patterns, Wi-Pulmo first validates the feasibility of using WiFi to estimate pulmonary function. Then, Wi-Pulmo designs an efficient fine-grained sensing quality-based algorithm for complete exhalation segmentation. Additionally, a relevant interference-tolerant learning algorithm based on variational inference is proposed to accurately map the CSI of WiFi signals to pulmonary function. Extensive experiments achieved average monitoring error rates of 2.59% for normal subjects in daily scenarios and 5.87% for real patients in tertiary hospitals over a two-month period. These satisfactory results demonstrate the strong effectiveness and robustness of Wi-Pulmo. Furthermore, our findings in clinical reveal a close correlation between chronic diseases and pulmonary function.

Connected and autonomous vehicles (CAVs) are an important paradigm of intelligent transportation systems. Cooperative perception (CP) and vehicular edge computing (VEC) enhance CAVs’ perception capacity of the region of interest (RoI) while alleviating the pressure of intensive computation on onboard resources. However, existing CP and computation schemes are based on inefficient broadcast communications and still face challenges, such as highly dynamic communication link channel conditions caused by vehicle mobility, and limited computing resources in VEC environments. Considering the delay sensitivity of CAVs’ perception tasks and the need for enhanced perception, we propose a unicast-based cooperative perception and computation scheme to achieve more efficient resource utilization and perception task execution in VEC scenarios. Our goal is to maximize CP gain and minimize task execution delay by optimizing the decision of each ego CAVs. To solve the sequential decision-making problem of multiobjective optimization, we propose a solution based on improved multiagent proximal policy optimization deep reinforcement learning, where CAVs agents make adaptive decisions distributed based on partial observations. Simulation results show that compared with the baseline algorithm, our proposed scheme effectively reduces the execution delay of ego CAVs perception tasks and ensures a high perception gain.

Satellite Edge Computing (SEC) enhances real-time data processing by deploying computational resources at the edge of satellite networks, reducing Task Completion Delay (TCD). To minimize TCD, the characteristics of satellites with large coverage, strong collaborative capabilities, and limited resources must be fully considered. This paper proposes a novel three-stage task offloading framework to optimize task execution in dynamic and resource-constrained satellite environments. First, to efficiently offload computational tasks among large-scale, heterogeneous users, we introduce a region division-based offloading strategy and develop the Adaptive Division Offloading Region (ADOR) algorithm, which dynamically partitions satellite coverage areas to improve offloading efficiency. Second, to enhance the collaborative computing capabilities of Low Earth Orbit (LEO) satellite constellations, we propose a Particle Swarm Optimization Genetic (PSOG) algorithm to optimize TS under dynamic conditions. Finally, to tackle the limited and interdependent computing resources of satellites, we design an Intelligent Parameter Adjustment (IPA) algorithm based on Q-learning, which dynamically adjusts computational parameters to maximize processing speed while ensuring system stability. Simulation results demonstrate that our proposed framework outperforms existing methods. Compared with the baseline algorithm, it achieves higher task offloading efficiency and better resource allocation. Additionally, it maintains stable satellite operations while reaching the highest processing speed.

Federated learning (FL), an emerging distributed learning paradigm, addresses challenges in decentralized environments, particularly in internet of things (IoT) networks where numerous devices generate vast amounts of private data. A major concern in FL for IoT systems is communication overhead, especially in resource-constrained and wireless environments where frequent model uploads for aggregation create a critical bottleneck. As the complexity of neural networks increases, traditional FL methods demand substantial communication resources, which limits scalability in IoT applications. To address this, we propose a novel sparse communication mechanism for FL, called FedSC, that achieves high generalization performance and accuracy under extremely low communication frequencies, particularly for non-IID data. On the client side, we propose a multi-level model compression mechanism to capture and retain important information from the trained local model, which is then uploaded to the server. On the server side, we propose an iterative extraction mechanism to reconstruct models of uniform size based on the client models. Each extraction is followed by an aggregation step in an iterative process, ensuring effective generalization with non-IID data. As a result, clients need to upload their models only 1-5 times after completing local training, significantly reducing the communication overhead compared to traditional FL, which requires continuous uploads throughout the entire training process. Simulations on public datasets with popular deep learning models demonstrate that FedSC reduces the number of model uploads from hundreds to just 1-5 times while maintaining high accuracy, highlighting its potential to significantly enhance communication efficiency for FL in IoT systems.

Because of the ambiguous and subjective property of the facial expression, the label noise is widely existing in the FER dataset. For this problem, in the training phase, current methods often directly predict whether the label is noised or not, aiming to reduce the contribution of the noised data. However, we argue that this kind of method suffers from the low reliability of such noise data decision operation. It makes that some mistakenly abounded clean data are not utilized sufficiently and some mistakenly kept noised data disturbing the model learning. In this paper, we propose a more reliable noise-label suppression method called ReSup. First, instead of directly predicting noised or not, ReSup makes the noise data decision by modeling the distribution of noise and clean labels simultaneously according to the disagreement between the prediction and the target. Specifically, to achieve optimal distribution modeling, ReSup models the similarity distribution of all samples. To further enhance the reliability of our noise decision results, ReSup uses two networks to jointly achieve noise suppression. Specifically, ReSup utilize the property that two networks are less likely to make the same mistakes, making two networks swap decisions and tending to trust decisions with high agreement. Extensive experiments on popular datasets shows the effectiveness of ReSup.

Digital Twins are virtual representations of physical assets and systems that rely on effective Data Management to integrate, process, and analyze diverse data sources. This article comprehensively examines Data Management challenges, architectures, techniques, and applications in the context of Digital Twins. It explores key issues such as data heterogeneity, quality assurance, scalability, security, and interoperability. The paper outlines architectural approaches like centralized, distributed, cloud-based, and blockchain solutions and Data Management techniques for modeling, integration, fusion, quality management, and visualization. Domain-specific considerations across manufacturing, smart cities, healthcare, and other sectors are discussed. Finally, open research challenges related to standards, real-time data processing, intelligent Data Management, and ethical aspects are highlighted. By synthesizing the state-of-the-art, this review serves as a valuable reference for developing robust Data Management strategies that enable Digital Twin deployments.

Autonomous aerial vehicles (AAVs) have found widespread utility in the field of multi-target tracking (MTT) due to their inherent advantages, such as ease of deployment, flexible maneuverability, and cooperative communication capabilities. AAVs can perform tasks ranging from regional surveillance to tracking and search-and-rescue operations in hazardous environments. Nonetheless, the issue of how to efficiently coordinate multiple AAVs to track diverse mobile targets remains a critical concern. This paper focuses on MTT with multi-AAV, aiming at optimizing system performance in scenarios where network availability is limited. In contrast to treating sensor perception as a monolithic process, we propose a scheme for cooperative sensing and data processing. This scheme is designed to reduce system response latency in environmental information sensing and multidimensional data processing for multiple AAVs. Furthermore, in contrast to assuming linear target movement and single-step target position prediction, we introduce a multi-agent deep reinforcement learning (MADRL) framework combined with multi-step prediction extended Kalman Filter (MP-EKF). This framework is tailored to enhance tracking precision, especially when targets’ trajectories are curved, which can reduce AAV flight displacement if the target’s position can be predicted multiple steps later. In addition, unlike using latency as a real-time application to measure the “freshness” of information, the Age of Information (AoI) is introduced for considering the waiting time of transmission and calculation between multiple AAVs. This assessment method is utilized to comprehensively evaluate and mitigate data latency within the MADRL algorithm. Finally, extensive simulation experiments demonstrate that the proposed scheme significantly outperforms both baseline methods and state-of-the-art approaches in terms of AoI, system latency, and energy consumption.

In large-scale dynamic network environments, optimizing the computation offloading and resource allocation strategy is key to improving resource utilization and meeting the diverse demands of User Equipment (UE). However, traditional strategies for providing personalized computing services face several challenges: dynamic changes in the environment and UE demands, along with the inefficiency and high costs of real-time data collection; the unpredictability of resource status leads to an inability to ensure long-term UE satisfaction. To address these challenges, we propose a Knowledge-Defined Networking (KDN)-based Adaptive Edge Resource Allocation Optimization (KARO) architecture, facilitating real-time data collection and analysis of environmental conditions. Additionally, we implement an environmental resource change perception module in the KARO to assess current and future resource utilization trends. Based on the real-time state and resource urgency, we develop a deep reinforcement learning-based Adaptive Long-term Computation Offloading and Resource Allocation (AL-CORA) strategy optimization algorithm. This algorithm adapts to the environmental resource urgency, autonomously balancing UE satisfaction and task execution cost. Experimental results indicate that AL-CORA effectively improves long-term UE satisfaction and task execution success rates, under the limited computation resource constraints.

Mobile Edge Computing (MEC) is a distributed computing paradigm that provides computing capabilities at the periphery of mobile cellular networks. This architecture empowers Mobile Users (MUs) to offload computation-intensive applications to large-scale computing nodes near the edge side, reducing application latency for MUs. The resource allocation and task offloading in MEC has been widely studied. However, the burgeoning complexity inherent to modern applications, often represented as Directed Acyclic Graphs (DAGs) comprising a multitude of subtasks with interdependencies, poses huge challenges for application offloading and resource allocation. Meanwhile, previous work has neglected the impact of edge caching on the offloading execution of dependent tasks. Therefore, this paper introduces a novel dynamiccaching dependency-aware taskoffloading (CachOf) scheme. First, to effectively enhance the rationality of cache and computing resource allocation, we develop a subtask priority computation scheme based on DAG dependencies. This scheme includes the execution sequence priority of subtasks on a single MU and the offloading sequence priority of subtasks from multiple MUs. Second, a dynamic caching scheme, designed to cater to dependent tasks, is proposed. This caching approach can not only assist offloading decisions, but also contribute to load balancing by harmonizing caching resources among edge servers. Finally, based on the task prioritization results and caching results, this paper presents a Deep Reinforcement Learning (DRL)-based offloading scheme to judiciously allocate resources and improve the execution efficiency of applications. Extensive simulation experiments demonstrate that CachOf outperforms other baseline schemes, achieving improved execution efficiency for applications.

To guarantee the low-congestion performance and quality of service (QoS) requirements of multi-services in Mega Low Earth Orbit Constellation Networks (MLEOCN), this paper focuses on the comprehensive communication link model in MLEOCN, commencing from users to access satellites, relayed by relay satellites, and finally delivered to the gateway by feeder satellites. Aiming at the problems of high congestion and low throughput in traditional path planning algorithms, we innovatively propose a multi-objective optimization service-correlated path optimization algorithm based on stochastic hill climbing strategy (MSCPO-SHCS). The algorithm initially achieves the joint optimization of three metrics through regular mapping and judicious weighting. Subsequently, it assesses the interplane hop via geometric parameter theory analysis (GPTA), then decouples the large-scale mixed integer optimization problem into the integer optimization problem superimposed linear programming problem, and ultimately employs the stochastic hill climbing strategy (SHCS) for path intelligent optimization. Based on the path Gaussianity assumption, we theoretically prove and numerically verify the convergence of the proposed algorithm. The simulation results indicate that the proposed algorithm boosts the throughput and load balancing coefficient compared with the greedy strategy, service-uncorrelated, minimum hop count, and resource allocation optimization. Additionally, it decreases the hop count compared with the maximum throughput and maximum balancing coefficient and maintains the optimal overall performance.

Volumetric video, also referred to as hologram video, is an emerging medium that represents 3D content in extended reality. As a next-generation video technology, it is poised to become a key application in 5G and future wireless communication networks. Because each user generally views only a specific portion of the volumetric video, known as the viewport, accurate prediction of the viewport is crucial for ensuring an optimal streaming performance. Despite its significance, research in this area is still in the early stages. To this end, this paper introduces a novel approach called Saliency and Trajectory-based Viewport Prediction (STVP), which enhances the accuracy of viewport prediction in volumetric video streaming by effectively leveraging both video saliency and viewport trajectory information. In particular, we first introduce a novel sampling method, Uniform Random Sampling (URS), which efficiently preserves video features while minimizing computational complexity. Next, we propose a saliency detection technique that integrates both spatial and temporal information to identify visually static and dynamic geometric and luminance-salient regions. Finally, we fuse saliency and trajectory information to achieve more accurate viewport prediction. Extensive experimental results validate the superiority of our method over existing state-of-the-art schemes. To the best of our knowledge, this is the first comprehensive study of viewport prediction in volumetric video streaming. We also make the source code of this work publicly available.

Volumetric videos offer an incredibly immersive viewing experience but encounters challenges in maintaining quality of experience (QoE) due to its ultra-high bandwidth requirements. One significant challenge stems from user’s spatial interactions, potentially leading to discrepancies between transmission bitrates and the actual quality of rendered viewports. In this study, we conduct comprehensive measurement experiments to investigate the impact of six degrees of freedom information on received video quality. Our results indicate that the correlation between spatial quality and transmission bitrates is influenced by the user’s viewing distance, exhibiting variability among users. To address this, we propose a spatial quality oriented rate control system, namely sparkle, that aims to satisfy spatial quality requirements while maximizing long-term QoE for volumetric video streaming services. Leveraging richer user interaction information, we devise a tailored learning-based algorithm to enhance long-term QoE. To address the complexity brought by richer state input and precise allocation, we integrate pre-constraints derived from three-dimensional displays to intervene action selection, efficiently reducing the action space and speeding up convergence. Extensive experimental results illustrate that sparkle significantly enhances the averaged QoE by up to 29% under practical network and user tracking scenarios.

The widespread adoption of 5 G networks and mobile devices has led to a surge in the generation of private data, creating massive data streams. Securing and continuously releasing histogram data over sliding windows in these streams has become a critical issue, as it enables understanding recent collective phenomena in data streams while preserving individual privacy. Existing state-of-the-art methods require buffering all data from each sliding window to reconstruct accurate histograms, which is unnecessary and significantly hampers efficiency. This paper proposes an online streaming sampling publication framework with differential privacy, named thePublishingApproach withSliding window estimation-count sketch(PAS), which constructs an approximate histogram without buffering each sliding window and subsequently generates publishable histograms. Specifically, we introduce a novel memory-efficient sketch structure called theSliding WindowEstimation-CountSketch(SES), which facilitates rapid retrieval of counts within sliding window intervals while providing guaranteed data protection. The output of this sketch structure approximates true counts while theoretically incorporating differentially private noise, thus ensuring$(\epsilon , \delta )$-differential privacy. Moreover, to improve the speed of histogram generation and reduce processing time in PAS, we propose an adaptive histogram generation algorithm based on SES. Extensive experiments are conducted to demonstrate the effectiveness of the proposed methods in comparison with other publication methods.

Recent years have witnessed a growing interest in Wi-Fi-based gesture recognition. However, existing works have predominantly focused on closed-set paradigms, where all testing gestures are predefined during training. This poses a significant challenge in real-world applications, as unseen gestures might be misclassified as known class during testing. To address this issue, we propose WiOpen, a robust Wi-Fi-based open-set gesture recognition (OSGR) framework. Implementing OSGR requires addressing challenges caused by the unique uncertainty in Wi-Fi sensing. This uncertainty, resulting from noise and domains, leads to widely scattered and irregular data distributions in collected Wi-Fi sensing data. Consequently, data ambiguity between classes and challenges in defining appropriate decision boundaries to identify unknowns arise. To tackle these challenges, WiOpen adopts a twofold approach to eliminate uncertainty and define precise decision boundaries. Initially, it addresses uncertainty induced by noise during data preprocessing by utilizing the channel state information (CSI) ratio. Next, it designs the OSGR network based on an uncertainty quantification method. Throughout the learning process, this network effectively mitigates uncertainty stemming from domains. Ultimately, the network leverages relationships among samples' neighbors to dynamically define open-set decision boundaries, successfully realizing OSGR. Comprehensive experiments on publicly accessible datasets confirm WiOpen's effectiveness.

Visual emotion analysis holds significant research value in both computer vision and psychology. However, existing methods for visual emotion analysis suffer from limited generalizability due to the ambiguity of emotion perception and the diversity of data scenarios. To tackle this issue, we introduce UniEmoX, a cross-modal semantic-guided large-scale pretraining framework. Inspired by psychological research emphasizing the inseparability of the emotional exploration process from the interaction between individuals and their environment, UniEmoX integrates scene-centric and person-centric low-level image spatial structural information, aiming to derive more nuanced and discriminative emotional representations. By exploiting the similarity between paired and unpaired image-text samples, UniEmoX distills rich semantic knowledge from the CLIP model to enhance emotional embedding representations more effectively. To the best of our knowledge, this is the first large-scale pretraining framework that integrates psychological theories with contemporary contrastive learning and masked image modeling techniques for emotion analysis across diverse scenarios. Additionally, we develop a visual emotional dataset titled Emo8. Emo8 samples cover a range of domains, including cartoon, natural, realistic, science fiction and advertising cover styles, covering nearly all common emotional scenes. Comprehensive experiments conducted on seven benchmark datasets across two downstream tasks validate the effectiveness of UniEmoX. The source code is available at https://github.com/chincharles/u-emo.

Vehicle trajectory prediction, as a key enabler of the intelligent transportation system, has attracted considerable attention from academia and industry in recent years. However, the variability and dynamism of traffic conditions pose significant challenges to current vehicle trajectory prediction methods, particularly in the form of domain bias. Domain bias occurs when a model trained on one traffic domain, such as one segment of a highway, underperforms when applied to another segment with different traffic patterns. To address this challenge and advance the field, we propose a new transfer learning-based collaborative vehicle trajectory prediction framework called TRACER, designed to provide reliable and accurate traffic predictions with high adaptability for cross-domain highway traffic scenarios. The core of our framework lies in an adaptive interactive extraction module and a trajectory generation module based on Bidirectional Long Short-Term Memory (BiLSTM), further strengthened by a pre-task of intention recognition for vehicle operation types. To improve model robustness, consistency regularization is applied by injecting disturbances into the target data, and a one-dimensional Convolution (Conv1D)-based intention extraction module is integrated into the BiLSTM-based trajectory generation process, leading to notable improvements in prediction accuracy. Our framework is first trained on source domain data, followed by the transfer of a small amount of labeled data from the target domain, and the overall model is further refined using unlabeled data. By effectively mitigating domain bias, TRACER significantly enhances trajectory prediction accuracy while maintaining high adaptability. The results underscore the importance of addressing domain shift challenges in trajectory prediction tasks and demonstrate the potential of domain adaptation techniques to improve the prediction accuracy of vehicle trajectories across different domains in highway scenarios.

It is necessary to establish a spatio-temporal correlation model in the traffic data to predict the state of the transportation system. Existing research has focused on traditional graph neural networks, which use predefined graphs and have shared parameters. But intuitive predefined graphs introduce biases into prediction tasks and the fine-grained spatio-temporal information can not be obtained by the parameter sharing model. In this paper, we consider it is crucial to learn node-specific parameters and adaptive graphs with complete edge information. To show this, we design a model based on graph structure that decouples nodes and edges into two modules. Each module extracts temporal and spatial features simultaneously. The adaptive node optimization module is used to learn the specific parameter patterns of all nodes, and the adaptive edge optimization module aims to mine the interdependencies among different nodes. Then we propose a Decoupled Adaptive Graph Convolution Attention Network for Traffic Forecasting (DAGCAN), which relies on the above two modules to dynamically capture the fine-grained spatio-temporal relationships in traffic data. Experimental results on four public transportation datasets, demonstrate that our model can further improve the accuracy of traffic prediction.

Vehicular Edge Computing (VEC) is an emerging computing paradigm that serves as a specific application of Mobile Edge Computing (MEC) in intelligent transportation systems. As a core technology of VEC, task offloading improves computing efficiency and service quality by offloading computing tasks from vehicular devices to edge nodes. However, the high mobility of vehicles, heterogeneity of resources, and real-time requirements present significant challenges for task offloading. To address the issue of reducing overall system latency and increasing the offloading success rate in multi-task offloading, we propose a task offloading scheme combining Deep Reinforcement Learning (DRL) and Kuhn-Munkres (KM) Matching algorithm, named the PDQKM offloading scheme. Firstly, to mitigate the delay caused by frequent Roadside Unit (RSU) handovers, we propose a method to detect whether a vehicle is within the coverage area of the RSU. This method filters out unreasonable offloading decisions, avoiding the overhead associated with frequent RSU handovers. Secondly, the combination of DRL and the KM matching algorithm leverages the strengths of both approaches. DRL provides initial offloading strategies in highly dynamic and high-dimensional decision environment. Although DRL may get stuck in local optima, it can quickly adapt to environmental changes. The KM matching algorithm, a classic solution for perfect task-resource matching, performs global optimization on the initial strategies provided by DRL. This integration overcomes the limitations that a single algorithm might have. Finally, to effectively coordinate and manage the heterogeneous resources of RSU, we utilize an improved KM matching algorithm to update computational resources in real time, enhancing matching efficiency. Experimental results demonstrate that PDQKM outperforms comparable offloading schemes in terms of overall system latency and offloading success rate optimization.

Hand gesture applications (HGA) are essential for human-machine interaction. Although the existing solutions achieve good performance in specific tasks, they still face challenges when users navigate through different application contexts, i.e., requiring multi-task ability to support newly arrived HGA tasks. In this paper, we propose a novel wrist-worn multi-task HGA system namedXHGA, which can implement modal-domain combination, data-domain adaptation and label-domain extension to ensure the performance in multi-task scenarios. The system introduces a novel two-stage training strategy, i.e., task-agnostic stage to align cross-modal features from unlabeled arbitrary gestures through contrastive learning, and task-related stage to learn modality contributions with limited labeled data in specific tasks through self-attention mechanism, while achieves multi-objective recognition simultaneously by employing an adaptive loss function weighting method. Extensive experiments demonstrate thatXHGAcan achieve an average accuracy of 92.7% with only using 15 labeled data per gesture under three HGA tasks. Compared with the state-of-the-art multi-modal approach,XHGAreduces 82.7% training time, and 47.7% storage, with about 5% improvements in accuracy. Code is available athttps://github.com/htang0/XHGA.

With the rise of transportation electrification, an increasing number of charging stations have been established, forming a city-scale charging system. These charging stations serve as intermediaries that connectsupplyanddemand, drawing power from the grid and renewable energy sources to provide electricity to electric vehicles. Maintaining a delicate balance between supply and demand has emerged as a significant challenge for the charging system. On amacroscopiclevel, it impacts the power grid's peak load and reliability, whilelocally, it influences electric vehicle detour events. To comprehensively model the spatio-temporal characteristics in the charging system, we partition the charging system by adopting a supply-demand-aware approach and propose OPS, an online power scheduling algorithm based on the regularization technique. OPS aims to achieve a bi-level balance between supply and demand while constraining the power output of the charging system. We substantiate the efficacy of OPS through rigorous theoretical proofs, demonstrating its comparability to the optimal solution. Furthermore, we conduct extensive evaluation experiments with real-world data sets to establish the feasibility of the proposed methodology in alleviating the supply-demand imbalance. The results indicate that OPS attains an empirical competitive ratio of less than 1.2.

In many RFID-enabled applications, objects are classified into different categories, and the information associated with each object's category (called category information) is written into the attached tag, allowing the reader to access it later. The category information sampling in such RFID systems, which is to randomly choose (sample) a few tags from each category and collect their category information, is fundamental for providing real-time monitoring and analysis in RFID. However, to the best of our knowledge, two technical challenges, i.e., how to guarantee a minimized execution time and reduce collection failure caused by missing tags, remain unsolved for this problem. In this paper, we address these two limitations by considering how to use the shortest possible time to sample a different number of random tags from each category and collect their category information sequentially in small batches. In particular, we first obtain a lower bound on the execution time of any protocol that can solve this problem. Subsequently, we present a near-OPTimalCategory information sampling protocol (OPT-C) that solves the problem with an execution time close to the lower bound. Finally, extensive simulation results demonstrate the superiority of OPT-C over existing protocols, while real-world experiments further validate its practicality.

In magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems, receiver (RX) feedback communication is promising to enhance the capability and efficiency of the system. Although some studies have explored in-band implementations with low overhead costs, it has not been comprehensively investigated. In this paper, we propose Relip, a Reliable layer-level in-band parallel feedback communication mechanism for MIMO MRC-WPT systems, which addresses the impact of RX-RX couplings (i.e., non-negligible interference from strong couplings and positive effects of relay phenomenon), and provides a theoretical analysis of communication reliability. Technically, we first devise an On-Off based two-phase modulation mechanism to achieve RX identification and dependency detection under relay phenomenon. Then, we utilize observed channel decomposability to collect group-level power transfer channel conditions for eliminating the interference caused by strong RX-RX couplings. Furthermore, we perform RX selection to optimize the trade-off between communication reliability and time overhead. We design and implement the Relip prototype and conduct extensive experiments. The results validate the effectiveness of our mechanism, i.e., Relip can provide ≥99% average decoding accuracy for concurrent feedback communication of 14 devices, achieving an 18.31% improvement compared to the state-of-the-art solution.

Although some studies in recent years have focused on the coexistence of service and task dependencies in the collaborative optimization of service caching and task offloading in Vehicle Edge Computing, the challenges brought by dual dependencies have not been fully addressed. Therefore, this paper proposes a more comprehensive joint optimization method for service caching and task offloading under dual dependencies. First, this paper proposes a service criticality prediction method based on the Gated Graph Recurrent Network to perceive complex task dependencies and accurately capture the service requirements of critical task types. Based on this, a hierarchical active-passive hybrid caching strategy is designed, which aims to satisfy diverse service demands while reducing the additional overhead caused by remote service requests. Second, a global task priority computation method based on application heterogeneity has been developed to prevent cascading delays in task chains. Finally, this paper formulates a joint optimization problem for service caching and task offloading in a three-layer VEC system, models it as a Markov Decision Process, and applies a Proximal Policy Optimization-driven collaborative optimization algorithm named COHCTO. Simulation results show that COHCTO achieves multi-objective optimization across metrics such as delay, energy consumption, caching hit rate, and application success rate under conditions different from those of other algorithms.

While the diffusion transformer (DiT) has become a focal point of interest in recent years, its application in low-light image enhancement remains a blank area for exploration. Current methods recover the details from low-light images while inevitably amplifying the noise in images, resulting in poor visual quality. In this paper, we firstly introduce DiT into the low-light enhancement task and design a novel Structure-guided Diffusion Transformer based Low-light image enhancement (SDTL) framework. We compress the feature through wavelet transform to improve the inference efficiency of the model and capture the multi-directional frequency band. Then we propose a Structure Enhancement Module (SEM) that uses structural prior to enhance the texture and leverages an adaptive fusion strategy to achieve more accurate enhancement effect. In Addition, we propose a Structure-guided Attention Block (SAB) to pay more attention to texture-riched tokens and avoid interference from noisy areas in noise prediction. Extensive qualitative and quantitative experiments demonstrate that our method achieves SOTA performance on several popular datasets, validating the effectiveness of SDTL in improving image quality and the potential of DiT in low-light enhancement tasks.

Unmanned aerial vehicles (UAV), due to their flexibility and extensive coverage, have gradually become essential for substation inspections. Wireless mesh networks (WMN) provide a scalable and resilient network environment for UAVs, where each node can serve as either an access point or a relay point, thereby enhancing the network’s fault tolerance and overall resilience. However, the UAV-WMN combined system is complex and dynamic, facing the challenge of dynamically adjusting node transmission power to minimize end-to-end (E2E) delay while ensuring channel utilization efficiency. Real-time topology changes, high-dimensional state spaces, and large solution spaces make it difficult for traditional algorithms to guarantee convergence and stability. Generic reinforcement learning (RL) methods also struggle with stable convergence. This paper introduces a new Lyapunov function-based proof to address these issues and provide a stable condition for dynamic control strategies. Then, we developed a specialized neural network power controller and combined it with the MATD3 algorithm, effectively enhancing the system’s convergence and E2E performance. Simulation experiments validate the effectiveness of this method and demonstrate its superior performance in complex scenarios compared to other algorithms.

With the continuous advancement of computer vision, image processing technologies, volumetric video, represented by point cloud videos, holds the potential for extensive applications in areas such as Virtual Reality (VR) and Augmented Reality (AR). Viewport prediction, also referred to as Field of View (FoV) prediction, is a crucial component in emerging VR and AR applications, playing a vital role in the transmission of point cloud videos. Currently, models for viewpoint prediction that integrate feature extraction and FoV information heavily rely on the spatial-temporal features extracted by convolutional neural networks. However, the drawback of 3D convolution lies in its inability to effectively capture long-term spatial-temporal dependencies within videos. Moreover, the temporal contrast layer used for time feature extraction only compares features within each block, leading to matching errors and inaccurate temporal feature extraction, consequently diminishing predictive performance. To address these limitations, we propose a Transformer-based Volumetric Point Cloud Video Viewport Prediction Network (VPFormer) that can efficiently extract spatial-temporal features from point cloud videos. VPFormer constitutes a viewport prediction framework that combines the spatial-temporal features of point cloud videos with user trajectory information. Specifically, we introduce a novel sampling method that effectively preserves spatial-temporal information while reducing computational complexity. Additionally, we incorporate context-aware dynamic positional encoding to capture inter-frame spatial-temporal context information. Subsequently, we introduce a voxel-based temporal contrast layer and partition the point cloud into smaller voxel blocks during feature matching, significantly reducing matching errors and enhancing the analysis and extraction of temporal features. Finally, by combining the spatial-temporal features of point cloud videos with user head trajectory information, we successfully predict future user viewpoints. Experimental results demonstrate that this approach outperforms other solutions in terms of performance.

Handwriting recognition systems have greatly enhanced AIoT applications, especially in human-computer interaction. Wireless-based methods, favored for their non-invasive nature and ease of deployment, are becoming more common. However, existing works, which typically depend on the user’s position, often perform poorly in varied writing positions. Additionally, they do not incorporate user identity information, which could lead to security vulnerabilities by failing to reject unauthorized users. To address these issues, this article introduces RF-Eye , a system that enables contactless, position-independent handwriting recognition and user identification without prior training. Its innovative approach uses each Radio-frequency identification (RFID) tag as a unique viewpoint for observing hand movements and employs pairs of tags to track directional changes. Specifically, building upon the signal transmission model and the Fresnel Zone, we propose a novel feature, DCG , to capture changes in gesture direction and confirm its consistency across different positions. Based on DCG , we develop unique patterns for common handwriting symbols that enhance our recognition algorithm. Moreover, to strengthen the system security, we link these patterns with distinct handwriting styles through the extraction of finer-grained features, thus, preventing the misuse of the system by unauthorized users. Extensive experiments demonstrate RF-Eye ’s efficacy, which achieves recognition accuracies of 93.5%, 95.2%, and 95.8% for 26 lowercase letters, 10 digits, and 10 graphic symbols, respectively, and identifying unauthorized users with 98.6% accuracy.

Vital sign detection, based on Channel State Information (CSI) from commercial off-the-shelf (COTS) WiFi devices, has become a popular research area. Previous works in this field mainly focus on respiration, while heartbeat sensing has not been well studied yet, because its signal is very weak and overwhelmed by hardware noises and the respiration signal. Different from existing research that exploits directional antenna, the proposed WiCG ( Wi Fi C ardio G ram) system uses common antennas, and not only accurately senses heartbeat rate but also provides the heartbeat signal for further analysis in complex real-life home scenes. Specifically, we first propose an effective denoising solution for Wi-Fi CSI by exploiting its spatial structure, which exhibits strong correlation among the In-phase/Quadrature components. Leveraging this characteristic with Principal Component Analysis (PCA) achieves effective reduction of ambient noise in both the amplitude and phase of the CSI. Then, we introduce a heartbeat enhancement scheme that utilizes the periodicity of the heartbeat signal. By applying Singular Spectrum Analysis (SSA), the complex effects of residual noise and respiratory interference are effectively mitigated. Extensive experiments have proven that WiCG can effectively sense the heartbeat rate. In a real deployment environment, the average detection error can be reduced to 0.28 bpm, close to current commercial heartbeat sensors.

This paper reviews three main aspects of authentication protocols of Internet of Things (IoT): classifications and limitations, current trends, and opportunities. First, we explore the significance of IoT authentication protocols in ensuring secure communication and the protection of transmitted and received data, focusing on the classifications and associated limitations. Second, we discuss the latest developments and trends, such as using blockchain technology and machine learning to enhance authentication protocols. Third, we highlight the future opportunities, including the development of human-centric authentication designs and improved platform interoperability. At the end of this paper, we provided some insights gained for the new researcher, offering analyses of the trends and challenges in this field, giving recommendations for improving IoT authentication protocols, and emphasizing the need for further research and cooperation to develop advanced security solutions.

Previous research in active learning has primarily focused on selecting examples from closed-set data, which consists solely of unlabeled examples from the target classes. However, this approach overlooks the more prevalent scenario of open-set data in real-world applications. Open-set data encompasses examples from both target classes and non-target classes. To fill this gap, we propose a novel framework called JOSAL, which enhances the accuracy of the classifier by precisely selecting the target class examples from open-set data. The JOSAL framework introduces the concept of joint learning, where the Sampler and Classifier components perform sampling and classification tasks, respectively, by sharing example features extracted from a pre-trained Encoder. To maximize the classification accuracy of the Classifier, the framework adopts a novel joint learning strategy. This strategy initially prioritizes optimizing the Sampler and gradually shifts the optimization attention to the Classifier. The experimental results demonstrate that, compared to baselines, our approach exhibits stronger sampling precision and achieves higher classification accuracy. To the best of our knowledge, this is the first work to address the open-set active learning problem using the joint learning paradigm.

With the capability of intelligent control and communicating with surrounding vehicles and infrastructures, connected and automated vehicles (CAVs) can drive cooperatively and have more positive effects on traffic efficiency. Cooperative and real-time path planning for CAVs stands as a pivotal solution to mitigate traffic congestion and augment travel efficiency. However, most of the existing path planning schemes predominantly concentrate on minimizing the travel times of vehicles, sidelining the broader issue of alleviating traffic congestion in urban settings. Therefore, in this paper, we propose a novel collaborative vehicle path planning scheme, leveraging the intelligent control and the communicating ability of CAVs. The primary objective is to reduce traffic congestion within the overall transportation system and improve traffic efficiency. Specifically, we focus on a general urban scenario with various types of vehicles, including CAVs, connected vehicles (CVs), and traditional human-driven vehicles (TVs), To enhance traffic efficiency in such a scenario, we design a collaborative path planning scheme to discover the efficient paths for both CAVs as well as CVs. In this scheme, we treat each CAV as an agent and formulate the multiple CAVs' path-planning problem as a Markov game. To solve the above Markov game, we design a multi-agent convolutional attention reinforcement learning (MACA) framework to generate paths with minimal travel time for CAVs. More concretely, the proposed MACA framework incorporates a convolutional neural network (CNN) layer to capture spatial correlation behind traffic conditions. Additionally, a graph attention network (GAT) layer is employed to integrate the influence of neighboring agents during the path-planning process. To further reduce traffic congestion, we extend the MACA framework into a collaborative MACA (C-MACA) scheme in vehicular networks, where CAVs are empowered to periodically broadcast their path information to surrounding CVs, providing valuable insights for their path planning. Subsequently, to prevent new congestion caused by the aggregation of CVs, we design a heuristic algorithm for CVs to make informed path decisions. We build up a simulator based on a real-world city road map and conduct extensive experiments. The experimental results demonstrate that the proposed scheme can decrease CVs' travel time by up to 10.9 % and reduce the average queue length around junctions by up to 6.5 % over several state-of-the-art approaches, without sacrificing the travel efficiency of CAVs.

Finding query patterns in a graph is fundamental for graph data analytics. Existing works mostly focus on either finding a single query pattern or finding patterns in a static graph. However, many applications today need to match multiple query patterns against a dynamically changing graph, i.e., online multiple graph pattern matching (online multi-GPM). Online multi-GPM is challenging as it requires quick responses for timely business decision-making. This paper proposes Wings — a distributed system for online multi-GPM. The key to efficient multi-GPM is a query planner that optimizes query plans by maximizing computation sharing among multiple queries and minimizing intermediate matching results. In addition, we also design an efficient query executor for Wings with memory footprint control and runtime redundant processing elimination. Our experimental results verified that Wings' designs are efficient for online multi-GPM.

Electromagnetic radiation (EMR) safety has always been a critical reason for hindering the development of magneticenabled wireless power transfer technology. People focus on the actual received energy at charging devices while paying attention to their health. Thus, we study this significant problem in this paper, and propose a universal safety guaranteed power-delivered-to-load (PDL) maximization scheme (called SafeGuard). Technically, we first utilize the off-the-shelf electromagnetic simulator to perform the EMR distribution analysis to ensure the universality of the method. Then, we innovatively introduce the concept of multiple importance sampling for achieving efficient EMR safety constraint extraction. Finally, we treat the proposed optimization problem as an optimal boundary point search problem from the perspective of space geometry, and devise a brand-new grid-based multi-constraint parallel processing algorithm to efficiently solve it. We implement a system prototype for SafeGuard, and conduct extensive experiments to evaluate it. The results indicate that our SafeGuard can obviously improve the achieved PDL by up to 1.75× compared with the state-of-the-art baseline while guaranteeing EMR safety. Furthermore, SafeGuard can accelerate the solution process by 29.12× compared with the traditional numerical method to satisfy the fast optimization requirement of wireless charging systems.

Device authentication plays a crucial role in preventing illegal access and ensuring smooth usage of magnetic wireless charging. However, current authentication techniques suffer from security vulnerabilities and are incompatible with low-cost receiver devices, thus severely limiting their applications. In this paper, we propose FreAuth, a novel Frequency feature-based device Authentication technology for magnetic wireless power transfer systems. Technically, we begin by conducting circuit measurements at the transmitter side to subtly retrieve impedance information related to the receiver without the need for its corporation. Then, we employ a dual-frequency interleaved-based subtraction technique to remove the ideal receiver impedance and capture the fairly weak frequency features. Furthermore, we normalize the captured frequency features to account for environment variations. These steps allow us to generate and store a hardware fingerprint for the receiver based on its frequency features. During device authentication, we use a discrete Frechet distance-based algorithm for fingerprint matching. We devise and implement a prototype of FreAuth and conduct extensive experiments to evaluate the proposed scheme. The experimental results validate the reliability (95.74% authentication accuracy among 60+ devices) and robustness (anti-interference with device location variations) of our FreAuth.

The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations for particular tasks. However, building the feature extraction component for such systems requires extensive domain-specific expertise or data. The exceptionally rapid development of foundation models is likely to usher in newfound abilities in such intelligent sensing. We propose a new scheme for sensing model, which we refer to as semi-generalist sensing model (SGSM). SGSM is able to semiautomatically solve various tasks using relatively less task-specific labeled data compared to traditional systems. Built through the analysis of the common theoretical model, SGSM can depict different modalities, such as the acoustic and Wi-Fi signal. Experimental results on such two heterogeneous sensors illustrate that SGSM functions across a wide range of scenarios, thereby establishing its broad applicability. In some cases, SGSM even achieves better performance than sensor-specific specialized solutions. Wi-Fi evaluations indicate a 20% accuracy improvement when applying SGSM to an existing sensing model.

Depression is a prevalent mental health disorder that significantly impacts individuals' lives and well-being. Early detection and intervention are crucial for effective treatment and management of depression. Recently, there are many end-to-end deep learning methods leveraging the facial expression features for automatic depression detection. However, most current methods overlook the temporal dynamics of facial expressions. Although very recent 3DCNN methods remedy this gap, they introduce more computational cost due to the selection of CNN-based backbones and redundant facial features. To address the above limitations, by considering the timing correlation of facial expressions, we propose a novel framework called FacialPulse, which recognizes depression with high accuracy and speed. By harnessing the bidirectional nature and proficiently addressing long-term dependencies, the Facial Motion Modeling Module (FMMM) is designed in FacialPulse to fully capture temporal features. Since the proposed FMMM has parallel processing capabilities and has the gate mechanism to mitigate gradient vanishing, this module can also significantly boost the training speed. Besides, to effectively use facial landmarks to replace original images to decrease information redundancy, a Facial Landmark Calibration Module (FLCM) is designed to eliminate facial landmark errors to further improve recognition accuracy. Extensive experiments on the AVEC2014 dataset and MMDA dataset (a depression dataset) demonstrate the superiority of FacialPulse on recognition accuracy and speed, with the average MAE (Mean Absolute Error) decreased by 21% compared to baselines, and the recognition speed increased by 100% compared to state-of-the-art methods. Codes are released at https://github.com/volatileee/FacialPulse.

Hidden WiFi cameras pose significant privacy threats, necessitating effective localization methods. In this work, we introduce CamLoPA, a system designed for the detection and localization of WiFi cameras. CamLoPA achieves this in just 45 seconds of user walking. It begins by analyzing the causal relationship between WiFi traffic and user movement to identify the presence of a snooping camera. Upon detection, CamLoPA utilizes a novel azimuth location model based on WiFi signal propagation path analysis to localize the hidden camera. Comprehensive evaluations demonstrate that CamLoPA can accurately and swiftly detect and localize snooping WiFi cameras with minimal constraints.

Wireless power transfer (WPT) systems using magnetic resonant coupling (MRC) have made significant progress recently, leading to various optimization methods in scenarios involving multiple-input multiple-output (MIMO) to improve charging performance. Adjusting the coil orientation of the power transmitter (TX) is a simple but effective method due to the directional nature of magnetic field distribution, but existing approaches often require unnecessary coil rotations. In this study, we introduce a Location-Aware Orientation Adjustment algorithm, known as LAORA, to address these inefficiencies. LAORA focuses on solving the problems of charging devices (RX) localization and location-based optimization. We begin by introducing the concept of Equivalent Impedance Distribution Image (EIDI) and transform the RX localization problem into a combined matching process involving EIDI. In addition, we establish a dynamic simulation framework to predict charging performance using RX-related knowledge, enabling us to obtain optimal TX orientations through reinforcement learning without needing to rotate on mechanical devices physically. We then implement the prototype and conduct extensive experiments. The results show that, compared to other existing orientation adjustment methods, LAORA achieves an average improvement of 186 % while reducing the mechanical rotations by 83.3 %.

WiFi-based technology is appealing for indoor localization due to the widely deployed infrastructures. Recently, path separation solutions have been proposed to address the multipath effects and achieve decimeter-level localization accuracy in line-of-sight (LoS) scenarios. However, these solutions experience serious performance degradation in non-line-of-sight (NLoS) scenarios, and couldn't be used for mobile device tracking where continuous LoS/NLoS switching happens. In this paper, we propose SaTrack, a LoS/NLoS state-aware mobile device tracking system. SaTrack identifies LoS/NLoS states based on the diversity of the strongest estimated paths when using different reference antennas. With the observation of spatial aggregation and temporal continuity for the Tx-Rx direct path, SaTrack chooses the direct path through two-step clustering, i.e., clustering in the spatial domain to form candidates and clustering again in the temporal domain to select the winner. Extensive experiments are conducted to evaluate the effectiveness of SaTrack. In a typical indoor environment with abundant multipath, SaTrack achieves 0.64m and 1.27m for the median and 90th percentile tracking errors, outperforming the state-of-the-art (SOTA) solutions.

In wireless networks, meeting the performance requirements of all tasks solely with Internet of Things (IoT) devices is challenging due to their limited computational power and battery capacity. Given their flexibility and mobility, the application of unmanned aerial vehicles (UAVs) in the context of mobile edge computing (MEC) has garnered significant interest within the sector. However, UAVs also face constraints in terms of resources like storage and computational power. Therefore, it is vital to develop effective UAV assistance solutions to provide long-term demands of in-network services. The dynamic scheduling and computation offloading of UAVs is the subject of this paper. Specifically, we propose a deep deterministic policy gradient algorithm based on a greedy strategy (DDPGG) to jointly optimize dynamic scheduling, device association, and task allocation of UAVs, with the goal of minimizing the weighted sum of total system energy consumption and time delay. The problem is formulated as a nonlinear programming problem involving mixed integers. The simulation results demonstrate that the DDPGG algorithm we have proposed exhibits a higher level of performance in comparison to its competitors.

With billions of IoT devices producing vast data globally, privacy and efficiency challenges arise in AI applications. Federated learning (FL) has been widely adopted to train deep neural networks (DNNs) without privacy leakage. Existing centralized and decentralized FL architectures have limitations, including memory burden, huge bandwidth pressure and non-IID data issues. This paper introduces a novel hybrid FL framework, named FedCD, merging the benefits of both centralized and decentralized FL architectures. FedCD strategically distributes the model based on layer sizes and consensus distances (i.e., the deviation between the local models and the global average models), effectively relieving network bandwidth pressures and accelerating training speed even under the non-IID setting. This method significantly mitigates resource constraints and improves model accuracy, offering a promising solution to the challenges in distributed machine learning. Extensive experiment results show the high effectiveness of FedCD. The total completion time of FedCD is reduced by 16.3%-53% and the average accuracy improvement is 1.85% compared to the baselines.

Cellular vehicle-to-everything (C-V2X) can provide ubiquitous mobile computing and communication services for vehicles, acting as a key technology to realize future urban intelligent transportation systems (ITS). Due to the lack of long-term insight into complex and dynamic urban road states, the existing historical road information-based strategies for C-V2X applications are inadequate to satisfy their high-performance requirements. Fortunately, it is feasible to provide fine-grained future road states for C-V2X decision-making by predicting traffic states to address this issue. To this end, this article proposes a fine-grained joint traffic prediction method in the urban road network with high-spatial complexity (ROUTE). ROUTE uniquely forecasts both micro-level (individual vehicle states) and macro-level traffic, thus supporting the diverse requirements of C-V2X applications. ROUTE is comprised of three key parts, including a vehicle coordinate transformation model, a spatial interaction-based turning model, and a micro-traffic prediction model. First, the complex spatial topology of the urban regional road network is normalized in ROUTE using the coordinate transformation model. Second, the turning model calculates the next road that the vehicle chooses after leaving the current one. Third, a transformer and generative adversarial network-based model (FORMERGAN) predicts future micro-traffic states. Extensive experimental results demonstrate that ROUTE surpasses its competitors in accurately predicting fine-grained long-term micro-traffic and macro-traffic states.

In this paper, we investigate the optimal configuration and dependence-aware task assignment for multi-task edge video analytics. Multi-task video analytics involves multiple objects in video frames and multiple dependent tasks, resulting in existing video configuration and task assignment scheme for single-task unsuitable to this scenario. Our paper aims to efficiently assign dependent tasks to multiple collaborative edge nodes with appropriate video configuration, to achieve low latency while maintain accuracy. Firstly, we conduct extensive experiments on real-world video datasets. The results reveal that the impact of resolution on the detection accuracy varies among different sizes of objects. Moreover, the computing and communication load of dependent tasks varies along the time due to the dynamic video content. Based on the experimental results, we propose a threshold-based downsampling strategy for large objects, aiming at minimizing the transmission latency while guaranteeing task analytic accuracy. In addition, the number of objects and workload of subsequent tasks turn out to be highly correlated, the computation and transmission demands of tasks can be thus estimated for each video chunk. Then, a heuristic dependence-aware task assignment algorithm is proposed to achieve minimum completion time of dependent tasks. Experimental results demonstrate that the proposed scheme can effectively reduce the execution time of multiple tasks while guaranteeing the analytic accuracy, outperforming the state-of-the-art benchmarks.

The integrated satellite-terrestrial network (ISTN) system has experienced significant growth, offering seamless communication services in remote areas with limited terrestrial infrastructure. However, designing a routing scheme for ISTN is exceedingly difficult, primarily due to the heightened complexity resulting from the inclusion of additional ground stations, along with the requirement to satisfy various constraints related to satellite service quality. To address these challenges, we study packet routing with ground stations and satellites working jointly to transmit packets, while prioritizing fast communication and meeting energy efficiency and packet loss requirements. Specifically, we formulate the problem of packet routing with constraints as a max-min problem using the Lagrange method. Then we propose a novel constrained Multi-Agent reinforcement learning (MARL) dynamic routing algorithm named CMADR, which efficiently balances objective improvement and constraint satisfaction during the updating of policy and Lagrange multipliers. Finally, we conduct extensive experiments and an ablation study using the OneWeb and Telesat mega-constellations. Results demonstrate that CMADR reduces the packet delay by a minimum of 21% and 15%, while meeting stringent energy consumption and packet loss rate constraints, outperforming several baseline algorithms.

Lung cancer is the leading cause of cancer death worldwide. The best solution for lung cancer is to diagnose the pulmonary nodules in the early stage, which is usually accomplished with the aid of thoracic computed tomography (CT). As deep learning thrives, convolutional neural networks (CNNs) have been introduced into pulmonary nodule detection to help doctors in this labor-intensive task and demonstrated to be very effective. However, the current pulmonary nodule detection methods are usually domain-specific, and cannot satisfy the requirement of working in diverse real-world scenarios. To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks. This attention module works in the axial, coronal, and sagittal directions. In each direction, we divide the input feature into groups, and for each group, we utilize a universal adapter bank to capture the feature subspaces of the domains spanned by all pulmonary nodule datasets. Then the bank outputs are combined from the perspective of domain to modulate the input group. Extensive experiments demonstrate that SGDA enables substantially better multi-domain pulmonary nodule detection performance compared with the state-of-the-art multi-domain learning methods.

With mobile phones becoming increasingly prevalent and embedding high-quality microphones, attackers have the ability to employ these microphones to eavesdrop user’s keyboard input. However, existing work usually assumes that keystroke eavesdropping is performed against known environments and victims, which inevitably makes attack systems lack generalization. To reveal the real threat of the acoustic signal-based attack strategy, this paper proposes a keystroke eavesdropping algorithm called KeystrokeSniffer, which is robust to unknown input environments and unknown victims. In particular, to mimic the real input environment of victims, an environment estimation algorithm is first designed by extracting the timbre-related characteristics to predict the keyboard type and identifying large-size key data from collected unlabeled samples to estimate the 3D microphone coordinates. Then, by imitating unknown environments and victim data, this algorithm achieves effective keystroke eavesdropping with a small training set. By further considering the commonalities of different keystroke habits, a robust feature extraction method that reflects the keystroke location is adopted to reduce the impact of individual input habits. Extensive experimental results using various commodity smartphones indicate that the scheme is capable of predicting keyboard input accurately under different unknown scenarios. Specifically, even when both the victims and keyboards are unknown, KeystrokeSniffer can still achieve high Top-5 accuracy, reaching 79.5% in predicting keystrokes and 96.7% in predicting meaningful words, which demonstrates KeystrokeSniffer has excellent generalization capabilities. By setting different parameter values of various impact factors, e.g., noise and hand length factors, the strong robustness of the system is demonstrated, which proves that KeystrokeSniffer can violate privacy in real situations.

Background subtraction forms the basis of many safety applications in airport traffic management, such as the visual conflict warning system. However, deep learning methods often mistakenly identify stationary aircraft as foreground, mainly because they prioritize learning appearance over motion features. This means that stationary aircraft with a similar appearance to moving ones are often incorrectly classified as foreground. To address this issue, a Motion-enhanced Background Subtraction Network (MBSNet) is proposed in this paper. MBSNet is designed to focus more on motion information within an encoder-decoder framework. Firstly, a Motion Augmentation Encoder Module (MAEM) is introduced, which generates a clean background frame without foreground from previous frames. This module compares the background frame with the current frame containing moving objects, indirectly enhancing the motion component in the encoded features. Because targets on the airport ground are relatively sparse, MAEM ensures a clean background image. Secondly, a Motion Accumulation Decoder Module (MADM) is designed, which accumulates motion-augmented features from the current frame and past frames based on feature dissimilarity measurement. Since aircraft exhibit consistent motion patterns, such as continuous straight travel with occasional turns, MADM further enhances the motion component in the accumulated feature vector. Finally, MBSNet is evaluated on the AGVS dataset, and our experiments demonstrate the effectiveness of the proposed method for airport background subtraction.

WiFi connection has been suffering from MAC forgery attacks due to the loose authentication mechanism between access points (APs) and clients. To address this problem, the physical (PHY) layer information-based fingerprint has been adopted for safe WiFi authentication. Since such a fingerprint is constant and unique for each specific network interface card (NIC), it can effectively prevent MAC forgery attacks. However, the PHY layer information-based fingerprint is still vulnerable to malicious attacks as it is extracted from Channel State Information (CSI), and its stability can be affected by the wireless environment. In this paper, we propose a novel undetectable attack framework, called PhyFinAtt, base on which the attacker can undermine the stability of the PHY layer-based authentication fingerprints through human movement and further attack the WiFi authentication protocols. Specifically, we first demonstrate that human movement at a designated location can affect the PHY fingerprint. We then illustrate the impact of human movement on the PHY fingerprint and the relationship between the movement and the channel quality to ensure that the PHY fingerprint is destroyed by the movement in an undetected way without affecting normal communication. Extensive experiments in real-world scenarios show that our proposed attack can effectively disrupt the stability of the PHY fingerprints and significantly degrade the performance of the authentication protocols based on such fingerprints. To the best of our knowledge, this is the first study on effective attacks against the PHY information-based WiFi authentication protocols. Furthermore, we also present a practical defense mechanism without involving any additional equipment to mitigate attacks similar to PhyFinAtt.

Vehicular crowd sensing (VCS), emerging as a new paradigm within mobile crowd sensing, leverages vehicles as the participator, which can obtain broader sensing coverage and higher sensing flexibility. Previous works ignored the strong impact of environmental factors on workers' travel costs, as well as improper gains from speculative behavior (i.e. workers detour or delay to get more compensation), resulting in unfair income of workers. Moreover, these works focused solely on sensing tasks within specific domains, lacking generalization ability. Therefore, our work is dedicated to providing a fair and universal VCS platform, which is called Environment-cost-based Heterogeneous Task Allocation (EHTA) framework. Our work differs from previous works in the following aspects: 1) We introduce the Environment Cost (EC) based on the investigation of traffic conditions to accurately quantify workers' efforts, and propose a straightforward yet efficacious detection methods to identify speculative behavior of malicious workers, both of which could guarantee the fairness in workers' income. 2) We design a spatial-temporal fair incentive mechanism based on monetary reward to ensure the fair execution of tasks in both space and time dimensions. 3) We summarize the characteristics of three kinds of sensing tasks and propose a universal task allocation algorithm to assign multiple types of tasks simultaneously. The effectiveness of our framework was validated by simulations, which are conducted on a data set comprising 13,000 taxi trajectories from Shanghai in April 2015. We compared our framework against four baseline algorithms, and the results shows that EHTA framework outperforms in terms of task expenditure, task utility and fairness.

Intelligent Transportation Systems (ITS) aim to enhance traffic management by improving connectivity and data sharing among vehicles and road infrastructure. In a Mixed Connected and Connectionless Vehicles (MCCV) scenario consisting of connected vehicles equipped with On-Board Units (OBUs) and non-connected vehicles lacking OBUs, communication disparities create challenges in critical lane-changing overtaking decisions. These discrepancies hinder the adaptation of fully connected scenarios to dynamic interactions among these different types of vehicles. Considering the diversity in decision-making ways and capabilities of non-connected vehicles in MCCV scenarios, ensuring the coordinated execution of safe and efficient lane-changing overtaking maneuvers by multiple connected vehicles is crucial for enhancing traffic efficiency. Therefore, we propose a collaborative strategy to facilitate safer and more efficient lane-changing overtaking maneuvers for connected vehicles in the MCCV scenario. First, we design a multi-criteria priority detection, and a dynamic event-triggered mechanism based on confidence intervals to foster efficient collaboration among connected vehicles, optimizing decision-making and reducing conflicts. Second, to accommodate diverse driving styles of autonomous and human-driven vehicles, we introduce an Improved Dynamic Precise Fuzzy C-Means (IDP-FCM) algorithm to dynamically identify and adapt to different driving styles, thereby improving safety. Finally, tackling the challenge of multiple connected vehicles performing lane-changing overtaking involving hybrid action space, our proposed Multi-agent Contrastive Parameterized Dueling Deep Q-Network (MCPDDQN) algorithm incorporates contrastive learning to improve strategy stability in complex driving scenarios. Experimental results demonstrate the effectiveness of our strategy in improving road safety and traffic efficiency of the MCCV scenario.

Federated learning (FL) has gained increasing attention due to its ability to collaboratively train while protecting client data privacy. However, vanilla FL cannot adapt to client heterogeneity, leading to a degradation in training efficiency due to stragglers, and is still vulnerable to privacy leakage. To address these issues, this paper proposes RingSFL, a novel distributed learning scheme that integrates FL with a model split mechanism to adapt to client heterogeneity while maintaining data privacy. In RingSFL, all clients form a ring topology. For each client, instead of training the model locally, the model is split and trained among all clients along the ring through a pre-defined direction. By properly setting the propagation lengths of heterogeneous clients, the straggler effect is mitigated, and the training efficiency of the system is significantly enhanced. Additionally, since the local models are blended, it is less likely for an eavesdropper to obtain the complete model and recover the raw data, thus improving data privacy. The experimental results on both simulation and prototype systems show that RingSFL can achieve better convergence performance than benchmark methods on independently identically distributed (IID) and non-IID datasets, while effectively preventing eavesdroppers from recovering training data.

The incorporation of Unmanned Aerial Vehicles (UAVs) into cellular networks opens up new possibilities to enhance their ubiquitous operations and establish superior performance owing to the high probability of line-of-sight (LoS) for air-to-ground channels. However, this also results in the UAV inducing more significant uplink interference to non-associated Base Stations (BSs). This paper explores the online design policy in cellular-connected multiple UAV communications in the absence of channel conditions, focusing on wireless resource allocation and dynamic three-dimensional (3-D) path planning. Our objective is to maximize the minimum uplink throughput for all UAVs while considering the energy constraints of the UAVs. First, we implement an online design utilizing the achievable rate based on the estimated instantaneous channel state information (CSI) for the current time slot, and the expected data rate for future time slots based on channel distribution information (CDI). Our solution employs the exact penalty method along with alternating optimization and successive convex optimization methods. Second, we formulate an online design by merely using the achievable rate based on the estimated instantaneous CSI for the current time slot. We introduce an energy-triggered penalty term to regulate the energy consumption of the UAVs, resulting in a low-complexity solution even if the CDI is unavailable before the flight. Lastly, we conduct extensive simulations to corroborate our findings and provide comprehensive comparisons with other baseline schemes to underline the effectiveness of the proposed designs.

Unmanned aerial vehicles (UAVs) have a significant potential for sensing applications in further cellular networks due to their extensive coverage and flexible deployment. In this paper, we consider a multi-cell cellular network with a cellular-connected UAV, which senses data with onboard sensors and uploads sensory data to the ground base stations (BSs). To evaluate the freshness of sensory data, we employ the concept of age of information (AoI), which is defined as the time elapsed since the latest successful transmission of sensory data. A lower AoI implies fresher sensory data, which may lead to the increase of UAV operation time. To balance such tradeoff, we aim to minimize the weighted sum of operation time and total AoI for the UAV by jointly optimizing transmission scheduling, BS association, as well as UAV trajectory. The problem is formulated as a mixed-integer nonlinear programming (MINLP) problem, which is difficult to solve due to the time-varying propagation channels. To this end, we first characterize the average communication performance with statistic channel information, and then develop a search algorithm to obtain the optimal solution via employing the optimal structure as well as convex optimization techniques, while a low-complexity Double Graph based Algorithm (DGA) is developed to obtain a suboptimal solution. Then, by taking into account the site-specific performance and making fast decisions online, we propose a Deep reinforcement Learning Algorithm (DLA). Compared to DGA, DLA can adapt to the specific local environment and obtain a solution more rapidly once the training process is completed. Simulation results show that the proposed algorithms outperform the benchmarks about 30%, and achieve flexible tradeoff between operation time and AoI of UAV sensing, which is not available by considering just one objective.

The integration of Roadside Units (RSUs) is vital for the development of autonomous driving technologies. Challenges arise from sinking computing capabilities into RSUs and vehicles in the paradigm of Vehicle Edge Computing (VEC), particularly due to heterogeneous computation and communication capacities of network nodes and multiple sources of computing tasks (node-mounted and offloading tasks). These challenges complicate network stability from the perspective of a long-term optimization evolving over time, considering unpredictable task distribution and environmental states. To tackle these challenges, we approach the problem of partial task offloading to minimize task delay while meeting the demand of system stability over time as a dynamic long-term optimization. Utilizing Lyapunov stochastic optimization tools, we successfully decouple the long-term delay minimization and stability constraint, transforming it into a per-slot scheduling problem. Since the per-slot scheduling problem with complicated Lyapunov drift functions can not be solved by numerical optimization at each time step, our solution leverages a proposed deep reinforcement learning algorithm, leading to extensive simulations that demonstrate the superior effectiveness and efficiency of our proposal compared to existing schemes.

Mobile radio frequency identification (RFID) systems typically experience the continual movement of many tags rapidly going in and out of the interrogating range of readers. Readers that are deployed to maintain a current, real-time list of tags, which are present in the interrogating zone at any moment, must repeatedly execute a series of reading cycles. Each of these reading cycles provides the readers very limited time to identify unknown tags (those newly entering into the reader’s range), and, at the same time, to detect missing tags (those just leaving the reader’s range). In this paper, we study the continuous tag recognition problem, which is critical for mobile RFID systems. First, we obtain a lower bound on communication time for solving this problem. We then design a near-OPTimal protocoL, called OPT-L, and prove that its communication time is approximately equal to the lower bound. Finally, we present extensive simulation and experimental results that demonstrate OPT-L’s superior performance over other existing protocols.

Breakthroughs in Wireless Energy Transfer technologies have revitalized Wireless Rechargeable Sensor Networks. However, how to schedule mobile chargers rationally has been quite a tricky problem. Most of the current work does not consider the variability of scenarios and how many mobile chargers should be scheduled as the most appropriate for each dispatch. At the same time, the focus of most work on the mobile charger scheduling problem has always been on reducing the number of dead nodes, and the most critical metric of network performance, packet arrival rate, is relatively neglected. In this article, we develop a DRL-based Partial Charging algorithm. Based on the number and urgency of charging requests, we classify charging requests into four scenarios. And for each scenario, we design a corresponding request allocation algorithm. Then, a Deep Reinforcement Learning algorithm is employed to train a decision model using environmental information to select which request allocation algorithm is optimal for the current scenario. After the allocation of charging requests is confirmed, to improve the Quality of Service, i.e., the packet arrival rate of the entire network, a partial charging scheduling algorithm is designed to maximize the total charging duration of nodes in the ideal state while ensuring that all charging requests are completed. In addition, we analyze the traffic information of the nodes and use the Analytic Hierarchy Process to determine the importance of the nodes to compensate for the inaccurate estimation of the node’s remaining lifetime in realistic scenarios. Simulation results show that our proposed algorithm outperforms the existing algorithms regarding the number of alive nodes and packet arrival rate.

In Mesh Wireless Networks (MWNs), the network coverage is extended by connecting Access Points (APs) in a mesh topology, where transmitting frames by multi-hop routing has to sustain the performances, such as end-to-end (E2E) delay and channel efficiency. Several recent studies have focused on minimizing E2E delay, but these methods are unable to adapt to the dynamic nature of MWNs. Meanwhile, reinforcement-learning-based methods offer better adaptability to dynamics but suffer from the problem of high-dimensional action spaces, leading to slower convergence. In this paper, we propose a multi-agent actor-critic reinforcement learning (MACRL) algorithm to optimize multiple objectives, specifically the minimization of E2E delay and the enhancement of channel efficiency. First, to reduce the action space and speed up the convergence in the dynamical optimization process, a centralized-critic-distributed-actor scheme is proposed. Then, a multi-objective reward balancing method is designed to dynamically balance the MWNs’ performances between the E2E delay and the channel efficiency. Finally, the trained MACRL algorithm is deployed in the QaulNet simulator to verify its effectiveness.

Aerial video streaming is a promising application of unmanned aerial vehicles (UAVs), which extends video service from ground to three-dimensional (3D) airspaces. However, high data rates and smooth transmission are required along with ubiquitous and environment-aware communications. To this end, we study the quality of experience (QoE) maximization problem in this paper for aerial video streaming over 3D cellular networks in urban environments with building avoidance. Different from the typical channel model based optimization in prior works, we tackle the joint design of 3D UAV trajectory and transmission scheduling as well as playback rate adaption with an environment and channel knowledge map (ECKM) approach, which provides rich information about the location-specific channel for enabling environment-aware communications. Specifically, we first consider the scenario with perfect ECKM, and propose efficient algorithms to obtain suboptimal solutions by utilizing two graph models and the iterative parameter-enabled block coordinate descent method. For the scenario without such map information, we propose a dueling Deep Q-learning (DQL) solution with map construction such that the learning process can be facilitated for path planning. Simulation results are provided to demonstrate the improvement in QoE by the proposed solutions over baseline schemes, as well as a tradeoff between video quality and rate variation.

Cross-silo federated learning (CFL) is a distributed learning paradigm that allows organizations (e.g., financial or medical entities) to train a global model on siloed data. Recent studies on mechanisms designed for CFL, however, rarely jointly consider the potential inter-organizational competition and the lack of credibility between organizations, which may discourage organizational participation. In this paper, we investigate the problem of inter-organizational competition and credibility assurance. We propose a distributed trading mechanism, called$TradeFL$, to incentivize organizations to contribute data and computational resources through mutual trading among organizations. Technically, TradeFL characterizes the competition among organizations and compensates for their damage incurred by competition. TradeFL runs on distributed organizations and provides credibility guarantees for compensation through a customized smart contract11Illustration of the prototype: https://github.com/user10963.. We prove that the interaction among organizations that contribute resources to maximize personal payoffs is a weighted potential game. Then, we propose a centralized algorithm and a distributed algorithm to determine the optimal resource contribution. Simulation results and evaluations based on real-world datasets demonstrate that our scheme achieves higher social welfare, increases the amount of contributed data by up to 64%, and improves the accuracy of the global model by at most 23.2%.

In recent years, receiver (RX) feedback communication has attracted increasing attention to enhance the charging performance for magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems. People prefer to adopt the in-band implementation with minimal overhead costs. However, the influence of RX-RX coupling couldn’t be directly ignored like that in the RFID field, i.e., strong couplings and relay phenomenon. In order to solve these two critical issues, we propose a Robust layer-level in-band parallel communication protocol for MIMO MRC-WPT systems (called Roland). Technically, we first utilize the observed channel decomposability to construct group-level channel relationship graph for eliminating the interference caused by strong RX-RX couplings. Then, we generalize such method to deal with the RX dependency due to relay phenomenon. Finally, we conduct extensive experiments on a prototype testbed to evaluate the effectiveness of the proposed scheme. The results demonstrate that our Roland could provide ≥95% average decoding accuracy for concurrent feedback communication of 14 devices. Compared with the state-of-the-art solution, the proposed protocol Roland can achieve an average decoding accuracy improvement of 20.41%.

Efficient point cloud video streaming requires accurate viewport prediction, and research on this topic is still in its infancy. This paper demonstrates a high-precision scheme for viewport prediction in the point cloud video, named Landscape, exploring both video saliency information and viewport trajectory. Specifically, we first propose a novel point cloud video sampling method, which reduces computational load while preserving video features. Furthermore, we introduce a new saliency detection technique that integrates temporal and spatial information to detect dynamic, static geometric, and color salient regions. Finally, we intelligently fuse saliency and trajectory information to achieve more accurate viewport prediction. We verify the performance of our proposed viewport prediction methods over state-of-the-art wireless networks.

As a popular way of representing holographic video or volumetric video, point cloud video can provide users with a highly immersive viewing experience of 6 degrees of freedom (6DoF) and is expected to become the mainstream video format of the future. However, the real-time transmission of point cloud video faces many challenges due to the huge amount of data and the large search space of the optimization problem with constraints. To this end, we propose Horizon, a novel Dynamic Adaptive Streaming over HTTP (DASH) based real-time point cloud video streaming system, which aims to maximize the user's viewing experience by predicting the next several steps through a rolling framework and uses a Deep Reinforcement Learning (DRL) based algorithm to achieve a real-time solution to the rolling optimization problem. We have prototyped this system and demonstrated its performance on a state-of-the-art wireless network.

Emotion plays a critical role in making the computer more human-like. As the first and most essential step, emotion recognition emerges recently as a hot but relatively nascent topic, i.e., current research mainly focuses on single modality (e.g., facial expression) while human emotion expressions are multi-modal in nature. To this end, we propose an unobtrusive emotion recognition system leveraging two emotion-rich and tightly-coupled modalities, i.e., gesture and facial expression. The system design faces two major challenges, namely, how to capture the emotional expression in both modalities without disturbing the subject and how to leverage the relationship between modalities for recognizing the emotion. For the former, we explore WiFi and vision for unobtrusive and contactless gesture and facial expression sensing, respectively. For the latter, we propose a novel deep learning framework named Multi-Source Learning (MSL) to efficiently exploit both self-correlation in the modality and cross-correlation between modalities for fine-grained emotion recognition. To evaluate the proposed method, we prototype the system on low-cost commodity WiFi and vision devices, build a first-of-its-kind WiFi-Vision emotion dataset, and conduct extensive experiments. Empirical results not only verify the effectiveness of WiFE in emotion recognition, but also confirm the superiority of multi-modality over single-modality.

Situational awareness tries to grasp the important events and circumstances in the physical world through sensing, communication, and reasoning. Tracking the evolution of changing situations is an essential part of this awareness and is crucial for providing appropriate resources and help during disasters. Social media, particularly Twitter, is playing an increasing role in this process in recent years. However, extracting intelligence from the available data involves several challenges, including (a) filtering out large amounts of irrelevant data, (b) fusion of heterogeneous data generated by the social media and other sources, and (c) working with partially geo-tagged social media data in order to deduce the needs of the affected people. Spatio-temporal analysis of the data plays a key role in understanding the situation, but is available only sparsely because only a small fraction of people post relevant text and of those very few enable location tracking. In this paper, we provide a comprehensive survey on data analytics to assess situational awareness from social media big data.

Volumetric video provides users with a good viewing experience of six degrees of freedom (DoF) and has wide applications in many fields such as teleconferencing and online games. However, the huge data volume and strict latency requirements of point cloud video, the most popular representative of volumetric video, pose a challenge to its transmission. Existing point cloud video transmission algorithms usually segment a long video by every one or several group of frames, predict network bandwidth and field of view (FoV) information, then perform adaptive transmission by solving the quality of experience (QoE) optimization problem. However, such segmentation neglects the impact of current optimization decisions on the subsequent video streaming process, as well as the accumulated prediction error across a long interval, severely degrading user’s QoE. Moreover, the complex constrained optimization problem makes the solution time too long to meet the real-time video streaming requirements. To this end, in this paper, we propose a rolling prediction-optimization-transmission (POT) framework, which makes predictions of network bandwidth and FoV in each short rolling window to reduce prediction error. And our framework takes into account the upper bounded QoE contribution of the subsequent point cloud video to improve the system performance. In addition, we design a deep reinforcement learning based real-time solver to make decisions for the fixed structure optimization problem in each roll, allowing our system to run in real-time. We have performed simulations and experiments, and the results show that our solution outperforms existing methods.

In this paper, we propose a servers-aided password-based subsequent-key-locked encryption mechanism to ensure the confidentiality of outsourced electronic health records (EHRs). The encryption mechanism achieves conditional forward transparency: a doctor can only access a patient's EHRs related to the current diagnosis with the patient's delegation. It also achieves portability: to delegate a doctor for accessing a specific part of EHRs, the patient only needs to send one key (at most 256 bits) in addition to the delegation information to the doctor; the patient does not need to maintain any secret in a local device. Then, we propose a blockchain-based secure EHR provenance mechanism, where a data structure of EHR provenance record is designed to precisely reflect the EHRs’ provenance information; a smart contract on a public blockchain is deployed to secure both EHRs and the corresponding provenance records. Finally, we develop a cloud-based eHealth system, dubbed HealthFort, based on the two mechanisms. Security analysis and comprehensive performance evaluation are conducted to demonstrate that HealthFort is secure and efficient.

Volumetric video enables a six-degree-of-freedom (6DoF) immersive viewing experience and has a wide range of applications in entertainment and education, among others. Most existing approaches to volumetric video streaming are extensions of VR video streaming solutions that do not take into account user behavior and the properties of the video during the tiling process, and the complexity of decoding is high. To this end, we study volumetric video streaming in this paper and address the research questions mentioned above. In particular, we first propose a hybrid visual saliency and hierarchical clustering empowered 3D tiling scheme that better matches the user’s field of view (FoV). Then, we build a quality of experience (QoE) model considering the volumetric video features as the optimization objective. In addition to the usual encoded version, we introduce the reconstructed version (i.e., decoded version, which allows the user to skip the decoding process and thus reduces the decoding overhead) and propose a joint computational and communication resource allocation scheme to achieve a trade-off between communication and computational resources to maximize the QoE. We perform exhaustive simulations and build a prototype system to verify the performance of the proposed tiling and transmission scheme. The results show that the proposed tiling and transmission scheme performs significantly better than the comparison schemes.

Field of view (FoV) prediction is critical in 360-degree video multicast, which is a key component of the emerging virtual reality and augmented reality applications. Most of the current prediction methods combining saliency detection and FoV information neither take into account that the distortion of projected 360-degree videos can invalidate the weight sharing of traditional convolutional networks nor do they adequately consider the difficulty of obtaining complete multi-user FoV information, which degrades the prediction performance. This article proposes a spherical convolution-empowered FoV prediction method, which is a multi-source prediction framework combining salient features extracted from 360-degree video with limited FoV feedback information. A spherical convolutional neural network is used instead of a traditional two-dimensional convolutional neural network to eliminate the problem of weight sharing failure caused by video projection distortion. Specifically, salient spatial-temporal features are extracted through a spherical convolution-based saliency detection model, after which the limited feedback FoV information is represented as a time-series model based on a spherical convolution-empowered gated recurrent unit network. Finally, the extracted salient video features are combined to predict future user FoVs. The experimental results show that the performance of the proposed method is better than other prediction methods.

In recent years, the fast development of mobile communications and cloud systems has substantially promoted edge computing. By pushing server resources to the edge, mobile service providers can deliver their content and services with enhanced performance, and mobile-network carriers can alleviate congestion in the core networks. Although edge computing has been attracting much interest, most current research is application-specific, and analysis is lacking from a business perspective of edge cloud providers (ECPs) that provide general-purpose edge cloud services to mobile service providers and users. In this article, we present a vision of general-purpose edge computing realized by multiple interconnected edge clouds, analyzing the business model from the viewpoint of ECPs and identifying the main issues to address to maximize benefits for ECPs. Specifically, we formalize the long-term revenue of ECPs as a function of server-resource allocation and public data-placement decisions subject to the amount of physical resources and inter-cloud data-transportation cost constraints. To optimize the long-term objective, we propose an online framework that integrates the drift-plus-penalty and primal-dual methods. With theoretical analysis and simulations, we show that the proposed method approximates the optimal solution in a challenging environment without having future knowledge of the system.

In point cloud video streaming systems, the field of view (FoV) prediction is critical for selecting the tiles, the objective of which is to optimize the expected long-term quality-of-experience (QoE) from the perspective of a user. On one hand, a satisfactory QoE accounts for not only the playback quality but also the playback smoothness. On the other hand, the large data volume of a selected tile requires the transmission to be adaptive to the system uncertainties. This paper applies a Markov decision process to formulate the problem of tile selection across the infinite discrete time horizon. In particular, a system state includes the FoV information, which is predicted from the Transformer. To alleviate the dependence on system uncertainty statistics, a deep reinforcement learning approach is derived for solving the optimal control policy. Under different settings, we conduct experiments based on the real throughput and head-mounted display data. The results show that compared to the existing baselines, our proposed prediction-control approach achieves a higher FoV prediction accuracy, better playback quality as well as smoothness, and hence a better average QoE for the user.

Running intelligent applications on a satellite is in urgent need, which can help to extract useful information from massive surveillance or remote sensing data and return it to ground in time. However, the limited computing ability on a satellite prohibits it from completing the whole application by itself quickly. Within the circumstance of space-air-ground integrated network (SAGIN), we propose to offload part of the computation task from the satellite to the ground station with strong computing ability, through the introduction of airship, which can assist the satellite not only by relaying but also in computing. To save the energy consumption of the satellite and airship, task offloading policy and resource allocation, are investigated for a special task model supporting deep neural network (DNN), which is popular in intelligent application. An optimization problem is formulated, which is difficult to solve. We achieve the global optimal solution through the following operations: 1) Transform the formulated problem into two levels, with every level dealing with discrete or continuous variables exclusively; 2) Explore implicit monotonicity and convexity of concerned functions so as to solve the non-convex lower level problem optimally only with several rounds of bisection or Golden search methods; 3) Solve the upper level problem optimally by enumeration but with polynomial complexity. Numerical results verify the effectiveness of our proposed method.

Feature extraction is important for non-intrusive appliance load monitoring (NILM), because it includes crucial steps which altogether transform raw signals into distinct features of appliances. Although numerous studies have achieved good results using transient harmonic features, their performances degrade in practical scenarios. In this paper, a time-frequency analysis-based framework for transient harmonic feature extraction is proposed, which takes all factors that would eventually influence NILM system into account. More specffically, the framework proposes a new qualitative transient harmonic feature, along with current retrieval and data augmentation methods. The proposed framework is evaluated on two well-known datasets (i.e., Controlled On/Off Loads Library and Home Equipment Laboratory Dataset). As compared with the other state-of-art methods, the proposed framework achieves similar accuracy (i.e., more than 96%) on single-load data, and more than 33% accuracy improvement over multi-load data (e.g., from 59.4% to 93% when six devices are active at the same time).

WiFi-based gait recognition is an attractive method for device-free user identification, but path-sensitive Channel State Information (CSI) hinders its application in multi-path environments, which exacerbates sampling and deployment costs (i.e., large number of samples and multiple specially placed devices). On the other hand, although video-based ideal CSI generation is promising for dramatically reducing samples, the missing environment-related information in the ideal CSI makes it unsuitable for general indoor scenarios with multiple walking paths.In this paper, we propose WiVi, a WiFi-video cross-modal fusion based multi-path gait recognition system which needs fewer samples and fewer devices simultaneously. When the subject walks naturally in the room, we determine whether he/she is walking on the predefined judgment paths with a K-Nearest Neighbors (KNN) classifier working on the WiFi-based human localization results. For each judgment path, we generate the ideal CSI through video-based simulation to decrease the number of needed samples, and adopt two separated neural networks (NNs) to fulfill environment-aware comparison among the ideal and measured CSIs. The first network is supervised by measured CSI samples, and learns to obtain the semi-ideal CSI features which contain the room-specific ‘accent’, i.e., the long-term environment influence normally caused by room layout. The second network is trained for similarity evaluation between the semi-ideal and measured features, with the existence of short-term environment influence such as channel variation or noises.We implement the prototype system and conduct extensive experiments to evaluate the performance. Experimental results show that WiVi’s recognition accuracy ranges from 85.4% for a 6-person group to 98.0% for a 3-person group. As compared with single-path gait recognition systems, we achieve average 113.8% performance improvement. As compared with the other multi-path gait recognition systems, we achieve similar or even better performance with needed samples being reduced by 57.1-93.7%

Internet of Things enables devices to communicate, collect and exchange data with the network. As the number of IoT devices keeps growing, the volume of data they produce is also increasing exponentially. Given the feature of limited computing and storage resources of IoT, it is inevitable to store data in the cloud for better services. However, for users to effectively and efficiently inspect those data over the cloud is a critical and open problem. Most public integrity auditing over the cloud schemes requires the user to do a sheer amount of preprocessing work on the local devices, which is unsuitable for IoT devices. With the development of edge computing extending cloud computing, it can provide computing capability for resource-constrained devices in close geographic proximity. In this paper, we design an auditing scheme based on secure computation outsourcing assisted by edge computing, in which the data preprocessing work can be offloaded to the edge server. The experiments show that it reduces the computing load on the devices and improves the efficiency of task processing.

This paper investigates an air-ground integrated multi-access edge computing system, which is deployed by an infrastructure provider (InP). Under a business agreement with the InP, a third-party service provider provides computing services to the subscribed mobile users (MUs). MUs compete for the shared spectrum and computing resources over time to achieve their distinctive goals. From the perspective of an MU, we deliberately define the age of update to capture the staleness of information from refreshing computation outcomes. Given the system dynamics, we model the interactions among MUs as a stochastic game. In the Nash equilibrium without cooperation, each MU behaves in accordance with the local system states and conjectures. We can hence transform the stochastic game into a single-agent Markov decision process. As another major contribution, we develop an online deep reinforcement learning (RL) scheme that adopts two separate double deep Q-networks to approximate the Q-factor and the post-decision Q-factor, respectively. The deep RL scheme allows each MU to optimize the behaviours with unknown dynamic statistics. Numerical experiments show that our proposed scheme outperforms the baselines in terms of the average utility under various system conditions.

Gestures constitute an important form of nonverbal communication where bodily actions are used for delivering messages alone or in parallel with spoken words. Recently, there exists an emerging trend of WiFi sensing-enabled gesture recognition due to its inherent merits like remote sensing, non-line-of-sight covering, and privacy-friendly. However, current WiFi-based approaches mainly reply on domain-specific training since they don’t know “where to look” and “when to look.” To this end, we propose WiGRUNT, a WiFi-enabled gesture recognition system using dual-attention network, to mimic how a keen human being intercepting a gesture regardless of the environment variations. The key insight is to train the network to dynamically focus on the domain-independent features of a gesture on the WiFi channel state information via a spatial-temporal dual-attention mechanism. WiGRUNT roots in a deep residual network (ResNet) backbone to evaluate the importance of spatial-temporal clues and exploit their inbuilt sequential correlations for fine-grained gesture recognition. We evaluate WiGRUNT on the open Widar3 dataset and show that it significantly outperforms its state-of-the-art rivals by achieving the best-ever performance in-domain or cross-domain.

User authentication plays a critical role in access control of a man-machine system, where the knowledge factor, such as a personal identification number, constitutes the most widely used authentication element. However, knowledge factors are usually vulnerable to the spoofing attack. Recently, the inheritance factor, such as fingerprints, emerges as an efficient alternative resilient to malicious users, but it normally requires special equipment. To this end, in this article, we propose WiPass, a device-free authentication system only leveraging the pervasive Wi-Fi infrastructure to explore keystroke dynamics (manner and rhythm of keystrokes) captured by the channel state information to recognize legitimate users while rejecting spoofers. However, it remains an open challenge to characterize the behavioral features hidden in the human subtle motions, such as keystrokes. Therefore, we build a signal enhancement model using Ricean distribution to amplify user keystroke dynamics and a hybrid learning model for user authentication, which consists of two parts, i.e., convolutional neural network based feature extraction and support vector machine based classification. The former relies on visualizing the channel responses into time-series images to learn the behavioral features of keystrokes in energy and spectrum domains, whereas the latter exploits such behavioral features for user authentication. We prototype WiPass on the low-cost off-the-shelf Wi-Fi devices and verify its performance. Empirical results show that WiPass achieves on average 92.1% authentication accuracy, 5.9% false accept rate, and 6.3% false reject rate in three real environments.

Data transmission in Vehicular Ad Hoc Networks (VANETs) often suffers from routing interruptions due to the unstable communication links between vehicles. Over the past decades, many traffic-aware routing protocols have been proposed to alleviate routing interruptions by sensing traffic conditions. However, in most traffic-aware routing protocols, vehicles must transmit a large number of control packets to accumulate traffic information, which may degrade network performance due to the resulting intense competition over the wireless medium. Instead of using control packets, we propose to leverage the beacon mechanism that has been widely used in VANETs to realize traffic awareness. Vehicles broadcast beacons to exchange necessary information with their neighbors periodically. We can leverage this information exchange process among vehicles to replace control packets. To realize this idea, first, a mathematical analysis is provided to demonstrate its feasibility. Then, we propose a concrete protocol to address the technical challenges of using beacons. Extensive simulation results show that our protocol performs better than the state-of-the-art counterparts regarding packet delivery ratio, average delivery time, and network overhead.

Change detection is the foundation of intelligent video surveillance of the airport ground. However, experiments have shown that change detection algorithms with good performance on traditional datasets (e.g., CDnet2014) perform poorly in airport ground surveillance. The reason is that traditional datasets focus on the diversity of scenarios, while the practical application requires robustness against various changes in a single scene. We posit that the solution to this problem is to establish a unique dataset for airport ground surveillance and develop specific algorithms for this scenario. In this paper, we present an Airport Ground Video Surveillance benchmark (AGVS) for change detection of the airport ground. AGVS includes 25 long videos, amounting to about 100000 frames and accurate ground truth for all frames. Each video contains multiple challenges specific to the airport ground (e.g., haze, camouflage, strip shape, shadow and illumination change, simultaneous multi-scale objects) and various appearance changes of the aircraft). Change detection ground truth is generated by manual annotation. The AGVS benchmark can be downloaded fromhttps://www.agvs-caac.com. Furthermore, we conduct a simple review of current change detection algorithms, both unsupervised or supervised, and then 21 state-of-the-art algorithms are tested and analyzed on the AGVS benchmark. Finally, we conclude with algorithm design principles of change detection for airport ground surveillance.

Video object segmentation (VOS) is the fundamental problem of vision-based intelligent transportation, and many VOS algorithms relying on inference from reference masks have been proposed. Due to the inherent defects of the inference strategy and the complex changes of targets, VOS methods that perform well on public datasets are usually ineffective in airport scenarios. We propose a spatiotemporal alignment network (STA-Net) that makes use of Automatic Dependent Surveillance-Broadcast (ADS-B) data as prior information to guide the long-term segmentation of aircraft. ADS-B is an airport-specific signal, which indicates the location of aircraft in real time. Based on ADS-B, we continuously generate new reference masks instead of using previous masks for inference, which greatly reduces the accumulation of inference errors. To achieve this, previous masks of each aircraft are aligned on the temporal domain based on the position information in ADS-B. All temporally-aligned masks are compared, and the one most similar to the current instant is reserved. This mask is both temporally and spatially aligned; hence it is a better reference mask for inference. Aligned masks are updated every time new ADS-B data arrive, so that they can support long-term inference. With the selected mask as a reference, aircraft of interest are segmented within a unified encoder-decoder framework over the long term. Experiments on a benchmark dataset and in a real airport scenario verify the effectiveness of the presented method.

Real-time smart grid monitoring is critical to enhancing resiliency and operational efficiency of power equipment. Cloud-based and edge-based fault detection systems integrating deep learning have been proposed recently to monitor the grid in real time. However, state-of-the-art cloud-based detection may require uploading a large amount of data and suffer from long network delay, while edge-based schemes do not adequately consider the detection requirement and thus cannot provide flexible and optimal performance. To solve these problems, we study a cloud-edge based hybrid smart grid fault detection system. Embedded devices are placed at the edge of the monitored equipment with several lightweight neural networks for fault detection. Considering limited communication resources, relatively low computation capabilities of edge devices, and different monitoring accuracies supported by these neural networks, we design an optimal communication and computational resource allocation method for this cloud-edge based smart grid fault detection system. Our method can maximize the processing throughput of the system and improve resource utilization while satisfying the data transmission and processing latency requirements. Extensive simulations are conducted and the results show the superiority of the proposed scheme over comparison schemes. We have also prototyped this system and verified its feasibility and performance in real-world scenarios.

We study how to support elasticity, that is, the ability to dynamically adjust the parallelism (i.e., the number of GPUs), for deep neural network (DNN) training in a GPU cluster. Elasticity can benefit multi-tenant GPU cluster management in many ways, for example, achieving various scheduling objectives (e.g., job throughput, job completion time, GPU efficiency) according to cluster load variations, utilizing transient idle resources, and supporting performance profiling, job migration, and straggler mitigation. We propose EDL, which enables elastic deep learning with a simple API and can be easily integrated with existing deep learning frameworks such as TensorFlow and PyTorch. EDL also incorporates techniques that are necessary to reduce the overhead of parallelism adjustments, such as stop-free scaling and dynamic data pipeline. We demonstrate with experiments that EDL can indeed bring significant benefits to the above-listed applications in GPU cluster management.

Real-time vital signs (breathing and heartbeat) monitoring is essential for patient care and sleep disease prevention. Current solutions are mostly based on wearable sensors or cameras, the former affects the quality of sleep, while the latter is not conducive to privacy protection, and the cost of these methods is usually expensive. In this paper, we propose Wital, a real-time vital signs monitoring system based on the low-cost and widespread COTS WiFi device. Most of the existing WiFi-based vital signs monitoring solutions utilize the line of sight (LOS) WiFi signals to achieve powerful performance. However, in our daily environments, NLOS sensing is more common. In this article, we first model the relationship between the energy ratio of LOS/NLOS signals and the ability to monitor vital signs based on the Ricean-K theory and theoretically prove that blocking LOS signals in NLOS sensing is more beneficial. We have also established a real-time vital signs monitoring system to verify our method, and the experimental results prove the effectiveness of our method.

In this paper, we study the optimal transmission of a multi-quality tiled 360 virtual reality (VR) video from a multi-antenna server (e.g., access point or base station) to multiple single-antenna users in a multiple-input multiple-output (MIMO)-orthogonal frequency division multiple access (OFDMA) system. We minimize the total transmission power with respect to the subcarrier allocation constraints, rate allocation constraints, and successful transmission constraints, by optimizing the beamforming vector and subcarrier, transmission power and rate allocation. The formulated resource allocation problem is a challenging mixed discrete-continuous optimization problem. We obtain an asymptotically optimal solution in the case of a large antenna array, and a suboptimal solution in the general case. As far as we know, this is the first work providing optimization-based design for 360 VR video transmission in MIMO-OFDMA systems. Finally, by numerical results, we show that the proposed solutions achieve significant improvement in performance compared to the existing solutions.

Magnetic wireless power transfer (WPT) has received widespread attention from both academia and industry, and magnetic resonance coupling (MRC) based WPT systems have a longer charging distance to support the scenarios with multiple transmitters (TXs) and multiple receivers (RXs). In such systems, an in-band reliable TX-RX communication protocol is essential to guarantee to charge performance. In this paper, we devise Onion, a dependency-aware in-band communication protocol for MIMO MRC-WPT systems. Technically, we extend the well-known EPCglobal C1G2 protocol in Radio Frequency Identification (RFID) fielded and make it suitable for mutual inductance based communication links in MRC-WPT systems. Furthermore, we craft an innovative onion-style layer-dependency based communication mechanism to utilize the positive impact of the relay phenomenon. We design and implement the Onion prototype and conduct extensive experiments to evaluate it. The experiment results demonstrate the effectiveness of the proposed protocol, which increases the communication success ratio by an average of 40% as compared to the dependency-unaware scheme.

In this paper, we investigate actual cloud-assisted electronic health (eHealth) systems in terms of security, efficiency, and functionality. Specifically, we propose a password-based subsequent-key-locked encryption mechanism to ensure the confidentiality of outsourced electronic health records (EHRs). We also propose a blockchain-based secure EHR provenance mechanism by designing the data structure of the EHR provenance record and deploying a public blockchain and smart contract to secure both EHRs and their provenance records. With the two mechanisms, we develop BESURE (blockchain-based cloud-assisted eHealth system with secure data provenance) to provide a secure EHR storage service with efficient provenance. Security analysis and comprehensive performance evaluation are conducted to demonstrate that BESURE is secure and efficient.

Fine-grained energy consumption analysis has great potential value in applications of Smart Grids, renewable energy, and Artificial Intelligence of Things. Non-Intrusive Load Monitoring (NILM) is a single-sensor alternative to the conventional one-sensor-for-one-appliance solution due to its ability to deduce individual appliances states from mixed measurements from the main power interface. Despite its advantages of low cost and easy maintenance, a few drawbacks hinders its widespread adoption. To enhance the Quality of Service (QoS) of NILM, four objectives should be achieved by careful designing: high accuracy, user transparency, low response delay, and low data redundancy.Inspired by observations of discriminative yet redundant current waveform and model sparsity, we propose LCL, a lightweight, contactless, plug-and-play solution for real-time load monitoring. The filtering module skips over unchanged input and compresses the measurements of interest using Compressed Sensing. The reconstruction-free inference module runs an attentional multi-label classification and returns all functioning appliance states directly from the compressed input. The compression module leverages model sparsity for real-time processing on edge devices. Evaluations based on our prototype deployed in real-life scenarios attest to the high QoS of LCL with a subset accuracy of 94.2% and a delay reduction of 52.2%. Our solution further filters out 96.8% of the redundant input and attains a Measurement Rate of 0.1 without noticeable impact on the performance.

Recently, multiple-input multiple-output (MIMO) technology has been introduced into magnetic resonant coupling (MRC) enabled wireless power transfer (WPT) systems for concurrent charging of multiple devices. However, impedance mismatching phenomena caused by strong TX-RX or RX-RX coupling greatly affect the power delivered to load (PDL) in practical charging systems. To solve this issue, we propose an effective scheduling algorithm for Impedance Matching enhanced PDL optimization in MIMO MRC-WPT systems (called IMP), which integrates the transmitter scheduling together with the impedance matching techniques, i.e., adjusting TX coils for tuning TX-RX coupling and grouping RXs to separate strongly coupled RX pairs. We formulate this as a joint optimization problem and decouple it into three sub-problems, i.e., current scheduling, coil adjustment, and RX grouping, and solve them through alternating direction method of multipliers (ADMM) based, tabu search (TS) based, and graph clique cover based algorithms, respectively. Extensive experiments are performed on a prototype testbed, and the results demonstrate the effectiveness of our solution. Compared with the state-of-the-art power transfer efficiency (PTE) maximization solution, the proposed algorithm IMP achieves a 74.7X performance improvement of PDL on average.

Backscatter communication integrated with RF energy harvesting provides a promising solution to prolong the lifetime of wireless sensor networks (WSNs). However, the existing centralized or flooding-based routing protocols can not be applied directly to large-scale backscatter-enabled WSN due to fussy implementation or excessive messages. In this paper, we investigate the routing protocol for such networks to maximize the throughput by arranging the uploading path of each sensor. We first propose a centralized solution by converting the original problem into a maximum flow problem. Then, after inspecting the characteristics of the backscatter-enabled sensors, we propose a flow balancing-based push-relabel algorithm. We conduct extensive experiments to evaluate the proposed algorithms. The results demonstrate the effectiveness of our distributed protocol, which outperforms the other baseline solutions and keeps close approximation to the centralized solution.

The point cloud videos, thanks to the multi-view and immersive experiences, have recently attracted notable attentions from both academia and industry. Due to the high data volume, a point cloud video also raises the challenge of quality-of-experience (QoE), which is in terms of the balance between playback quality and buffering delay during the transmission under time-varying system conditions. In this paper, we propose a deep reinforcement learning (DRL) approach to optimize the expected long-term QoE for the client. Over the time horizon, the proposed approach learns to select the tiles of the corresponding video for transmissions in an iterative way. Under various settings, numerical experiments based on real throughput data traces are conducted to evaluate the proposed approach. Compared to the baselines, our approach not only enhances the video quality but also reduces the re-buffering time, obtaining an improvement of average QoE for the client by 9%–14%.

The construction of ground base stations is often time-consuming and costly, especially in challenging areas such as disaster areas and military battlefields. With the advancement of unmanned aerial vehicle (UAV) technology, UAV-mounted aerial base stations have recently become increasingly attractive for fast and cost-effective communication establishment, and UAV deployment optimization has since are of homogeneous become a vital research problem. However, early studies tend to consider an oversimplified scenario where UAVs are of homogeneous capabilities, leading to limited applicabilities. We consider a more realistic and complex UAV deployment problem, where UAVs have heterogeneous capabilities. This new deployment problem strives to minimize the number of UAVs deployed while meeting the ground user coverage requirements as well as UAV-to-UAV connectivity requirement, by selecting the appropriate UAVs, calculating their three-dimensional (3D) positions, and adjusting their transmission powers. UAV positions are optimized for average air-to-ground channel quality improvement alongside. To tackle this NP-hard problem, we propose MO-BPSO-GA, which carefully adapts and combines multi-objective particle swarm optimization (MO-PSO), binary particle swarm optimization (BPSO), and genetic algorithm (GA). Simulation results demonstrate that MO-BPSO-GA swiftly converges to an outstanding solution in terms of the number of UAVs deployed, the potion of ground users covered, and the mean channel quality.

Unmanned-aerial-vehicle (UAV)-enabled mobile-edge computing (MEC) has emerged as a promising paradigm to extend the coverage of computation service for Internet of Things (IoT) applications, which are usually time sensitive and computation intensive. In this article, a novel design framework is proposed for a multi-UAV-enabled MEC system, where edge servers are equipped on multiple UAVs to provide flexible computation assistance to IoT devices with hard deadlines. The aim is to maximize the number of served IoT devices through jointly optimizing UAV trajectory and service indicator as well as resource allocation and computation offloading, where the chosen IoT devices will complete their computation tasks on time under given energy budgets and co-channel interference is taken into account. We formulate the optimization problem as a mixed integer nonlinear programming (MINLP), which is challenging to solve directly. The problem is first reformulated to a more mathematically tractable form by adding a penalty term to the objective function. We then decouple the problem into two subproblems and develop an iterative algorithm by solving the two subproblems with alternating optimization and successive convex approximation techniques, where the proposed algorithm converges to a Karush–Kuhn–Tucker (KKT) solution. In addition, an efficient initialization scheme is proposed based on multiple traveling salesman problem with time windows (m-TSPTWs) method. Finally, simulation results are provided to demonstrate that the proposed joint design achieves significant performance gains over baseline schemes.

User authentication is the first and most critical step in protecting a man-machine system from a malicious spoofer. However, security and privacy are just like the two sides of one coin, hard to see both at the same time, especially by the current mainstream credential- and biometric-based approaches. To this end, we propose WiONE, a safe and privacy-preserving user authentication system leveraging the ubiquitous Wi-Fi infrastructure by exploring “how you behave” rather than “who you are”. The key idea is to apply deep learning to user physical behavior captured by Wi-Fi channel state information (CSI) to identify legitimate users while rejecting spoofers. The design of WiONE faces two challenges, namely, how to capture the subtle behavior, such as a keystroke on CSI, and how to mitigate the heavy environment-specific training required by deep learning. For the former, we design a behavior enhancement model based on the Rician fading to highlight the behavior-induced information by suppressing the behavior-unrelated information on channel response. For the latter, we develop a behavior characterization method tailored for the prototypical networks to facilitate the extraction of the domain-independent behavioral features and enable one-shot recognition of a new user in a new environment. Numerous experiments are conducted in several real-world environments, and the results show that WiONE outperforms its state-of-the-art rivals in authentication performance with much less training effort.

Unmanned aerial vehicles (UAVs) can be flexibly deployed to offload cellular traffic or to provide video services for emergency scenarios without infrastructure. However, the inherent resource allocation and three-dimensional (3D) aerial trajectory design have not been formally studied. In this paper, we study the joint resource allocation and 3D aerial trajectory design for dynamic adaptive streaming over HTTP (DASH)-enabled services in a UAV communication system, where a UAV is employed as a base station for multiuser video streaming. Various factors are taken into account, including video data rate, quality variation, communication outage, play interruption, etc. By adopting a video streaming utility model, two fundamental problems are formulated with different practical aims: the first problem maximizes the minimum utility for all users within a given time horizon such that max-min fairness can be provided, and the second problem minimizes the UAV operation time subject to the individual utility requirement for all users to prolong UAV endurance. To tackle the first non-convex problem, we decouple it into three sub-problems, and a three-stage iterative algorithm is proposed to obtain a suboptimal solution by solving the three sub-problems with successive convex approximation and alternating optimization techniques. An exponential search based algorithm is proposed for the second problem by utilizing the structure of the considered problem and a similar three-stage iterative algorithm. Extensive simulations are carried out to evaluate the performance, and the results show that our proposed designs significantly outperform baseline schemes. Furthermore, our results reveal new insights of UAV movement for video streaming and unveil the tradeoff between utility and quality variance.

This paper investigates adaptive streaming of one or multiple tiled 360 videos from a multi-antenna base station (BS) to one or multiple single-antenna users, respectively, in a multi-carrier wireless system. We aim to maximize the video quality while keeping rebuffering time small via encoding rate adaptation at each group of pictures (GOP) and transmission adaptation at each (transmission) slot. To capture the impact of field-of-view (FoV) prediction, we consider three cases of FoV viewing probability distributions, i.e., perfect, imperfect, and unknown FoV viewing probability distributions, and use the average total utility, worst average total utility, and worst total utility as the respective performance metrics. In the single-user scenario, we optimize the encoding rates of the tiles, encoding rates of the FoVs, and transmission beamforming vectors for all subcarriers to maximize the total utility in each case. In the multi-user scenario, we adopt rate splitting with successive decoding and optimize the encoding rates of the tiles, encoding rates of the FoVs, rates of the common and private messages, and transmission beamforming vectors for all subcarriers to maximize the total utility in each case. Then, we separate the challenging optimization problem into multiple tractable problems in each scenario. In the single-user scenario, we obtain a globally optimal solution of each problem using transformation techniques and the Karush-Kuhn-Tucker (KKT) conditions. In the multi-user scenario, we obtain a KKT point of each problem using the concave-convex procedure (CCCP). Finally, numerical results demonstrate that the proposed solutions achieve notable gains in quality, quality variation, and rebuffering time over existing schemes in all three cases. To the best of our knowledge, this is the first work revealing the impact of FoV prediction on the performance of adaptive streaming of tiled 360 videos.

Vehicular computation offloading is a well-received strategy to execute delay-sensitive and/or compute-intensive tasks of legacy vehicles. The response time of vehicular computation offloading can be shortened by using mobile edge computing that offers strong computing power, driving these computation tasks closer to end users. However, the quality of communication is hard to guarantee due to the obstruction of dense buildings or lack of infrastructure in some zones. Unmanned Aerial Vehicles (UAVs), therefore, have become one of the means to establish communication links for the two ends owing to its characteristics of ignoring terrain and flexible deployment. To make a sensible decision of computation offloading, nevertheless vehicles need to gather offloading-related global information, in which Software-Defined Networking (SDN) has shown its advances in data collection and centralized management. In this paper, thus, we propose an SDN-enabled UAV-assisted vehicular computation offloading optimization framework to minimize the system cost of vehicle computing tasks. In our framework, the UAV and the Mobile Edge Computing (MEC) server can work on behalf of the vehicle users to execute the delay-sensitive and compute-intensive tasks. The UAV, in a meanwhile, can also be deployed as a relay node to assist in forwarding computation tasks to the MEC server. We formulate the offloading decision-making problem as a multi-players computation offloading sequential game, and design the UAV-assisted Vehicular computation Cost Optimization (UVCO) algorithm to solve this problem. Simulation results demonstrate that our proposed algorithm can make the offloading decision to minimize the Average System Cost (ASC).

The Internet of Vehicles (IoV) enables real-time data exchange among vehicles and roadside units and thus provides a promising solution to alleviate traffic jams in the urban area. Meanwhile, better traffic management via efficient traffic light control can benefit the IoV as well by enabling a better communication environment and decreasing the network load. As such, IoV and efficient traffic light control can formulate a virtuous cycle. Edge computing, an emerging technology to provide low-latency computation capabilities at the edge of the network, can further improve the performance of this cycle. However, while the collected information is valuable, an efficient solution for better utilization and faster feedback has yet to be developed for edge-empowered IoV. To this end, we propose a Decentralized Reinforcement Learning at the Edge for traffic light control in the IoV (DRLE). DRLE exploits the ubiquity of the IoV to accelerate traffic data collection and interpretation towards better traffic light control and congestion alleviation. Operating within the coverage of the edge servers, DRLE aggregates data from neighboring edge servers for city-scale traffic light control. DRLE decomposes the highly complex problem of large area control into a decentralized multi-agent problem. We prove its global optima with concrete mathematical reasoning and demonstrate its superiority over several state-of-the-art algorithms via extensive evaluations.

Radio frequency identification (RFID) has been widely used in many fields such as object tracking and inventory management. For RFID systems, grouping is a fundamental issue which can support efficient multicast transmissions, dynamic tag management, and accurate aggregate queries. Existing grouping protocols have drawbacks of unknown theoretical communication time, high computational cost on the server end and inability to deal with unexpected tags which are those tags whose IDs have not been collected by readers. In this paper, we would like to address the above limitations and consider a more general grouping problem that allows an arbitrary number of unexpected tags to present. Our objective is to design a protocol that guarantees the reader to efficiently and correctly notify each known tag of its group-ID, while the probability that an unexpected tag is mistakenly notified of any group-ID is smaller than a pre-determined value. In this paper, we first obtain a lower bound on the communication time for solving this generalized grouping problem. Then, we propose a near-optimal protocol, called OPT-G, and prove that its communication time approximately equals the lower bound. Finally, we report extensive simulation results that demonstrate OPT-G's near-optimal performance and its superiority over existing baseline schemes.

In this paper, we would like to investigate the optimal wireless streaming of a multi-quality tiled 360 virtual reality (VR) video from a server to multiple users. To this end, we propose to maximally exploit potential multicast opportunities by effectively utilizing characteristics of multi-quality tiled 360 VR videos and computation resources at the users' side. In particular, we consider two requirements for quality variation in one field-of-view (FoV), i.e., the absolute smoothness requirement and the relative smoothness requirement, and two video playback modes, i.e., the direct-playback mode (without user transcoding) and transcode-playback mode (with user transcoding). Besides natural multicast opportunities, we introduce two new types of multicast opportunities, namely, relative smoothness-enabled multicast opportunities, which allow a flexible tradeoff between viewing quality and communications resource consumption, and transcoding-enabled multicast opportunities, which allow a flexible tradeoff between computation and communications resource consumptions. Then, we establish a novel mathematical model that reflects the impacts of natural, relative smoothness-enabled, and transcoding-enabled multicast opportunities on the average transmission energy and transcoding energy. Based on this model, we optimize the transmission resource allocation, playback quality level selection, and transmission quality level selection to minimize the energy consumption in the four cases with different requirements for quality variation and video playback modes. By comparing the optimal values in the four cases, we prove that the energy consumption reduces when more multicast opportunities can be utilized. Finally, numerical results show substantial gains of the proposed solutions over existing schemes, and demonstrate the importance of exploiting of the three types of multicast opportunities.

State access in existing distributed stream processing systems is restricted locally within each operator. However, in advanced stream analytics such as online learning and dynamic graph analytics, enabling state sharing across different operators makes application development easier and stream processing more efficient. In addition, when stream records are timestamped, proper time semantics should be defined for both state updates and fetches. We propose a new state abstraction to address the limitations of existing systems and develop a distributed stream processing system, Nova, with native support for timestamped state sharing. We validate the expressiveness and efficiency of Nova with extensive experiments.

In this paper, we study the optimal wireless streaming of a multi-quality tiled 360 virtual reality (VR) video from a multi-antenna server to multiple single-antenna users in a multiple-input multiple-output (MIMO)-orthogonal frequency division multiple access (OFDMA) system. In the scenario without user transcoding, we jointly optimize beamforming and subcarrier, transmission power, and rate allocation to minimize the total transmission power. This problem is a challenging mixed discrete-continuous optimization problem. We obtain a globally optimal solution for small multicast groups, an asymptotically optimal solution for a large antenna array, and a suboptimal solution for the general case. In the scenario with user transcoding, we jointly optimize the quality level selection, beamforming, and subcarrier, transmission power, and rate allocation to minimize the weighted sum of the average total transmission power and the transcoding power. This problem is a two-timescale mixed discrete-continuous optimization problem, which is even more challenging than the problem for the scenario without user transcoding. We obtain a globally optimal solution for small multicast groups, an asymptotically optimal solution for a large antenna array, and a low-complexity suboptimal solution for the general case. Finally, numerical results demonstrate the significant gains of proposed solutions over the existing solutions.

This paper investigates the problem of age of information (AoI)-aware resource awareness in an unmanned aerial vehicle (UAV)-assisted mobile-edge computing (MEC) system, which is deployed by an infrastructure provider (InP). A service provider leases resources from the InP to serve the mobile users (MUs) with sporadic computation requests. Due to the limited number of channels and the finite shared I/O resource of the UAV, the MUs compete to schedule local and remote task computations in accordance with the observations of system dynamics. The aim of each MU is to selfishly maximize the expected long-term computation performance. We formulate the non-cooperative interactions among the MUs as a stochastic game. To approach the Nash equilibrium solutions, we propose a novel online deep reinforcement learning (DRL) scheme, which enables each MU to behave using its local conjectures only. The DRL scheme employs two separate deep Q-networks to approximate the Q-factor and the post-decision Q-factor for each MU. Numerical experiments show the potentials of the online DRL scheme in balancing the tradeoff between AoI and energy consumption.

In this paper, we investigate wireless streaming of multi-quality tiled 360 virtual reality (VR) videos from a multi-antenna server to multiple single-antenna users in a multicarrier system. To capture the impact of field-of-view (FoV) prediction, we consider three cases of FoV viewing probability distributions, i.e., perfect, imperfect and unknown FoV viewing probability distributions, and use the average total utility, worst average total utility and worst total utility as the respective performance metrics. We adopt rate splitting with successive decoding for efficient transmission of multiple sets of tiles of different 360 VR videos to their requesting users. In each case, we optimize the encoding rates of the tiles, minimum encoding rates of the FoVs, rates of the common and private messages and transmission beamforming vectors to maximize the total utility. The problems in the three cases are all challenging nonconvex optimization problems. We successfully transform the problem in each case into a difference of convex (DC) programming problem with a differentiable objective function, and obtain a suboptimal solution using concave-convex procedure (CCCP). Finally, numerical results demonstrate the proposed solutions achieve notable gains over existing schemes in all three cases. To the best of our knowledge, this is the first work revealing the impact of FoV prediction and its accuracy on the performance of streaming of multi-quality tiled 360 VR videos.

Point cloud video is the most popular representation of hologram, which is the medium to precedent natural content in VR/AR/MR and is expected to be the next generation video. Point cloud video system provides users immersive viewing experience with six degrees of freedom (6DoF) and has wide applications in many fields such as online education and entertainment. To further enhance these applications, point cloud video streaming is in critical demand. The inherent challenges lie in the large size by the necessity of recording the three-dimensional coordinates besides color information, and the associated high computation complexity of encoding/decoding. To this end, this paper proposes a communication and computational resource allocation scheme for QoE-driven point cloud video streaming. In particular, with the goal to maximize the defined QoE by selecting proper quality levels (uncompressed tiles at different quality levels are also considered) for each partitioned point cloud video tile, we formulate this into an optimization problem under the limited communication and computational resources constraints and propose a scheme to solve it. Extensive simulations are conducted and the simulation results show the superior performance of the proposed scheme over the existing schemes.

Network Function Virtualization (NFV) enables flexible deployment of network services as applications. Network operators expect to use a limited number of Network Function (NF) instances to handle the fluctuating traffic load and provide network services. However, it is a big challenge to guarantee the Quality of Service (QoS) under the unpredictable network traffic while minimizing the processing resources. One typical solution is to realize NF scale-out, scale-in and load balancing by elastically migrating the related traffic flows with SoftwareDefined Networking (SDN). However, it is difficult to optimally migrate flows since many real-time statuses of NF instances should be considered to make accurate decisions. In this paper, we propose DeepMigration to solve the problem by efficiently and dynamically migrating traffic flows among different NF instances. DeepMigration is a Deep Reinforcement Learning (DRL)-based solution coupled with Graph Neural Network (GNN). By taking advantages of the graph-based relationship deduction ability from our customized GNN and the self-evolution ability from the experience training of DRL, DeepMigration can accurately model the cost (e.g., migration latency) and the benefit (e.g., reducing the number of NF instances) of flow migration among different NF instances and generate dynamic and effective flow migration policies to improve the QoS. Experiment results show that DeepMigration requires less migration cost and saves up to 71.6{%} of the computation time than existing solutions.

By integrating both energy harvesting and backscatter communication technologies, so-called `battery-free tag' emerges as a promising solution to the energy related issues in IoT. However, such tags present new challenges due to the unstable energy supply and excitation signals, which are critical to realize successful backscatter communications. In this paper, we present a novel system, denoted as ecUWB, which enables robust communication for battery-free tags where unstable WiFi signals act as the unified source for both energy supply and excitation signals. At tag side, we propose a charging-transmission division scheme to achieve better signal utilization, and introduce a re-transmission mechanism for possible excitation signal interruption. At receiver side, we implement a simply method which is based on DBSCAN (Density-Based Spatial Clustering of Applications with Noise) to predict the uncontrollable signals, and propose an energy-centric tag scheduling method according to the tag energy estimation results. Extensive experiments are carried out on customized tags and NI USRP platform. The results show that ecUWB outperforms the existing ones in terms of performance and efficiency under the unstable WiFi signals.

Falls are the leading cause of fatal and non-fatal injuries for the elderly, and fall detection system is critical for reducing the aid response time. Wearable sensor-based system becomes popular for its convenience and non-invasion of privacy. In this paper, we focus on fall detection system to be integrated into low-cost COTS (Commercial Off-The-Shelf) smart band, which is expected to be worn by the elderly for a long time due to its advantages of low price and low power consumption. Aiming at the low sampling rate property inherent in such devices, we analyze the characteristic of fall signal and propose a system which achieve better accuracy by combining the features of time domain, time-frequency domain and instantaneous frequency. We further apply data augmentation mechanism to tackle the issue of fall data lack. Extensive experiments are conducted to evaluate the proposed system. The results demonstrate that our system can achieve over 98% accuracy on our dataset and 97% accuracy on open source dataset.

In many real-time RFID-enabled applications (e.g., logistic tracking and warehouse controlling), a subset of wanted tags is often selected from a tag population for monitoring and querying purposes. How this subset of tags is rapidly selected, which is referred to as the subset selection problem, becomes pivotal for boosting the efficiency in RFID systems. Current state-of-the-art schemes result in high communication latencies, which are far from the optimum, and this degrades the system performance. This problem is addressed in this paper by using a simple Bit-Counting Function BCF(), which has also been employed widely by other protocols in RFID systems. In particular, we first propose a near-OPTimal SeLection protocol, denoted by OPTSL, to rapidly solve this problem based on the simple function BCF(). Second, we prove that the communication time of OPTSL is near-optimal with rigorous theoretical analysis. Finally, we conduct extensive simulations to verify that the communication time of the proposed OPT-SL is not only near-optimal but also significantly less than that of benchmark protocols.

Millimeter wave (mmWave) signal-based localization is a promising scheme due to high precision in the lineof-sight (LoS) scenarios. However, even small obstacles would hinder mmWave localization by blocking the LoS paths, and environment reflection-based schemes under non-LoS (NLoS) scenarios couldn't guarantee the precision. In this paper, we investigate mmWave NLoS localization scheme based on recent fast-growing research for specialized mmWave reflectors. Our system uses multiple reflectors in the environment to act as anchors for target localization. Firstly, we propose a two-phase reflector discovery mechanism to let transmitter identify the reflectors and estimate their positions as well. Secondly, we introduce a hashing-based beam alignment method with logarithmic complexity to obtain the relative relationship among reflectors and the target. Lastly, we put forward a triangulation-based method for target localization, along with credit-based fusing mechanism to handle the possible imprecise estimated reflector positions. Extensive experiments are carried out to evaluate the proposed scheme. The results demonstrate the effectiveness of the proposed system, which achieves 50% average improvement over environment reflection-based methods. Furthermore, the proposed hashing-based beam alignment process dramatically reduces the time-consumption as compared with baseline using exhaustive search, e.g., 18x, 37x and 40x reductions are observed with 1, 4 and 7 reflectors, respectively.

Body movement is one of the most important indicators of sleep quality for elderly people living alone. Body movement is crucial for sleep staging and can be combined with other indicators, such as breathing and heart rate to monitor sleep quality. Nevertheless, traditional sleep monitoring methods are inconvenient and may invade users' privacy. To solve these problems, we propose a contactless body movement recognition (CBMR) method via WiFi signals. First, CBMR uses commercial off-the-shelf WiFi devices to collect channel state information (CSI) data of body movement and segment the CSI data by sliding window. Then, the context information of the segmented CSI data is learned by a bidirectional recurrent neural network (Bi-RNN). Bi-RNN can fuse the forward and backward propagation information at some point, and input it into a deeper independently recurrent neural network (IndRNN) with residual mechanism to extract the deeper features and capture the time dependencies of CSI data. Finally, the type of body movement can be recognized and classified by the softmax function. CBMR can effectively reduce data preprocessing and the delay caused by manually extracting features. The results of an experiment conducted on a complex body movement data set show that our method gives desirable performance and achieves an average accuracy of greater than 93.5%, which implies a prospect application of CBMR.

Completion time and energy consumption of the unmanned aerial vehicle (UAV) are two important design aspects in UAV-enabled applications. In this article, we consider a UAV-enabled mobile-edge computing (MEC) system for Internet-of-Things (IoT) computation offloading with limited or no common cloud/edge infrastructure. We study the joint design of computation offloading and resource allocation, as well as UAV trajectory for minimization of energy consumption and completion time of the UAV, subject to the IoT devices' task and energy budget constraints. We first consider the UAV energy minimization problem without predetermined completion time, a discretized nonconvex equivalent problem is obtained by using the path discretization technique. An efficient alternating optimization algorithm for the discretized problem is proposed by decoupling it into two subproblems and addressing the two subproblems with successive convex approximation (SCA)-based algorithms iteratively. Subsequently, we focus on the completion time minimization problem, which is nonconvex and challenging to solve. By using the same path discretization approximation model to reformulate problem, a similar alternating optimization algorithm is proposed. Furthermore, we study the Pareto-optimal solution that balances the tradeoff between the UAV energy and completion time. The simulation results are provided to corroborate this article and show that the proposed designs outperform the baseline schemes. Our results unveil the tradeoff between completion time and energy consumption of the UAV for the MEC system, and the proposed solution can provide the performance close to the lower bound.

Multi-view videos (MVVs) provide immersive viewing experience, at the cost of traffic load increase for wireless networks. In this paper, we would like to optimize MVV transmission in a multiuser wireless network by exploiting both natural multicast opportunities and view synthesis-enabled multicast opportunities. Specifically, we first establish a mathematical model to specify view synthesis at the server and each user, and characterize its impact on multicast opportunities. This model is highly nontrivial and fundamentally enables the optimization of view synthesis-based multicast opportunities. For given video quality requirements of all users, we consider the optimization of view selection, transmission time and power allocation to minimize the average weighted sum energy consumption for view transmission and synthesis. In addition, under the energy consumption constraints at the server and each user respectively, we consider the optimization of view selection, transmission time and power allocation and video quality selection to maximize the total utility. These two optimization problems are challenging mixed discrete-continuous optimization problems. For the first problem, we propose an algorithm to obtain an optimal solution with reduced computational complexity by exploiting optimality properties. For each problem, to reduce computational complexity, we also propose a low-complexity algorithm to obtain a suboptimal solution, using Difference of Convex (DC) programming. Finally, numerical results show the advantage of the proposed solutions over existing ones, and demonstrate the importance of the optimization of view synthesis-enabled multicast opportunities in MVV transmission.

In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network. With the observation of global network state at each scheduling slot, the roadside unit (RSU) allocates the frequency bands and schedules packet transmissions for all vehicle user equipment-pairs (VUE-pairs). We model the stochastic decision-making procedure as a discrete-time single-agent Markov decision process (MDP). The technical challenges in solving the optimal control policy originate from high spatial mobility and temporally varying traffic information arrivals of the VUE-pairs. To make the problem solving tractable, we first decompose the original MDP into a series of per-VUE-pair MDPs. Then we propose a proactive algorithm based on long short-term memory and deep reinforcement learning techniques to address the partial observability and the curse of high dimensionality in local network state space faced by each VUE-pair. With the proposed algorithm, the RSU makes the optimal frequency band allocation and packet scheduling decision at each scheduling slot in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical experiments validate the theoretical analysis and demonstrate the significant performance improvements from the proposed algorithm.

Good quality sleep is essential for good health and sleep monitoring becomes a vital research topic. This paper provides a low cost, continuous and contactless WiFi-based vital signs (breathing and heart rate) monitoring method. In particular, we set up the antennas based on Fresnel diffraction model and signal propagation theory, which enhances the detection of weak breathing/heartbeat motion. We implement a prototype system using the off-shelf devices and a real-time processing system to monitor vital signs in real time. The experimental results indicate the accurate breathing rate and heart rate detection performance. To the best of our knowledge, this is the first work to use a pair of WiFi devices and omnidirectional antennas to achieve real-time individual breathing rate and heart rate monitoring in different sleeping postures.

In this paper, we would like to investigate fundamental impacts of multicast opportunities on efficient transmission of a 360 VR video to multiple users in the cases with and without transcoding at each user. We establish a novel mathematical model that reflects the impacts of multicast opportunities on the average transmission energy in both cases and the transcoding energy in the case with user transcoding, and facilitates the optimal exploitation of transcoding-enabled multicast opportunities. In the case without user transcoding, we optimize the transmission resource allocation to minimize the average transmission energy by exploiting natural multicast opportunities. The problem is nonconvex. We transform it to an equivalent convex problem and obtain an optimal solution using standard convex optimization techniques. In the case with user transcoding, we optimize the transmission resource allocation and the transmission quality level selection to minimize the weighted sum of the average transmission energy and the transcoding energy by exploiting both natural and transcoding- enabled multicast opportunities. The problem is a challenging mixed discrete-continuous optimization problem. We transform it to a Difference of Convex (DC) programming problem and obtain a suboptimal solution using a DC algorithm. Finally, numerical results demonstrate the importance of effective exploitation of transcoding-enabled multicast opportunities in the case with user transcoding.

How can we effectively log a fine-grained sleep record consisting of still postures and in-place motions for the sleep disorder diagnosis without any specialized hardware? Existing sensor-based or vision-based solutions are either obstructive to use or rely on particular devices. This paper introduces SleepGuardian, a Radio Frequency (RF) based sleep monitoring system leveraging only omnipresent WiFi signals to provide a silent (unobtrusive and free of privacy concerns) yet loyal (finegrained and reliable) logging service. The key to SleepGuardian is to model the energy feature of wireless channel as a Gaussian Mixture Model (GMM) to adaptively recognize motions happened during sleep. We prototype SleepGuardian with off-the-shelf WiFi devices and evaluate it in an office. Experimental results over 11 subjects with several artificial and real periods of sleep demonstrate that SleepGuardian is effective since it achieves 100% overall accuracy (ACC), 0% false negative rate (FNR) and 0.64 s mean absolute error (MAE) on average. Considering that SleepGuardian is compatible with existing WiFi infrastructure, it constitutes a low-cost yet promising solution for sleep monitoring.

In this paper, we investigate the optimization of task operation sequences for designing practical multi-user mobile edge computing (MEC) systems. First, we consider a computation task model with non-negligible sizes of computation results and arbitrary task arrival times and deadlines. Based on it, we further establish a computation offloading model considering non-negligible executing durations, allowing parallel transmissions and executions for different tasks, and reflecting the impact of task operation sequences. Then, we formulate the weighted sum energy consumption minimization problem to optimize the task operation sequences and starting times for uploading, executing and downloading as well as uploading and downloading time durations. The problem is a challenging mixed discrete-continuous optimization problem. By analyzing structural properties of task operation sequences, we develop an algorithm to obtain an optimal solution. In addition, using several optimization techniques, we transform the problem to an equivalent Difference of Convex (DC) problem, and develop a low-complexity algorithm to obtain a suboptimal solution using Penalty Convex Concave Procedure (CCP). Finally, numerical results demonstrate the advantages of the suboptimal solution over some optimized schemes with typical choices for task operation sequences.

In recent years, the rapid development of cloud computing, networking, and mobile computing have substantially promoted mobile edge computing (MEC). Currently, most of the MEC services can be roughly divided into two categories: computation offloading to accelerate computation and save the energy of mobile devices and data services to shorten the latency between the content providers and the mobile users. Although emerging services such as user-specified transcoding and AR/VR systems require joint optimization of computing resource allocation and data placement, there is little research on it. In this work, we carry out an in-depth study on the interaction of computing resource allocation and data placement in mobile edge computing environments. Based on the analysis of the temporal and spatial characteristics of the two tasks, we propose a joint optimization framework that works with online manner. The proposed method employs hybrid timescales: a coarse-grained timescale to update the data placement and a fine-grained timescale to decide computing resource allocation. The proposed method achieves provable near-optimal performance without buffering users' requirements and does not assume that future trends in user requirements are predictable.

Facilitating real-time query over massive IoT data streams becomes increasingly important nowadays, for that it can boost the performances of real-time network services significantly. Let δ = e1, e2, ⋯ , et, ⋯ represent an IoT data stream, where each element et arrives at time point t. In this paper, we consider the problem of how to support fast range emptiness querying over an IoT data stream δ in sliding window model with a space-efficient data structure, and we denote this problem as the (ε, L)-ARE-problem. To be more formally, subjected to the constraint of one-pass scan of stream δ, the main task of the (ε, L)-ARE-problem is to design a space-efficient data structure that is capable of always representing W(t, n), which are the n latest elements of stream δ until time point t (i.e., W(t, n) = emax{1,t-n+1}, ⋯ , et-1, et), and quickly answering an emptiness query of the form ”W(t, n) ∩ I = 0?”, with a false positive rate no larger than ε, for any query interval I of length up to L. We design a space-efficient data structure D to solve the (ε, L)-ARE-problem and prove that D has constant time cost for querying an interval, inserting a stream element and evicting outdated elements. The efficiency is demonstrated with extensive simulation results as well.

In recent years, the fast development of mobile computing has substantially promoted the mobile edge computing (also known as multi-access edge computing, MEC). Placing content in edges is one of the most important uses of MEC for that it can benefit a variety of service and applications such as video streaming and VR/AR. Currently, most of the existing researches are application specified, and the heterogeneities in data allocating devices and content have not been sufficiently explored. Aiming at developing a general optimal data allocating decision algorithm for MEC, in this work, we carry out in-depth study on the interaction of data allocating and fetching in heterogenous edge computing networks, showing the NP-hardness of the optimal decision problem. We then present polynomial algorithms with 1 - 1/e-approximation factor. Our algorithms has reasonable performance guarantee with low computation complexity. We verify the proposed approach with analysis and simulations.

In this paper, we present WoSense, a device-free and real-time behavior analysis system leveraging only WiFi infrastructures. WoSense aims to remotely recognize various human behaviors like surfing, gaming and working around computers, which are considered to be an essential part of our daily lives both at work and at home. The key of WoSense is to exploit the signal distortions on channel data caused by gestures like finger and hand movements, and then identify possible behaviors via the composite of gestures. Therefore, two critical challenges need to be tackled: how to enhance such insignificant distortions led by micro gestures, how to segment the continuous signals according to different gestures in a real-time manner? For the former, instead of relying on empirical studies like our rivals, WoSense offers a Fresnel zone based model with theoretic understandings between the gestures and signal distortions. For the latter, WoSense employs a light-weight automatic segmentation algorithm exploring the variance feature of channel data. We prototype WoSense on the commodity low-cost WiFi devices and evaluate its performance in extensive real- world experiments. WoSense achieves an average 96.77% accuracy for distinguishing the typing and mousing gestures, and 92.5% accuracy for recognizing four different behaviors, i.e., stationary, surfing, gaming and working.

Virtual Reality (VR) provides an immersive 360 viewing experience and has been widely used in vast areas such as education, entertainment and training. To further widen its applications, networked 360 VR video becomes essential. Quality of Experience (QoE), which objectively measures user experience, is vital for 360 VR video transmission mechanism design. However, to the best of our knowledge, there are few subjective QoE metric for 360 VR video transmission over wireless networks. In this paper, we aim to fill this gap by proposing a general QoE model based on subjective quality evaluation experiments. First, the state-of-the-art 360 VR video processing and wireless transmission schemes are used to conduct subjective experiments according to the international standard. Then, how user experience is affected by different factors, including users' viewing angle, tiling (how the 360 VR video is partitioned into smaller parts to facilitate transmission), stall and resolution switch, is analyzed mathematically. A general QoE model is finally proposed to facilitate the future 360 VR video streaming mechanism design.

A 360 virtual reality (VR) video, recording a scene of interest in every direction, provides VR users with immersive viewing experience. However, transmission of a 360 VR video which is of a much larger size than a traditional video to mobile users brings a heavy burden to a wireless network. In this paper, we consider multi-quality multicast of a 360 VR video from a single server to multiple users using time division multiple access (TDMA). To improve transmission efficiency, tiling is adopted, and each tile is pre-encoded into multiple representations with different qualities. We optimize the quality level selection, transmission time allocation and transmission power allocation to maximize the total utility of all users under the transmission time and power allocation constraints as well as the quality smoothness constraints for mixed-quality tiles. The problem is a challenging mixed discrete-continuous optimization problem. We propose two low-complexity algorithms to obtain two suboptimal solutions, using continuous relaxation and DC programming, respectively. Finally, numerical results demonstrate the advantage of the proposed solutions.

Multi-view videos (MVVs) provide immersive viewing experience, at the cost of heavy load to wireless networks. Except for further improving viewing experience, view synthesis can create multicast opportunities for efficient transmission of MVVs in multiuser wireless networks, which has not been recognized in existing literature. In this paper, we would like to exploit view synthesis-enabled multicast opportunities for energy-efficient MVV transmission in a multiuser wireless network. Specifically, we first establish a mathematical model to characterize the impact of view synthesis on multicast opportunities and energy consumption. Then, we consider the optimization of view selection, transmission time and power allocation to minimize the weighted sum energy consumption for view transmission and synthesis, which is a challenging mixed discrete-continuous optimization problem. We propose an algorithm to obtain an optimal solution with reduced computational complexity by exploiting optimality properties. To further reduce computational complexity, we also propose two low-complexity algorithms to obtain two suboptimal solutions, based on continuous relaxation and Difference of Convex (DC) programming, respectively. Finally, numerical results demonstrate the advantage of the proposed solutions.

Emotion is a unique feature of human beings. Recent research in emotion sensing has already revealed its potentials in enhancing our living experiences through applications like emotion companion and autism treatment. However, existing solutions exploring audiovisual clues or psychological sensors have several critical concerns such as the availability (specialized hardware), reliability (illumination and line-of-sight constraints) and privacy issues (being watched). To this end, we present EmoSense, a first-of-its-kind WiFi-based emotion sensing system leveraging the temporal and frequency fingerprints on the wireless channel data induced by the physical expression of emotion. EmoSense has been prototyped with off- the-shelf WiFi devices and evaluated by comparing with the main-stream sensor-based approach in real environments. Experimental results demonstrate its effectiveness and robustness. Considering that EmoSense is compatible with existing WiFi infrastructures, it constitutes a low-cost yet promising solution for emotion sensing.

Video caching is one of the most important research issues in Content-Centric Network (CCN) and greatly affects its overall performance. The computational complexity of state-of-the-art optimal caching schemes is high, due to the arbitrary network topologies. In this paper, the popularity-aware video caching in topology-known CCN is studied. The complex arbitrary network typology is mapped into a virtual cascade network topology and a caching scheme is designed in accordance with the transformed virtual network rather than the original network. This scheme is proved optimal, and is with polynomial computational complexity. Simulations are conducted and the results show that the proposed scheme outperforms the existing schemes.

Sleep is a major event of our daily lives. Its quality constitutes a critical indicator of people's health conditions, both mentally and physically. Existing sleep monitoring systems either are obstructive to use or fail to provide adequate coverage. To overcome these shortages, we propose Sleepy, an adaptive and noninvasive sleep monitoring system leveraging channel response in the commercial WiFi devices. Sleepy needs no calibrations or target-dependent training to recognize posture changes during sleep. To achieve that, a Gaussian Mixture Model (GMM) based foreground extraction method has been designed to adaptively distinguish motions like rollovers (foreground) from background (stationary postures). We prototype Sleepy and evaluate it in two real environments. In the short-term controlled experiments, Sleepy achieves 95.04% detection accuracy and 4.07% false negative rate. In the 60-minute real sleep studies, Sleepy demonstrates strong stability. Considering that Sleepy is compatible with existing WiFi infrastructures, it constitutes a low-cost yet promising solution for sleep monitoring.

In this paper, we consider multi-quality multicast beamforming of a video stream from a multi-antenna base station to multiple single-antenna users receiving different qualities of the same video stream, via scalable video coding (SVC). Leveraging the layered structure of SVC and exploiting superposition coding as well as successive interference cancellation, we propose a layer-based multi-quality multicast beamforming scheme. To reduce the computational complexity, we also propose a quality-based multi-quality multicast beamforming scheme, which further utilizes the layered structure of SVC and quality information of all users. Under each scheme, for given quality requirements of all users, we formulate the corresponding optimal beamforming design as a non-convex power minimization problem, and obtain a globally optimal solution for a class of special cases as well as a locally optimal solution for the general case. Then, we show that the minimum total transmission power of the layer-based power minimization problem is the same as that of the quality-based power minimization problem, although the latter incurs a lower computational complexity. Next, we consider the optimal joint layer selection and quality-based multi-quality multicast beamforming design to maximize the total utility representing the satisfaction with the received video quality for all users under a given maximum transmission power budget, which is NP-hard in general. Based on the optimal solution of the quality-based power minimization problem, we develop a greedy algorithm to obtain a near optimal solution. Finally, numerical results show that the proposed solutions achieve better performance than existing solutions.

IEEE 802.11ad, the standard specification for millimeter-wave wireless networks, enables high-speed wireless transmission by using the 60GHz frequency. However, small cell size due to the nature of millimeter-wave wireless network leads high communication overhead caused by frequent handovers. Fast Initial Link Setup (FILS), which is standardized as IEEE 802.11ai, is one option to mitigate the overhead caused by frequent handovers. FILS can shorten the initial link setup time and hence a longer time can be obtained for data communication. However, there is no study of FILS' effects in IEEE 802.11ad wireless network. In this paper, we investigate the effects of FILS in IEEE 802.11ad wireless networks. We conducted simulation of the link setup procedure of FILS and the popular initial link setup scheme, WPA2-Enterprise, in IEEE 802.11ad wireless networks. The simulation results show that FILS can drastically shorten the initial link setups time and reduce the failure ratio of initial link setup when multiple link setups are made many stations simultaneously.

Software-defined networking (SDN) enables network subscribers to negotiate QoS parameters in a on-demand basis. On the other hand, peak-time congestion accompanying the fast-growing traffic in recent years forces Internet service provider (ISP) to put forward a new pricing scheme by taking into account when a user uses Internet in addition to how much a user uses Internet. In this paper, we study the payoff optimization problem of ISP and network subscribers in SDN-enabled networks. A self-interested network subscriber always tries to obtain network resources as much as possible even if the network is congested; on the other hand, rational ISP tends to charge a higher price without providing subscribers guaranteed Quality of Service (QoS). A Stackelberg game is hence constructed to analyze the competitive interactions between ISP and home network subscribers. Specifically, ISP decides its pricing strategy for each time slot by solving a payoff optimization problem. Given the pricing strategy, network subscribers then decide the bandwidth to be reserved in a on-demand basis aiming to optimize their own payoff as well. We analyze the Nash equilibrium solution of the game. Simulation results confirm that the proposed pricing scheme can largely improve the payoff of network subscribers and ISP, compared to the usage-based pricing (UBP) scheme. Furthermore, the portion of surplus obtained by ISP increases with the increase of traffic load.

The past few years have witnessed a huge acceleration in global Internet traffic. Users' demand for contents is also rising accordingly. Therefore, content providers (CPs) that provide contents for users get high revenue from the traffic growth. There are generally two ways for CPs to get revenue: (i) charge users for the contents they view or download; (ii) get revenue from advertisers. On the other hand, Internet service providers (ISPs) are investing in network infrastructure to provide better quality of service (QoS), but they do not benefit directly from the content traffic. One option for ISPs to compensate their investment cost is sharing CPs' revenue by side payment from CPs to ISPs. Then ISPs will be motivated to keep on investing in developing new network technology and enlarging the capacity to improve QoS. However, it is important to evaluate how each player is affected by this kind of side payment. Our previous work has studied this problem by assuming that CPs charged users for the contents they view or download, in this paper it is considered that CP does not directly charge end users, but charges advertisers for revenue. Stackelberg game is utilized to study the interactions among ISP, CP, end users and advertisers. A unique Nash equilibrium is established and numerical analysis has validated our theoretic results. It shows that side payment from CP to ISP impairs the CP's investment of contents, and ISP can benefit from charging CP, while CP's payoff is impaired.

In this paper, we consider the problem of spectrum sharing in a Cognitive Radio Network (CRN) with spectrum holder, two secondary operators and secondary users (SUs). In the system model under consideration, the spectrum allocated to the two secondary operators can be shared by SUs, which means that secondary operators buy spectrum from spectrum holder and then sell spectrum access service to SUs. We model the relationship between secondary operators and SUs as a two-stage stackelberg game, where secondary operators make spectrum channel quality and price decisions in the first stage, and then the SUs make their spectrum demands decisions. The backward induction method is employed to solve the stackelberg game. Numerical results are performed to evaluate our analysis.

Nowadays, mobile network operators (MNOs) are trying to deploy wireless local area network (LAN) to offload mobile data from their cellular networks to complementary wireless LAN for congestion relief and cost savings. However, these network-centric methods do not take into consideration mobile user's (MU's) interests of monetary cost, energy consumption, and applications' deadlines. How the MU decides whether to offload their traffic to a complementary wireless LAN is non-trivial and important issue. Previous studies assume that MNO adopts usage-based pricing for mobile data, which only cares about how much a MU consumes data but not when a MU consumes data. In this paper, we study the MU's policy to minimize his monetary cost and energy consumption under time-dependent pricing (TDP). We formulate MU's wireless LAN offloading problem as a finite-horizon discrete-time Markov decision process (MDP) and establish an optimal policy by a dynamic programming based algorithm. Extensive simulations are conducted to validate our proposed offloading algorithm.

In order to improve the quality of service (QoS) for mobile users (MUs) and save investment cost for deploying new cellular base station, mobile network operators (MNOs) are deploying wireless local area network (LAN) access points (APs) to offload MU's traffic from cellular network to wireless LAN. However, offloading too much traffic from cellular network may impair MNO's profit since the cellular network price is higher than that of wireless LAN, whose price is low or even zero. Therefore, how to deploy wireless LAN APs to offload traffic without impairing MNO's profit is a critical problem for MNOs. As far as the authors understand, existing studies about deployment of wireless LAN APs do not consider MNO's profit and are usually in a heuristic manner. In this paper, we study the location-based advertising (LBA) leveraged wireless LAN deployment, where MNO may also collect revenue by selling LBA service in different locations to advertisers. We formulate MNO's profit maximization problem by considering different MU's demand in different locations, wireless LAN price for MUs, and revenue from LBA service. Extensive simulations are conducted to validate our analytical results.

The ongoing evolution of personal mobile devices capabilities and wireless technologies result in a huge growth of traffic on mobile networks (3G/4G). One of the most promising approaches to handle this data crisis is to offload the fast growing traffic onto femtocell networks. Since both the 3G/4G macrocell and femtocells operate on the same licensed spectrum, the cross-tier interference should be well managed. In this paper, we propose a utility-based transmission power allocation policy for the uplink transmission in femtocell networks. Our main motivation is to design the transmission power allocation policy aiming at optimizing the joint utility of femtocell users (FUs) subject to a interference temperature constraint at the macrocell base station (MBS) side. We provide a novel floating-ceiling water-filling (FCWF) algorithm with little computational overhead to obtain the optimal solution for the joint utility optimization problem. Numerical results confirm that the joint utility and average SINR can be significant improved with the proposed method.

In this paper, we consider multi-quality multicast of a video stream from a multi-antenna base station (BS) to multiple single-antenna users requiring the video at different quality levels, using scalable video coding (SVC). Leveraging the layered structure of SVC and exploiting superposition coding (SC) as well as successive interference cancelation (SIC), we propose a power-efficient layer-based multi- quality multicast beamforming scheme. To reduce the computational complexity, we also propose a power- efficient quality-based multi-quality multicast beamforming scheme, which further utilizes the layered structure of SVC and quality requirements of all users. Under each scheme, for given quality requirements of all users, we formulate the corresponding beamforming design as a non-convex power minimization problem, and obtain a globally optimal solution for a class of special cases as well as a locally optimal solution for the general case. Then, we show that the minimum total transmission power of the quality-based optimization problem is the same as that of the layer-based optimization problem, although the former requires a lower computational complexity. Finally, numerical results show that the proposed solutions achieve better performance than existing solutions.

Designing mobile edge computing (MEC) systems by jointly optimizing communication and computation resources, which can help increase mobile batteries' lifetime and improve quality of experience for computation-intensive and latency-sensitive applications, has received significant interest. In this paper, we consider energy-efficient resource allocation schemes for a multi-user mobile edge computing system with inelastic computation tasks and non-negligible task execution durations. First, we establish a mathematical model to characterize the offloading of a computation task from a mobile to the base station (BS) equipped with MEC servers. This computation-offloading model consists of three stages, i.e., task uploading, task executing, and computation result downloading, and allows parallel transmissions and executions for different tasks. Then, we formulate the weighted sum energy consumption minimization problem to optimally allocate the task operation sequence, the uploading and downloading time durations as well as the starting times for uploading, executing and downloading, which is a challenging mixed discrete- continuous optimization problem and is NP-hard in general. We propose a method to obtain an optimal solution and develop a low-complexity algorithm to obtain a suboptimal solution, by connecting the optimization problem to a three-stage flow-shop scheduling problem and utilizing Johnson's algorithm as well as convex optimization techniques. Finally, numerical results show that the proposed sub-optimal solution outperforms existing comparison schemes.

Edge-caching, which only caches the contents near the users, has low implementation cost and performs comparably with the conventional on-path caching schemes in \textit{Information-Centric Networking} (ICN). However, the independent edge-caching can not capture the content popularity dynamics accurately since each cache node only has local content request information. In addition, the caching information of the cache nodes within the same neighborhood is not efficiently utilized. To solve these issues, we propose a coordinated edge-caching system, where the cache nodes within the same neighborhood can help each other to improve the caching performance. We design a caching decision method for each node, and the decision method takes caching information of edge nodes within the same neighborhood into consideration. We theoretically illustrate the effectiveness of the proposed scheme in typical network scenarios. Simulations are conducted on the real-world network topologies under both stationary and temporal popularity workloads, and the results show the performance of our proposed scheme is superior to the comparison schemes.

Virtual reality (VR) video provides an immersive 360 viewing experience to a user wearing a head-mounted display: as the user rotates his head, correspondingly different fields-of-view (FoV) of the 360 video are rendered for observation. Transmitting the entire 360 video in high quality over bandwidth-constrained networks from server to client for real-time playback is challenging. In this paper we propose a multi-stream switching framework for VR video streaming: the server preencodes a set of VR video streams covering different view ranges that account for server-client round trip time (RTT) delay, and during streaming the server transmits and switches streams according to a user's detected head rotation angle. For a given RTT, we formulate an optimization to seek multiple VR streams of different view ranges and the head-angle-to-stream mapping function simultaneously, in order to minimize the expected distortion subject to bandwidth and storage constraints. We propose an alternating algorithm that, at each iteration, computes the optimal streams while keeping the mapping function fixed and vice versa. Experiments show that for the same bandwidth, our multi-stream switching scheme outperforms a non-switching single-stream approach by up to 2.9dB in PSNR.

In this paper, we target the resource allocation and layer selection problem for the realtime video streaming over highway scenario, by employing Scalable Video Coding (SVC) for the video contents. Especially, we take the freeze-free playback as one of the constraint as well. Since the formulated resource allocation and SVC layer selection problem is NP-hard, we propose the Resource Allocation and Layer Selection with Base layer guarantee (RALSB) algorithm to solve this problem in two phases: the Base layer Guarantee (BG) phase, and the Resource allocation and SVC layer selection (RS) phase. Simulation results show that the proposed RALSB can prevent/reduce the playback freeze in typical scenarios.

In this paper, we jointly consider communication, caching and computation in a multi-user cache-assisted mobile edge computing (MEC) system, consisting of one base station (BS) of caching and computing capabilities and multiple users with computation-intensive and latency-sensitive applications. We propose a joint caching and offloading mechanism which involves task uploading and executing for tasks with uncached computation results as well as computation result downloading for all tasks at the BS, and efficiently utilizes multi-user diversity and multicasting opportunities. Then, we formulate the average total energy minimization problem subject to the caching and deadline constraints to optimally allocate the storage resource at the BS for caching computation results as well as the uploading and downloading time durations. The problem is a challenging mixed discrete-continuous optimization problem. We show that strong duality holds, and obtain an optimal solution using a dual method. To reduce the computational complexity, we further propose a low-complexity suboptimal solution. Finally, numerical results show that the proposed suboptimal solution outperforms existing comparison schemes.

Disaster detection is an important research topic and draws great attentions from both industry and academia. In this paper, we study the hybrid landslide detection system, which utilizes the video surveillance camera and multiple kinds of sensors and can detect the landslide automatically. Edge processing is adopted in this hybrid system to fuse the sensor data based on the Dempster-Shafer (D-S) theory, i.e. utilizing multiple sensors' information to calculate the possibility of the landslide. Edge processing can make faster decisions than the control center, the results of the edge processing are then used to schedule the sensor's transmission frequency and video transmission under the network constraints in this system. The simulation results show that the proposed scheme outperforms the competing schemes in typical network scenarios.

Human activity recognition based on wireless signals emerges as a research hotspot recently. Though tremendous efforts have been devoted and significant progresses have been achieved, one fundamental issue still remains open, i.e., theoretical modeling between signal dynamics and human activities. This paper fills in the blank by addressing several theoretical issues and providing insightful mathematical analysis including a signal-activity model. To validate such analysis, a prototype system has been built, where a series of real-world experiments has been conducted. Empirical results have justified our theoretical findings. Moreover, important hands-on experiences on the system implementation and parameter settings have been offered.

Location estimation in Wi-Fi environment has gained considerable attention over the past years, and the Cramer-Rao Lower Bound (CRLB) can be used to evaluate the performance of the localization system. In this paper, we analyze the CRLB of Wi- Fi indoor localization using fingerprint and assistant nodes. This localization method combines received signal strength (RSS) and Time of Arrival (TOA) into together, and constructs a fixed spatial model with several assistant nodes to improve localization performance. There are two purposes of the CRLB analysis framework proposed in this paper. Firstly, the expression of lower bound on location estimation error can help in designing and refining efficient localization algorithm and parameters. Secondly, the error trends can provide suggestions for a positioning system design and deployment. Furthermore, detailed analysis as well as experimental results are both presented in this paper.

Content Centric Network (CCN) has become a heated research topic recently, as it is proposed as an alternative of the future network. The routers in CCN have the caching abilities and the caching strategies affect the system performance greatly. Each content in CCN is associated with a popularity, which is determined by the corresponding requested times. Popularity-aware caching scheme caches the popular content close to users and can lead to better caching performance in terms of smaller average transmission hops traveled. Content popularity significantly affects the overall system performance, and the content size is not considered during the content level popularity (i.e. item popularity) calculation. In this paper, we study the impact of the item popularity and chunk popularity in CCN, where the chunk popularity is the normalized item popularity considering the content size. Extensive simulations are conducted and the simulation results show the advantages and disadvantages of each scheme. A new popularity calculation method is proposed to perform the tradeoff between the item popularity and chunk popularity.

With rapid increases in demand for mobile data, mobile network operators are trying to expand wireless network capacity by deploying WiFi hotspots to offload their mobile traffic. However, these network-centric methods usually do not fulfill interests of mobile users (MUs). MUs consider many problems to decide whether to offload their traffic to a complementary WiFi network. In this paper, we study the WiFi offloading problem from MU's perspective by considering delay-tolerance of traffic, monetary cost, energy consumption as well as the availability of MU's mobility pattern. We first formulate the WiFi offloading problem as a finite-horizon discrete-time Markov decision process (FDTMDP) with known MU's mobility pattern and propose a dynamic programming based offloading algorithm. Since MU's mobility pattern may not be known in advance, we then propose a reinforcement learning based offloading algorithm, which can work well with unknown MU's mobility pattern. Extensive simulations are conducted to validate our proposed offloading algorithms.

Broadcasting of real-time video, especially accidents relevant, plays an important role in Vehicle Ad-hoc Networks (VANETs). Multi-view video enables the perception of the targeted scene from multiple angles. By subscribing the real-time multi-view video broadcast, drivers can obtain better knowledge of the highway traffic and road conditions. However, compared with the traditional single view video transmission, the multiview video transmission is more challenging, because of the VANETs' channel variation and a much larger network data rate requirement. The inherent problem thus becomes how to utilize the limited network bandwidth to stream the real-time multi-view video. As far as the authors understand, this problem has not yet been solved in any formal way. This paper focuses on the realtime multi-view broadcast over VANETs and formulates it into an optimization problem with the objective to maximize the average video quality received by users. By exploring the VANET channel characteristic, the correlations inside the multi-view and video popularity, an algorithm named as RMV is proposed to solve the optimization problem. Extensive simulations are conducted and simulation results show that the proposed scheme can outperform the comparison schemes in typical VANET scenarios to a great extent.

Heterogeneous networks (HetNets) are intended to offer wide area coverage and high data rate transmission by deploying small cells besides macrocells. Device-to-device (D2D) communication as an underlay of cellular network enriches local service and offloads base station. In this paper, we target the video transmission demanded by picocell edge users (PEUEs), who suffer from low quality channel due to the inter-cell interference from macrocell and long physical distance from picocell. Moreover, the wireless channels are burst-loss prone for upper layer applications such as video on demand (VoD), which makes the traditional channel coding such as forward error correction (FEC) insufficient. In this paper, we address these issues and propose a cooperative video transmission scheme to improve PEUEs' received video quality by constructing two transmission paths from picocell to each PEUE. The two transmission paths are the direct transmission from pico-eNB (i.e., base station) to PEUE and a relay-assisted path by means of D2D communication for frame recovery, respectively. Reference frame selection and unequal error protection are adopted to further improve the overall performance. Extensive simulations are conducted and results demonstrate that the proposed scheme outperforms state-of-the-art scheme in Config.4b scenarios defined by 3GPP.

Mobile video traffic is exploding and it is particularly challenging to stream video when high density of users are "on the move", e.g., in public transport systems. It becomes increasingly problematic as video traffic is predicted to account for more than 80% of Internet traffic by 2019. This will be exacerbated by factors such as cellular network coverage issues and unstable network throughput due to high speed mobility. By exploiting the predictable public transport mobility patterns, spatio-temporal correlation of user interests and users' video viewing behaviors, we proposed TransFetch which uses intelligent caching on-board the public transport vehicles as well as a novel video chunk placement algorithm. We show through extensive simulations, that TransFetch reduces the system cellular data usage by up to 45% and improves the quality of video streaming by up to 35%. Finally, we demonstrate the practical feasibility of TransFetch by implementing caching units on a Raspberry-Pi and a mobile app on an Android device.

Free viewpoint video (FVV) offers compelling interactive experience by allowing users to switch to any viewing angle at any time. An FVV is composed of a large number of camera-captured anchor views, with virtual views (not captured by any camera) rendered from their nearby anchors using techniques such as depth-image-based rendering (DIBR). We consider a group of wireless users who may interact with an FVV by independently switching views. We study a novel live FVV streaming network where each user pulls a subset of anchors from the server via a primary channel. To enhance anchor availability at each user, a user generates network-coded (NC) packets using some of its anchors and broadcasts them to its direct neighbors via a secondary channel. Given limited primary and secondary channel bandwidths at the devices, we seek to maximize the received video quality (i.e., minimize distortion) by jointly optimizing the set of anchors each device pulls and the anchor combination to generate NC packets. To our best knowledge, this is among the first body of work addressing such joint optimization problem for wireless live FVV streaming with NC-based collaboration. We first formulate the problem and show that it is NP-hard. We then propose a scalable and effective algorithm called PAFV (Peer-Assisted Freeview Video). In PAFV, each node collaboratively and distributedly decides on the anchors to pull and NC packets to share so as to minimize video distortion in its neighborhood. Extensive simulation studies show that PAFV outperforms other algorithms, achieving substantially lower video distortion (often by more than 20-50%) with significantly less redundancy (by as much as 70%). Our Android-based video experiment further confirms the effectiveness of PAFV over comparison schemes.

Network traffic load usually differs significantly at different times of a day due to users' different time preference. Network congestion may happen in traffic peak times. In order to prevent this from happening, network service providers (NSPs) can either over-provision capacity for demand at peak times of the day, or use dynamic time-dependent pricing (TDP) scheme to reduce the demand at traffic peak times. Since over-provisioning network capacity is costly, many researchers have proposed TDP schemes to control congestion as well as to improve the revenue of NSPs. To the best of our knowledge, all these studies consider only the monopoly NSP case. In our previous work, the duopoly and oligopoly NSP cases have been studied. NSPs try to maximize their overall revenue by setting time-dependent prices, while users choose NSPs by considering their own time preference, congestion statuses in the networks and the prices set by the NSPs. One assumption that has been made is that Quality of Service (QoS) function of each NSP is linear, which means that the level of QoS degradation is proportional to the number of users in the network. However, in reality, the level of QoS may degrade rapidly after a certain point, which is not reflected through linear QoS functions. Therefore, concave QoS function is a better choice. In this paper, the case of concave QoS function is considered. TDP is evaluated under different QoS functions. The results shows that TDP is also effective under concave QoS functions.

Dynamic spectrum reallocation, under which the spectrum owners temporarily share the underutilized spectrum to secondary users for economic profit, is an important approach to improve the spectrum utilization ratio. Auction is believed to be a natural marketing tool to incentivize the spectrum owners, and thus redistribute the idle spectrum efficiently. Extensive researches have been done in the problem of truthful spectrum auction, in which the bidders bid based on their true valuations of the spectrum. The true valuation of the individual bidder, however, is a private information which should be protected against exposure. In this paper, we propose a privacy preserving truthful spectrum auction scheme by utilizing homomorphic encryption. The proposed scheme reveals the group bids but hides the users' bids even from the auctioneer. The evaluation results show that the proposed scheme achieves good spectrum utilization efficiency with low communication and computation overheads.

WiFi-Direct, a Wi-Fi standard, enables devices to connect easily with each other without requiring a wireless access point and communicate at typical WiFi speeds for file transfer, Internet connectivity, etc. It is widely used in many applications such as the traffic local sharing. The loss model of WiFi-direct link can facilitate the theoretical analysis when designing or optimizing the systems hence it is an important issue to be investigated. But as far as we understand, no formal work has been done to analyse the WiFi-Direct channels. In this paper, we set up the experiments connecting two mobile devices using WiFi-Direct and analyzed the performance of the loss models in literature. A new model based on Gilbert-Elliot model was proposed thereafter and evaluated with likelihood criterion. The new model turned out to outperform others in the evaluation.

Video is playing a more and more important role in future Vehicular Ad-hoc Network (VANET) communication. It is a feasible medium for information sharing and entertainment (infotainment) with its high capacity, consistency and influence on human beings. This paper introduces the SVC coding scheme to VANET video streaming. We propose an Optimal Scheduling Algorithm (OSA) for video streaming in highway VANET scenarios using scalable video coding (SVC). We conduct extensive simulations to evaluate the performance of OSA. Simulation results show that OSA outperforms all the competing schemes over variant density and velocity highway VANET.

Heterogeneous networks (HetNets) are intended to offer wide area coverage and high data rate transmission by deploying small cells besides macrocells. One way to improve the system throughput is intercell interference coordination. The coordination methods in literature use the system throughput as the only selection criteria without considering each user's data rate requirement and investigate the intercell interference only during the period when small cell's edge users are served. In this paper, we propose an algorithm to maximize the users' data rate satisfaction ratio in HetNet leveraging on the two existing intercell interference coordination schemes ABS and CoMP. Intensive simulations are conducted and the results demonstrate that our proposed scheme achieves considerable gains over competing schemes in terms of the data rate satisfaction ratio and the system capacity in Config.4b scenarios defined by 3GPP.

The current coding standard employs differential coding to reduce the coding rate. Decoding error may propagate in the following frames after a loss-unrecoverable frame. Since most of the current electronic devices are implemented with multiple interfaces, such as the 3G and WiFi, one way to solve the error propagation problem is to use cooperative strategies, which leverage on the ‘uncorrelatedness’ of the clients' channels (different channels may experience different channel losses). The cooperative strategies helping to repair the primary network's (base station to client) losses via the neighboring clients' packets sharing (client to client) through the second network interface and optimally allocating the modulation and coding schemes to the limited network resource can improve the clients' received quality massively. The inherent problem is how to solve the resource allocation problem with the cooperative strategies. In this paper, we jointly consider the resource allocation and the cooperative repair for the video streaming. We formulate the problem into the optimization problem, i.e. maximizing the clients' received video quality, and apply the structured network coding to further improve the overall performance. Simulation results show that the proposed approach outperforms the other competing schemes by at least 1.5dB in term of the received video quality in typical network scenarios.

In interactive multiview video streaming (IMVS), a user observes one view at a time, but can periodically switch to a desired neighboring captured view as the video is played back in time. Previous IMVS works focus on efficient compression techniques that facilitate interactive view switching. In this paper, in addition to the loss-resilient aspect during network streaming we address how to design efficient coding tools and optimize frame structure for transmission to facilitate view switching and contain error propagation in differentially coded video due to packet losses. We first design a new unified distributed source coding (uDSC) frame-a new coding tool that simultaneously offers view switching and loss-resilient capabilities-for periodic insertion into the multiview frame structure. After inserting uDSC-frames into the coding structure, we schedule packets for network transmission in a rate-distortion optimal manner for both wireless multicast and wired unicast streaming scenarios. For wireless multicast over a Gilbert-Elliott loss model, frames in a group of pictures are packetized and reordered, so that uDSC frames are correctly decoded with high probability, mitigating error propagation. For wired unicast, we use a Markov decision process to optimize packet transmission to minimize expected distortion given a bandwidth constraint. Experimental results show that systems that insert uDSC frames and optimize packet transmission can outperform other competing coding schemes by up to 2.8 and 11.6 dB in wireless multicast and wired unicast streaming scenarios, respectively.

By transmitting texture and depth videos from two adjacent captured viewpoints, a client can synthesize via depth-image-based rendering (DIBR) any intermediate virtual view of the scene, determined by the dynamic movement of the client's head. In so doing, depth perception of the 3D scene will be created through motion parallax. Due to the stringent playback deadline of interactive free viewpoint video, burst packet losses in the texture and depth video streams caused by transmission over unreliable channels are difficult to overcome and can severely degrade the synthesized view quality at the client. We propose a multiple description coding (MDC) of free viewpoint video in texture-plus-depth format that will be transmitted on two disjoint network paths. Specifically, we encode even frames of the left view and odd frames of the right view separately as one description and transmit it on path one. Similarly, we encode odd frames of the left view and even frames of the right view as the second description and transmit it on path two. Appropriate quantization parameters (QP) are selected for each description, such that its data rate matches optimally the available transmission bandwidth on each of the two paths. If the receiver receives one description but not the other due to burst loss on one of the paths, it can still partially reconstruct the missing frames in the loss-corrupted description using a computationally efficient DIBR-based recovery scheme that we design. Extensive experimental results show that our MDC streaming system can outperform the traditional single-path single-description transmission scheme by up to 7dB in Peak Signal-to-Noise Ratio (PSNR) of the synthesized intermediate view at the receiving client.

Because of differential coding used in standard video compression algorithms to exploit temporal correlation in adjacent frames for coding gain a frame lost in network will cause error propagation in subsequent frames at the decoder Previously proposed distributed source coding (DSC) frames can be periodically inserted to halt this error propagation by overcoming the uncertainty at encoder of which frames will be correctly received at decoder without resorting to large intra-coded I-frames In the case of interactive multiview video streaming (IMVS) where a user watches one of M available captured views at a time but can periodically select and switch to a neighboring view the encoder must encode multiview video to enable this view-switching interactivity without knowing the exact view trajectories taken by viewers at stream time In this paper we propose a unified DSC frame construction for IMVS so that the encoder can overcome both types of uncertainty in a coding-efficient manner; ie halt error propagation in differentially coded multiview video and facilitate periodic interactive view-switching at the same time Having the additional unified DSC frames we design a multiview frame structure to maximize the expected number of correctly decoded frames at decoder for a given bandwidth constraint We develop a fast algorithm to find locally optimal structure parameters and packetization and packet reordering strategies for transmission Experimental results show that our optimized frame structures using unified DSC frames outperform naïve structures using I- and P-frames only by up to 49% in fraction of correctly decoded frames under typical network condition.

Video multicast over broadband wireless networks suffers from packet losses induced by fading wireless channels and user heterogeneity in channel conditions within a multicast group. A promising solution to these problems is the use of layered hybrid FEC/ARQ for scalable video multicast. However, how to allocate the radio resources to multiple video layers and how to address the cross-layer combination of application layer hybrid FEC/ARQ and physical layer MCS (modulation and coding schemes) for each video layer, is not a trivial issue. We prove that this problem is NP-hard and propose an optimal Error-resilient Video Multicast (ERVM) framework in infrastructure-based broadband wireless networks. To avoid user heterogeneity and feedback implosion, we use a weighted designated user group to send light-weight feedback messages. The ERVM algorithm is based on the dynamic programming method with a pseudo-polynomial run time, and can get the optimal transmission configuration to maximize the expected utility for the designated user group, which is a probabilistic function of the received video rate. Simulation results show that our ERVM algorithm offers significant improvements over the conventional single-layer FEC/ARQ scheme and the layered FEC scheme. Furthermore, our weighted designated user group with light-weight and accurate feedbacks is better than other user feedback schemes.

Video multicast over Wireless Wide Area Networks (WWAN) is difficult because of unavoidable packet losses and impracticality of retransmission on a per packet, per client basis, due to the known NAK implosion problem. Recent approach exploits clients' cooperation for packet recovery, so that a peer group's received WWAN packets are shared using a secondary network like Wireless Local Area Network (WLAN). For multiview video multicast, where a client can switch views interactively by subscribing to different WWAN multicast channels streaming different views, two new difficulties arise. First, system must provide timely view-switching mechanism, so that client can switch to a desired view quickly for correct decoding and display. Second, it is difficult for system to leverage neighboring peers for cooperative loss recovery, since neighbors are more likely to be subscribing to different views than a loss-stricken peer. In this paper, we use Distributed Source Coding (DSC), a new compression tool in video coding, to solve both problems. Each DSC frame is encoded with a set of predictor frames, and correct decoding only requires one of the predictors in the set to be available at decoder. Periodic insertion of DSC frames into video streams then enables a peer to switch from view v to v' at the DSC frame boundary, assuming DSC frame of view v' was encoded using a frame in view v as one predictor. For the same assumption, a neighbor watching view v can help a peer watching view v' evade error propagation resulting from earlier losses and resume decoding at the DSC boundary. Experiments show that optimized usage of DSC frames in a coding structure, where unequal error protection is enabled to decrease the probability of decoding failure earlier in a group of pictures, outperforms a structure using I-frames instead for view switching by up to 11 dB in video quality in typical WWAN network loss environment.

Error resilient video broadcast over Wireless Wide Area Networks (WWAN) remains difficult due to unavoidable packet losses (a result of the underlying unreliable and time-varying transmission medium) and unavailability of per-packet, per-user retransmissions (stemming from the well-known NAK implosion problem). Previous cooperative solutions for multi-homed devices listening to the same video broadcast call for local recovery via packet sharing: assuming peers are physically located more than one transmission wavelength apart, channels to the streaming source are statistically independent, and peers can exchange different subsets of received packets with neighbors via a secondary network like ad hoc Wireless Local Area Net work (WLAN) to alleviate individual WWAN packet losses. While it is known that using structured network coding (SNC) to encode received packets before peer exchange can further improve packet repair performance, the decisions of who should send repair packets encoded in what SNC types at available transmission opportunities were not optimized in any formal way. In this paper, we propose a distributed decision making strategy based on Markov decision process (MDP), so that each peer can make locally optimal transmission decisions based on observations eavesdropped on the WLAN channel. Our proposed MDP is both computationally scalable and peer-adaptive, so that state transition probabilities in MDP can be appropriately estimated based on observed aggregate behavior of other peers. Experiments show that decisions made using our proposed MDP outperformed decisions made by a random scheme by at least 4dB in PSNR in received video quality.

Error resilient video multicast over Wireless Wide Area Networks (WWAN) is difficult because of unavoidable packet losses and impracticality of retransmission on a per packet, per client basis due to the well-known NAK implosion problem. In response, Cooperative Peer-to-peer Repair (CPR) calls for multi-homed devices listening to the same video multicast to locally exchange received WWAN packets via a secondary network like ad hoc Wireless Local Area Network (WLAN) to alleviate individual WWAN packet losses. When videos of the interested 3D scene are captured by multiple closely spaced cameras, each video can be encoded into a separate video stream and transmitted on its own WWAN multicast channel. Clients can then switch observation viewpoints periodically by simply re-subscribing to different WWAN multicast channels- a scenario called interactive multiview video streaming (IMVS). IMVS complicates the CPR WWAN loss recovery process, however, since neighbors of a loss-stricken peer can now be watching different views. In this paper, we optimize the decision process for individual peers during CPR for recovery of multiview video content in IMVS. In particular, for each available transmission opportunity, a peer decides-using Markov decision process as a mathematical formalism-whether to transmit, and if so, how the CPR packet should be encoded using structured network coding (SNC). A loss-stricken peer can then either recover using received CPR packets of the same view, or using packets of two adjacent views and subsequent view interpolation via image-based rendering. Experiments show that decisions made using our proposed MDP outperforms decisions made by a random scheme by at least 1.8dB in PSNR in received video quality in typical network scenario.