In multi-chip IGBT power modules, package-level failures typically manifest first as localized distortions in the copper baseplate temperature field before evolving into catastrophic faults. However, existing Power Internet of Things (Power IoT) monitoring approaches mainly rely on single-point indicators, such as on-state voltage drop or case temperature, making them inadequate for capturing spatially nonuniform thermal anomalies under sparse sensing. This paper proposes a terminal–edge–cloud collaborative method for parallel multi-module temperature-field reconstruction in Power IoT, which maps sparse thermocouple measurements to a high-resolution temperature field while meeting real-time constraints. At the terminal layer, the thermocouple array layout is optimized using a condition-number minimization criterion to maximize system observability. At the edge layer, a physics-constrained conditional generative adversarial network (PC-cGAN) is deployed on an MPSoC platform, and a multi-objective particle swarm optimization algorithm is used to automatically search network architectures and hyperparameters under resource constraints, thereby balancing reconstruction accuracy and inference latency. Experimental results demonstrate that a single edge node can monitor 4–6 power modules in parallel, with an inference latency of 11.8 ms for four-module parallel processing, achieving a 3.1× efficiency improvement over serial architectures. Using 12 sparse measurements, the proposed method achieves a root mean square error of 1.89°C, a mean absolute error of 1.52°C, and a hotspot deviation of 2.34°C; compared with CNN baselines, these metrics improve by 29.5%, 29.3%, and 32.2%, respectively, while reducing communication bandwidth by 98% relative to cloud-centric approaches. The proposed method provides an engineering-ready solution for scalable, real-time thermal-state monitoring of power-module arrays in converter systems.

Tracking maneuvering targets, such as connected and automated vehicles, requires modeling their movements with pre-defined kinematic models. However, sudden and unpredictable maneuvers often lead to model mismatch, resulting in significant peak tracking errors. To address this problem, we propose a maneuver detection-aided deep learning multiple model filter (MD-DL-MM) technique for target tracking and state estimation, designed to suppress peak errors and improve tracking performance. The core innovation of the MD-DL-MM technique is the integration of a self-attention-based discrimination network, which dynamically determines the weights of the target’s motion models. To consider the potential impact of a specific kinematic models on the state estimation accuracy, a statistical hypothesis testing-based method is introduced to evaluate the validity of kinematic models. This metric system-atically examines the suitability of the motion model, ensuring that the most appropriate model is selected and applied at each stage of the tracking process. On that basis, two distinct state estimation methods are designed. Specifically, when the kinematic model is more appropriate and the target exhibits non-maneuvering, state estimates are obtained using a recursive model-based Kalman filter (MB-KF), which provides optimal estimation with the minimum mean square error (MMSE). On the other hand, when the target exhibits sudden maneuvers or unpredictable maneuvers, a data-driven learning-based network is utilized to achieve high-precision state estimation. Extensive simulation results and real-world experimental data demonstrate that the proposed algorithm outperforms traditional methods such as the Singer, current statistical (CS), and the interactive multiple model (IMM) algorithm, as well as deep learning-based algorithms like DeepMTT and KalmanNet. The proposed algorithm achieves superior performance in terms of stability, computational efficiency, and tracking accuracy across diverse scenarios.

Lightweight Internet of Things (IoT) devices—microcontroller-class nodes with less than 512KB RAM, sub-100MHz clocks, and low-power radios (BLE, Zigbee, LoRa, NB-IoT)—are now widely deployed in settings where traditional security stacks are infeasible. This survey examines how Artificial Intelligence (AI) can harden such constrained platforms against device-, network-, and application-layer threats, including spoofing, routing manipulation, DDoS, malware, and Advanced Persistent Threats (APTs). We (i) formalize alightweight envelopethat bounds feasible defenses in terms of RAM, CPU, bandwidth, and energy; (ii) consolidate protocol-side risks across BLE, Zigbee, and LoRaWAN; and (iii) review deployable AI techniques through adeployment-firstlens that separates training (edge, cloud, federated learning) from on-device inference. Distinct from prior surveys, we provide resource-annotated comparisons that report accuracyalongsidemodel size, peak RAM, latency, and estimated energy per inference, showing how pruning, post-training quantization, distillation, and feature narrowing shift feasibility on MCU targets. Covered methods include compact classifiers (linear models, trees, SVM), quantized TinyCNN/TinyRNN and graph-based intrusion detection, reinforcement learning for adaptive rate limiting and channel selection, and privacy-preserving federated learning with update compression. We conclude with a pragmatic agenda—energy-adaptive inference, LPWAN-aware scheduling and federated learning, robustness to poisoning and evasion, and reproducible benchmarks that couple accuracy with size/latency/energy on real hardware—aimed at making AI-based security practical at scale for lightweight IoT deployments.

Automatic depression detection from facial videos is promising for IoT deployment but has long suffered from the black-box nature of deep models, which overlook how depression manifests on the face. This lack of interpretability leads to redundant feature learning, overly complex architectures, and consequently a trade-off between accuracy and deployability. We introduce a lightweight, interpretable system that explicitly models static–dynamic facial patterns, color channels, and regional textures. At its core is a Hybrid Static–Dynamic Model (HSDM) with detachable modules and identity decoupling, supported by two task-driven preprocessing steps (blue-channel suppression and 90° Gabor filtering). On AVEC2013/2014, our approach reduces mean absolute error by 10.1% on AVEC2014 while maintaining competitive results on AVEC2013. From a systems perspective, it achieves real-time inference on Jetson Nano (0.071M parameters, 0.21 GFLOPs, 17.69 ms latency, 56.54 samples/s throughput), outperforming larger SOTA models under identical conditions. The design facilitates on-device deployment and offers transparent decision paths through interpretable static–dynamic fusion, color synergy, and region-level analysis.

Industrial cyber-physical systems have been used as the foundational platform for ensuring resilient and robust communication in dynamic industrial environments. In the specific scenario of industrial control systems experiencing abrupt temperature disturbances and cyber infection dynamics, conventional methods relying on static thresholds and SIS models fail to deliver optimal stability. In this paper, we propose the real-time adaptive reconfiguration algorithm (RTARA), which integrates temperature-dependent SIR modeling, spectral graph theory, and an adaptive gossip framework to dynamically adjust communication protocols and trigger network reconfiguration when a critical threshold is breached. Our implementation employs a momentum-based gradient descent update enhanced with a recursive composite operator, achieving rapid convergence as evidenced by an MSE reduction from 0.045 to 0.012, a convergence rate improvement from 0.020 to 0.004, and a decrease in adaptation latency from 2.5 s to 0.5 s. The experimental results demonstrate that our approach significantly enhances network stability, with a stability index increasing from 0.70 to 0.95, thereby confirming its superior performance.

In this paper, we investigate the problem of predictive beamforming design for tracking vehicles in an integrated sensing and communication (ISAC)-based near-field vehicle-toinfrastructure (V2I) system. The waveform design in near-field scenarios requires the joint consideration of both range and angle dimensions, posing new challenges to conventional beamforming and tracking strategies. To address this issue, we propose a predictive beamforming framework leveraging a large language model (LLM)-based neural network (LNN), which exploits historical channel state information (CSI) to facilitate accurate future beamforming decisions. Cramér–Rao bounds (CRBs) for angle and distance estimation, along with the achievable sum-rate, are applied as key metrics to evaluate the sensing and communication performance of the V2I system, respectively. Capitalizing on the derived performance metrics, we formulate the optimization problems aiming either to maximize the sum-rate subject to CRB constraints or to minimize the CRB while ensuring a required communication rate, thereby accommodating different design requirements. Moreover, to effectively capture the stochastic nature of vehicle driving behavior, the performance metrics are further expressed in expectation form over the distribution of possible driving states. Consequently, a data-driven optimization approach based on the LNN is adopted to handle the resulting intractable analytical expressions, and the underlying LNN is trained with task-specific loss functions. During the training process, low-rank adaptation (LoRA) is incorporated to fine-tune the pre-trained LLM, which significantly reduces the number of trainable parameters. Simulation results demonstrate that the proposed framework accurately predicts future vehicle kinematic parameters and effectively optimizes the power allocation across transmit links. As a result, it achieves superior and robust performance in both communication and sensing tasks, highlighting its potential as a vital solution for next-generation near-field V2I systems.

Integrated sensing and communications (ISAC) systems promise dual use of spectrum and hardware for data transmission and environmental awareness. However, extending ISAC to satellite networks is challenged by high path loss, long delays, and the overhead of channel estimation. To address these challenges, we propose a channel-agnostic predictive beamforming framework for satellite ISAC (S-ISAC) within a crowdsourced bistatic architecture. Unlike conventional bistatic architectures that require a dedicated sensing receiver, our design aggregates echoes from multiple ground internet of things (IoT) devices (GIDs) in a crowdsourced manner to improve sensing performance without introducing any additional sensing equipment. We propose a model termed Historical Geometric-based LLM (HG-LLM) as a realization of the channel-agnostic predictive beamforming framework. HG-LLM learns to map historical geometric information (HGI) of the satellite, sensing target, and GIDs directly to future beamforming matrices, eliminating the need for channel state information (CSI). We propose two key modules in HG-LLM, namely, the Histogeometric Encoder, which transforms spatial-temporal data into LLM-compatible embeddings, and the TokenBeamformer, which translates the LLM outputs into optimized beamforming weights. Moreover, the backbone LLM is fine-tuned using low-rank adaptation for efficient adaptation to predictive beamforming tasks. Extensive simulations demonstrate that HG-LLM achieves performance levels comparable to channel-based methods across diverse settings, despite relying solely on HGI without requiring explicit CSI.

Foundation models like CLIP demonstrate exceptional capabilities over a broad domain of knowledge, such as with zero-shot classification; however, they also require significant computational resources, narrowing their real-world utility. Recent studies have shown that mapping features from pre-trained vision encoders into CLIP’s latent space can transfer some of CLIP’s abilities to smaller vision encoders, offering a promising alternative. Yet, the performance of these vision encoders still falls short of CLIP’s native capabilities, particularly in low-data regimes. In this work, we argue that enhancing training data coverage/diversity significantly improves mapping efficacy. We achieve this using tailored loss functions rather than relying on data augmentation or increasing training samples. For instance, we exploit the inherent multimodal nature of CLIP’s latent space, by incorporating cycle-consistency loss as one of our loss functions. Moreover, the mapping is learned using entirely unlabelled and unpaired data, eliminating the need for manual labelling or data pairing in novel domains. From these findings, our resulting method (Zoom-shot) offers a viable path to flexible zero-shot models for resource-limited, data-scarce settings. We test Zoom-shot’s zero-shot performance across various pre-trained vision encoders on coarse- and fine-grained datasets and achieve superior performance compared to recent works. In our ablations, we find Zoom-shot allows for a trade-off between data and compute during training; allowing for a significant reduction in required training data. All code and models are available on GitHub.

Cell-free massive multiple-input multiple-output (CF-mMIMO) is a promising architecture for 6G wireless networks through distributed access point (AP) cooperation. In large-scale deployments where user demand exceeds system capacity, effective user admission control (UAC) is essential to select users while meeting quality-of-service (QoS) requirements. The UAC problem in CF-mMIMO is inherently challenging, involving both discrete user selection and continuous power allocation variables. To address this challenge, we propose a Graphormer-enhanced Monte Carlo Tree Search (GE-MCTS) framework that integrates a Graphormer-based neural network (NN) with Monte Carlo Tree Search (MCTS). This framework leverages the Graphormer’s capability to model the graph-structured AP–user topology and MCTS’s planning proficiency to efficiently explore the vast decision space. Furthermore, to accommodate users initially unadmitted due to system constraints, we introduce a complementary AP deployment problem. By adapting the GE-MCTS framework, we optimize the placement of additional APs to achieve full user admission with the minimal number of new APs required. Simulation results demonstrate the effectiveness of our proposed framework. For UAC, with low computational complexity, GE-MCTS consistently admits 26.3–41.7% more users compared to baseline methods across various network scales. For AP deployment, our framework requires 45–73% fewer additional APs to achieve full user admission, highlighting its efficiency and scalability.

This paper investigates a general integrated sensing and covert communication (ISCC) system, where a base station (BS) transmits signals to covert users (CUs) while simultaneously sensing a dynamic target that acts as a warden (WA), maliciously attempting to eavesdrop on the covert communication. An essential task in realizing ISCC is the beamforming design, which however, is complicated by the dynamic nature of both the WA and the CUs in practice, i.e., (i) the rapid movement of the WA and (ii) the time-varying number of CUs. To address these challenges, in this paper, we develop a versatile recurrent graph neural network (RGNN)-based beamforming design framework, where the penalty method is first employed to transform the constrained optimization problem into an unconstrained one, and then an RGNN is customized to effectively output the beamforming vectors. Through implicitly learning features from the historical warden detection channels and the instantaneous channel state information among CUs and BS, the proposed approach could predict the next-time slot beamforming matrix while accommodating a scalable number of CUs, thus eliminating repeated WA channel estimation and re-optimization when handling dynamic scenarios. Moreover, a convolutional long short-term memory (CLSTM)-augmented message passing GNN (CL-MPGNN) is developed to realize the RGNN framework. In particular, a CLSTM module is first adopted to exploit the spatial-temporal features from the input to facilitate an effective predictive beamforming. Then, a set of message-passing layers is employed to guarantee the scalability of the beamforming design. Simulations verify the effectiveness of the proposed algorithm in terms of the covert communication performance, the covert communication-sensing tradeoff, and the generalizability, respectively.

Distributed optimal control algorithms have been used as the foundational framework for adaptive error management in ultra-dense 6G sensor network deployments, enabling efficient data transmission and robust error resilience. In the specific scenario of ultra-dense 6G networks, characterized by high uncertainties in both signal acquisition and communication channels, traditional fixed-threshold schemes fail to mitigate error clustering and achieve rapid convergence. In this paper, we propose a distributed adaptive stability control algorithm (DASCA) based on the distributed Hamilton-Jacobi-Bellman optimal control framework to address these limitations. Our approach integrates an enhanced consensus update protocol with higher-order compensation and adaptive step-size strategies, significantly improving convergence rate and error minimization. Experimental results demonstrate that the DASCA reduces the cost functional by approximately 50% and increases the convergence rate by around 60%, thereby outperforming conventional methods and confirming its efficacy in rapid error mitigation.

Reconstructing dynamic 3D (4D) scenes is challenging due to complex temporal dynamics and viewpoint sparsity in monocular videos. Existing extensions of 3D Gaussian Splatting (3D-GS) with its temporal modeling often fail to capture temporal correlations across frames, leading to redundant 3D Gaussians and reduced efficiency. To address this limitation, we propose DeDiff-4DGS, a framework that integrates temporal correlations and diffusion priors through two novel modules. The Temporal 3D Gaussian Latent Fusion (T3DLF) module fuses temporal information from sparse reference frames to promote spatio-temporal coherence and reduce the number of required 3D Gaussians. The Latent Diffusion Converter for 3D Gaussians (LDC3D) module enriches reference frames with semantic priors, complementing T3DLF under sparse-view conditions. Experimental results on standard benchmarks demonstrate that DeDiff-4DGS delivers higher reconstruction quality and improved efficiency over current state-of-the-art approaches.

Large-scale distributed communication networks have been widely recognized as the backbone for efficient data dissemination in cloud and IoT systems, serving as the foundation for dynamic routing, load balancing, and synchronization. In the specific scenario of real-time routing, traditional static approaches fail to adapt to variable communication delays, congestion, and node failures, resulting in high average end-to-end delay and suboptimal performance. In this paper, we propose the adaptive routing and fault tolerance protocol (ARFTP), a unified framework that leverages adaptive Susceptible-Infectious-Recovered (SIR) model applications and dynamic gossip algorithms to minimize the average end-to-end delay while ensuring load balancing and fault tolerance in large-scale distributed networks. Our approach employs an adaptive weight mechanism that continuously updates routing decisions based on real-time congestion and delay feedback, integrating recursive load feedback and a backup routing strategy to achieve efficient information dissemination. Experimental results demonstrate that the ARFTP reduces the average end-to-end delay to 0.15 s, increases throughput to 0.92, and significantly improves load balancing and fault tolerance compared to conventional static routing methods.

Foundation models for remote sensing have garnered increasing attention for their strong performance across various observation tasks. However, current models lack robustness in managing diverse input types and handling incomplete data in downstream tasks. In this paper, we propose RobSense, a robust multi-modal foundation model for Multi-spectral and Synthetic Aperture Radar data. RobSense is designed with modular components and pre-trained by a combination of temporal multi-modal alignment and masked autoencoder strategies on a huge-scale dataset. Therefore, it can effectively support diverse input types, from static to temporal, uni-modal to multi-modal. To further handle the incomplete data, we incorporate two uni-modal latent reconstructors that recover rich representations from incomplete inputs, addressing variability in spectral bands and temporal sequence irregularities. Extensive experiments demonstrate that RobSense consistently outperforms state-of-the-art baselines on complete datasets across four input types for segmentation, classification, and change detection. On incomplete datasets, RobSense outperforms the baselines by considerably larger margins when the missing rate increases. Project page: https://ikhado.github.io/robsense/

As a new communications architecture, the Space-Air-Ground integrated network (SAGIN) integrates satellites, airborne platforms, and terrestrial networks to enhance global connectivity and support robust and flexible communication capabilities. Efficient task offloading and resource allocation are crucial for SAGIN to meet the quality of service (QoS) requirements at low cost. In this paper, we formulate task offloading and resource allocation as a time-sequential decision-making problem, aiming to maximize task completion within available communication and computational resources. We propose an online approach referred to as graph fusion deep reinforcement learning (GF-DRL). GF-DRL incorporates a graph feature extraction network that utilizes a graph convolutional network (GCN) to extract features from both the task graph and user equipment (UE) graph, along with two attention mechanisms (hard and soft) to merge the two graphs. We also propose an action encoding and mapping network to generate both discrete (offloading) and continuous (allocation) decisions in an end-to-end manner. Simulation results validate the effectiveness of our proposed GF-DRL compared to state-of-the-art task offloading resource allocation approaches.

LEO cloud storage constellation (LCSC) has gained significant popularity thanks to its on-board data storage capability and extensive inter-satellite connectivity. Unfortunately, the satellite disks will fail occasionally due to cosmic radiation and energy depletion, which leads to data loss and network unavailable. However, multi-node repair in the LCSC leads to the larger repair delay and the higher energy cost. To address this, we introduced the aggregation and multicast coded repair (AMCR) to fast recover the stored data using Reed-Solomon (RS) codes. We first propose the multi-weight multinode repair tree (MWNRT) model, i.e., a staged tree graph containing edge weights, to measure the multiple factors affecting repair performance. Next, we analyze the repair delay and the energy cost associated with multi-node repair leveraging AMCR. Then, to minimize repair delay while reducing energy cost, the aggregation-based multiple single-node repair trees construction (A-MSRT) algorithm is designed to construct multiple single-node repair trees based on the shortest-path principles. While the multicast-based aggregation of multiple repair trees (M-AMRT) algorithm is designed to select the repair tree with the longest delay from the output of A-MSRT as the initial repair tree, then adds the remaining replacement nodes. And the complexity of the two algorithms is elaborated and proven to be reasonable. Simulations show that AMCR scheme outperforms other schemes under different network conditions in LCSC.

Space-air-ground integrated networks (SAGIN), a cornerstone of 6G, face challenges in task offloading and resource allocation (TORA) due to their heterogeneity, dynamic topology, and high mobility. To address these, we formulate a multi-objective TORA problem under dynamic topologies to minimize latency and inter-node power consumption. We propose a dynamic heterogeneous graph neural network (DHGNN) that, combined with reinforcement learning, adaptively updates node features to capture cross-domain dependencies. Simulations demonstrate that our method outperforms existing GDRL approaches in reward, latency, and power efficiency.

In this paper, we focus on the application of coded distributed computing (CDC) in a multi-server clustered network (MSCN), which is designed to accelerate the gradient update process in federated learning (FL) by considering both communication and computational heterogeneity. As the number of participating devices increases and resource heterogeneity becomes more pronounced, reducing total execution latency (TEL) has become a critical challenge. To address this issue, we focus on optimizing the matching between heterogeneous devices and server task loads to improve resource utilization while enhancing the robustness and fault tolerance of the FL system. To minimize TEL, we propose a greedy algorithm and an iter-genetic algorithm for device assignment, named GADA and IGADA, based on the task allocation for the single server (TASS) algorithm, respectively. Based on simulation results and theoretical analysis, we confirm that our proposed algorithms substantially reduce the TEL in various scenarios compared to existing CDC methods, with complexity markedly lower than that of the exhaustive scheme.

Satellite Federated Learning (SFL) has emerged as a transformative paradigm for distributed machine learning in Low Earth Orbit (LEO) mega-constellations, enabling real-time processing of space-acquired data and enhancing remote sensing missions. The integration of Inter-Satellite Links (ISLs) into SFL alleviates synchronization delays due to intermittent connectivity between LEO satellites and ground-based parameter server (PS). However, the traffic generated from satellites creates communication bandwidth bottlenecks at the PS in the global model aggregation procedure. To address this issue, this paper proposes a novel SFL framework that leverages in-network model aggregation through ISLs to improve communication efficiency. Furthermore, two aggregation strategies, i.e., Chain Aggregation (CA) and Ring Aggregation (RA), are discussed in detail. Through system latency analysis and comprehensive simulations across constellation scales and data distributions, we demonstrate that: (1) in-network model aggregation fundamentally transforms communication load growth from ${\mathcal{O}}\left({{N^2}}\right)$ to ${\mathcal{O}}\left(N\right)$, and (2) the convergence time improves with increasing number of satellites, but degrades beyond a threshold.

Directional modulation (DM) is a physical layer security (PLS) technique implemented at the transmitter, leveraging antenna arrays to ensure secure communications. Through a process of spatial precoding between transceivers to transmit signals in specific directions, DM is capable of disrupting communications in unintended directions to prevent eavesdropping. In general, recent progress in the development of multiple-input multiple-output (MIMO) systems, including advanced radio frequency (RF), antenna technologies, along with innovative precoding algorithms, has enhanced the capabilities of DM techniques, leading to a multitude of robust DM variants. Hence, this survey aims to offer a comprehensive overview of DM, covering its fundamentals, promising variants, applications, hardware implementations, and future trends. Initially, the basic principle of DM is outlined in a general manner for subsequent comprehension. Subsequently, the large family of DM techniques is categorized into distinct variants based on the types of transmitting arrays. Next, we give a comprehensive survey of DM in common wireless scenarios, including multi-user (MU), relay, Internet of Things (IoT), and non-orthogonal access (NOMA) networks. Furthermore, we provide an illustration of DM system implementations, encompassing foundational architectures and cost-effective hardware realizations. Finally, concerning the unresolved challenges and current research focal points in DM, we present future research directions that merit further exploration and reference.

Intelligent fault diagnosis (IFD) plays a crucial role in ensuring the safe operation of industrial machinery and improving production efficiency. However, traditional supervised deep learning methods require a large amount of training data and labels, which are often located in different clients. Additionally, the cost of data labeling is high, making labels difficult to acquire. Meanwhile, differences in data distribution among clients may also hinder the model’s performance. To tackle these challenges, this paper proposes a semi-supervised federated learning framework, SSFL-DCSL, which integrates dual contrastive loss and soft labeling to address data and label scarcity for distributed clients with few labeled samples while safeguarding user privacy. It enables representation learning using unlabeled data on the client side and facilitates joint learning among clients through prototypes, thereby achieving mutual knowledge sharing and preventing local model divergence. Specifically, first, a sample weighting function based on the Laplace distribution is designed to alleviate bias caused by low confidence in pseudo labels during the semi-supervised training process. Second, a dual contrastive loss is introduced to mitigate model divergence caused by different data distributions, comprising local contrastive loss and global contrastive loss. Third, local prototypes are aggregated on the server with weighted averaging and updated with momentum to share knowledge among clients. To evaluate the proposed SSFL-DCSL framework, experiments are conducted on two publicly available datasets and a dataset collected on motors from the factory. In the most challenging task, where only 10% of the data are labeled, the proposed SSFL-DCSL can improve accuracy by 1.15% to 7.85% over state-of-the-art methods.

Massive emissions of greenhouse gases (GHGs) have a negative impact on the development of sustainable agriculture. While techniques of imputation and forecasting facilitate the observation of GHG emissions with improved accuracy, there is a lack of an integrated model for both GHG emission data imputation and forecasting, particularly in few-shot learning scenarios. To address this issue, this paper proposes a pre-trained large language model dubbed Agri-LLM for GHG emission data imputation and forecasting in smart agriculture. Notably, this model develops an information fusion embedding layer that fuses missing patterns, temporal irregularities and incomplete time series into multi-level patched tokens. A global temporal similarity informed prompting module is further elaborated on to generate suitable prompts for target time series, based on similar temporal characteristics captured from other nodes. Finally, the model aligns the pre-trained knowledge language with multi-level integrated tokens directly without altering the large language model’s backbone. The experimental studies demonstrate that our model outperforms state-of-the-art baselines in both tasks of imputation and forecasting using full-sample training. Extensive experiments also confirm that the Agri-LLM exhibits superior performance in few-shot learning scenarios and the effectiveness of each proposed model component.

Spatiotemporal data collected by sensors within an urban Internet of Things (IoT) system inevitably contains some missing values, which significantly affects the accuracy of spatiotemporal data forecasting. However, existing techniques, including those based on Large Language Models (LLMs), show limited effectiveness in forecasting with missing values, especially in scenarios involving high-dimensional sensor data. In this article, we propose a novel spatiotemporal pre-trained large language model dubbed SPLLM for forecasting with missing values. In this network, we seamlessly integrate a specialized spatiotemporal fusion Graph Convolutional Network (GCN) module that extracts intricate spatiotemporal and graph-based information, for generating suitable inputs to the SPLLM. Furthermore, we propose a Feed-Forward Network (FFN) fine-tuning strategy within the LLM and a final fusion layer to enable the model to leverage the pre-trained foundational knowledge of the LLM and adapt to new incomplete data simultaneously. The experimental results indicate that SPLLM outperforms state-of-the-art models on real-world public datasets. Notably, SPLLM exhibits a superior performance in tackling incomplete sensory data with a variety of missing rates. A comprehensive ablation study of key components is conducted to demonstrate their efficiency.

The Susceptible-Infected-Recovered paradigm (SIR) coupled with decentralized gossip remains central to information flow and misinformation mitigation in heterogeneous urban networks, yet static parameters (β, γ, τ) and limited adaptivity hinder responsiveness under rapidly varying conditions. We propose the stochastic trust-enhanced calibration algorithm (STCA), which unifies dynamic trust updates with adaptive gossip control under a high-order Hamilton-Jacobi-Bellman (HJB) stochastic optimization framework. At its core, the STCA performs iterative calibration of (β, γ, τ) via gradient descent augmented by fractal-inspired performance metrics and recursive coupling operators, yielding robust stability guarantees and real-time adaptation to mobility and load fluctuations. Experiments demonstrate a 50 % reduction in detection time (15 s vs. 30 s), an isolation-efficiency gain of approximately 19 % (0:95 vs. 0:80), and a 50 % increase in communication throughput (1200 units vs. 800 units). These results indicate that jointly enhancing trust dynamics, stochastic control, and adaptive gossip via STCA constitutes a scalable technological advancement for smart-city information dissemination, delivering certificate-oriented stability and performance suitable for next-generation (6G+) deployments.

Entropy-driven network coding has been used as a basis for optimizing data transmission and enhancing resource utilization in Fog-Cloud IoT architectures, including applications in smart cities, industrial automation, environmental monitoring, and healthcare. In Fog-Cloud IoT architectures, conventional data transmission protocols are inefficient because they cannot adapt to dynamic entropy levels, resulting in underutilized bandwidth, increased latency, and higher energy consumption. In this paper, we propose an Enhanced Entropy-Driven Network Coding (E-EDNC) framework to address these problems. Our framework integrates real-time entropy estimation with adaptive coding strategies and employs a hybrid evolutionary-reinforcement learning (HE-RL) algorithm to dynamically optimize coding parameters and scheduling decisions. Experimental results demonstrate that E-EDNC improves bandwidth utilization by 25%, reduces latency by 25%, and decreases energy consumption by 12%, thereby enhancing overall data transmission efficiency and reliability in Fog-Cloud IoT environments.

In this study, we investigate the use of simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) mounted on energy-efficient uncrewed aerial vehicles (UAVs) to support satellite Internet of Things (IoT) communications served by low-Earth orbit (LEO) satellites. First, we propose a STAR-RIS-equipped UAV framework termed integrated STAR-RIS and UAV (ISRU). Then, we aim to optimize energy efficiency by jointly adjusting the UAV’s flight path, STAR-RIS phase-shifts, and power allocation among IoT devices, all while maintaining equitable user fairness level. However, solving this problem presents considerable challenges due to the nonconvexity and NP-hardness properties of the objective function and constraints. To address, our work introduces a Dinkelbach-based alternating optimization (AO) procedure termed integrated trajectory, phase-shift, and power allocation (ITPP). Our simulation results show that the integration of ISRU and ITPP can achieve 67% higher sum-rates than non-ISRU schemes and save up to 40% more energy than unoptimized trajectory schemes.

Space-Air-Ground integrated network (SAGIN) is a crucial component of the 6G, enabling global and seamless communication coverage. This multi-layered communication system integrates space, air, and terrestrial segments, each with computational capability, and also serves as a ubiquitous computing platform. An efficient task offloading and resource allocation scheme is key in SAGIN to maximize resource utilization efficiency, meeting the stringent quality of service (QoS) requirements for different service types. In this paper, we introduce a dynamic SAGIN model featuring diverse antenna configurations, two timescale types, different channel models for each segment, and dual service types. We formulate a problem of sequential decision-making task offloading and resource allocation. Our proposed solution is an innovative online approach referred to as graphic deep reinforcement learning (GDRL). This approach utilizes a graph neural network (GNN)-based feature extraction network to identify the inherent dependencies within the graphical structure of the states. We design an action mapping network with an encoding scheme for end-to-end generation of task offloading and resource allocation decisions. Additionally, we incorporate meta-learning into GDRL to swiftly adapt to rapid changes in key parameters of the SAGIN environment, significantly reducing online deployment complexity. Simulation results validate that our proposed GDRL significantly outperforms state-of-the-art DRL approaches by achieving the highest reward and lowest overall latency.

Accurate estimation and detection, along with phase shift optimization, are vital for implementing reconfigurable intelligent surface (RIS)-enabled multi-antenna systems in highly disruptive industrial IoT environments. Motivated by the remarkable capabilities of deep learning (DL) techniques, this paper introduces a pioneering approach to address challenges in channel estimation, channel correlation prediction, and symbol detection for industrial IoT. We develop an optimization framework for large-scale IoT deployments to maximize the signal-to-interference-plus-noise ratio (SINR) while minimizing transmit power. We also propose a transformer-based channel correlation predictor for IoT devices, which enables adaptive pilot retransmissions and reduces training overhead through a co-design approach that integrates communication, computation, and control. Extensive simulations under realistic, time-varying industrial IoT channel conditions demonstrate the superiority of our DL-driven approach, achieving significant improvements in detection accuracy and SINR.

Time series forecasting is pivotal in both academic research and practical applications across diverse industries. However, effectively leveraging external factors to enhance forecasting performance remains a significant challenge, necessitating further investigation. Current frameworks exhibit notable limitations in modeling the impact of external factors on both intrinsic and extrinsic correlations within time series data. To address these challenges, we propose a novel mechanism that systematically integrates contextual information from external factors with temporal dependencies, while maintaining compatibility with various encoder-decoder algorithms. This approach enables backbone models to embed dependent patterns from external factors across multiple correlated time series, effectively capturing their influence on both prior and adjacent timesteps. Our study centered on the application of time series forecasting for demand prediction, as sales forecasting poses unique challenges stemming from the complexity and variability of market conditions influenced by numerous external factors. We conducted extensive experiments on three real-world retail datasets, showcasing the substantial performance enhancement of backbone models when integrated with our proposed contextual embedding mechanism. Specifically, our approach achieves improvements of up to 26 % in Mean Squared Error (MSE) and 15 % in Mean Absolute Error (MAE) compared to both the original backbone models and other state-of-the-art (SOTA) baseline methods. The proposed mechanism is also evaluated on Weather and Energy datasets to further verify its generalization capability. We will release the source codes and experimental datasets at our GitHub1.

In the context of massive machine-type communications (mMTC) within the Internet of Things (IoT), joint activity detection and channel estimation (JADCE) is a key challenge in enabling massive access due to sporadic device access patterns. In this work, we consider both single-antenna and multiple-antenna base station scenarios and formulate the JADCE problem using the least absolute shrinkage and selection operator (LASSO) framework. To address this problem, we propose a model-driven network that utilizes compressive sensing (CS) and deep learning techniques. Specifically, we first design a prediction-correction alternating direction method of multipliers (PC-ADMM) as the underlying algorithm of the model-driven network. Then, the network is developed based on the PC-ADMM and is designed to be complex-valued. Furthermore, we also model the proximal operator, typically used to generate sparse solutions in LASSO, as a channel attention module within the model-driven network to enhance robustness. Numerical results show that the proposed PC-ADMM framework outperforms existing LASSO-based methods in terms of channel estimation and device activity detection.

Integrating data security with resource management enhances security, efficiency, and reliability of blockchain-enabled mobile edge computing (MEC) systems. However, challenges such as secure data storage, timely task execution, and limited parallelism introduce complexities in task offloading decisions and resource allocation strategies. To address these challenges, the task latency minimization problem in blockchain-enabled MEC networks is formulated as an NP-hard optimization problem. The model incorporates constraints on parallelism, partial task offloading, bandwidth and computation resource allocation among mobile users (MUs) and edge servers (ESs). To enhance the reliability and transparency of data storage, a dual-blockchain framework is proposed, consisting of multiple MU blockchains and a dedicated ES blockchain. To tackle the NP-hard problem, the original optimization problem is decomposed into multiple sub-problems, facilitating parameter decoupling. An alternating optimization algorithm is employed to refine task offloading decisions and resource allocation of MUs and ESs with limited parallelism. The ESs update their strategies iteratively based on feedback mechanisms. Additionally, a task prioritization formulation is developed to enhance scalability, considering sub-level task importance, urgency, and first-level task classification. Extensive simulation experiments demonstrate that the proposed algorithm achieves lower task latency compared to existing methods across varying network sizes, offloading schemes, and parallelism constraints. By optimizing the parallel processing of tasks, the waiting latency of this algorithm is reduced on average by 35. 35%, 57. 16% and 35. 35% compared to other methods, respectively.

As a promising candidate for high-mobility communications, orthogonal chirp division multiplexing (OCDM) has attracted growing attention owing to its robustness to Doppler shifts and efficient hardware implementation. In this paper, motivated by the urgent demand for seamless and reliable communications in high-speed railway (HSR) scenarios, we innovatively integrate OCDM into cell-free massive multiple-input multiple-output (CFmMIMO) systems and establish a novel transmission framework, termed CFmMIMO-OCDM. Within this framework, we conduct a comprehensive analysis of the doubly-dispersive HSR channel model and derive the input-output signal relation in HSR communications. Moreover, to address the challenges posed by high computational complexity and excessive data exchange inherent in centralized signal processing, we first reveal the quasi-sparsity of the Fresnel-domain channel matrix in HSR communications. Then, we develop a distributed baseband processing (DBP) architecture by leveraging the channel sparsity. Aimed at enhancing the signal detection efficiency and accuracy, we further design a distributed message passing (DMP)-based detection algorithm for CFmMIMO-OCDM in HSR communications, which achieves considerably reduced complexity and data exchange compared to the centralized detection. Numerical results confirm the superiority of CFmMIMO-OCDM over conventional orthogonal frequency division multiplexing (OFDM)-assisted CFmMIMO systems in HSR communications. Moreover, theoretical analysis and numerical results are provided to demonstrate that our proposed DMP detection can achieve attractive bit error rate (BER) and complexity performance compared to conventional centralized detection.

A Orthogonal Time Frequency Space (OTFS) system has demonstrated its potential advantages in high-mobility communication scenarios. A low complexity detection algorithm is always a critical challenge for the OTFS receiver. In this paper, we propose a novel detection chain based low-complexity successive interference cancellation (SIC) symbol detection algorithm for OTFS system. Specifically, we first set a protection interval in OTFS data frames, which can provide some inter-symbol interference (ISI)-free areas in received signals. Based on these ISI-free areas, we can construct the detection chain to determine the detection order of the SIC algorithm based on the association relationship of received signals. Furthermore, in order to mitigate the error propagation of the SIC algorithm, we propose a detection direction selection scheme, which can provide the direction selection gain and significantly improve the performance. Moreover, we analyze the complexity of the proposed SIC algorithm. Compared with many existing detection algorithms, the proposed SIC algorithm can significantly reduce the detection complexity. Simulation results show that in the channel scenario with the line of sight (LOS) path, the proposed algorithm outperforms that of message passing (MP) and maximal ratio combining (MRC) algorithms at high SNRs. Furthermore, in the channel scenario without the LOS path, the proposed algorithm is close to MP and MRC algorithms.

Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time performance, mainly due to inflexible scene representation strategy without leveraging any prior information. In this paper, we introduce SP-SLAM, a novel neural RGB-D SLAM system that performs tracking and mapping in real-time. SP-SLAM computes depth images and establishes sparse voxel-encoded scene priors near the surface reconstruction. Simultaneously, we employ triplanes to store scene appearance information, striking a balance between achieving high-quality geometric texture mapping and minimizing memory consumption. Furthermore, in SP-SLAM, we introduce an effective optimization strategy for mapping, allowing the system to continuously optimize the poses of all historical input frames during runtime without increasing computational overhead. We conduct extensive evaluations on five benchmark datasets (Replica, ScanNet, TUM RGB-D, Synthetic RGB-D, 7-Scenes). The results demonstrate that, compared to existing methods, we achieve superior tracking accuracy and reconstruction quality, while running at a significantly faster speed.

Recent research in smart factory networks has shown that advanced adaptive control are essential for managing the multidimensional uncertainties inherent in communication systems. In dynamic environments where traditional fuzzy controllers suffer from slow convergence and reduced robustness, rapid error decay is critical to ensure system stability. In this article, we propose the adaptive reinforcement fuzzy control algorithm (ARFCA), a novel scheme that integrates advanced Type-2 fuzzy inference, reinforcement learning-based control updates, and temporal memory defuzzification to maximize the convergence rate (CR). Experimental results demonstrate that the proposed ARFCA achieves a CR approximately three times higher and reduces control error by nearly 80% compared to conventional methods, thereby significantly enhancing system reliability and scalability.

Underwater acoustic target recognition (UATR) can be significantly empowered by advancements in deep learning (DL). However, the effectiveness of DL-based UATR methods is often constrained by the limited computing resources available on underwater platforms. Most of the existing knowledge distillation (KD) strategies try to build lightweight DL models, but these strategies rarely consider the acoustic properties of underwater environments, making them less efficient for UATR tasks. Thus, fully harnessing the potential of DL techniques while ensuring the model’s practicality, is one of the urgent problems to be solved in UATR research. In this work, we introduce the union-domain KD (UDKD) to establish an accurate and lightweight UATR model. UDKD integrates two KD strategies: dual-frequency band distillation (DBD) and cross-domain masked distillation (CMD). DBD improves the learning process for a simple student model by decoupling the knowledge of spectrograms into the local structural (i.e., line spectra) and global composition (i.e., propagation patterns) aspects. CMD reduces redundant information from the Fourier Transform process, enabling the student model to concentrate on essential signal elements and to learn underlying time–frequency distribution. Extensive experiments on two real-world oceanic datasets confirm the superior performance of UDKD compared to existing KD methods, i.e., achieving an accuracy of 94.81% ($\uparrow ~3.19$% versus 91.62%). Notably, UDKD showcases a 10.5% improvement in the prediction accuracy of the lightweight student model.

Relic landslide, formed over a long period, possess the potential for reactivation, making them a hazardous geological phenomenon. While reliable relic landslide detection benefits the effective monitoring and prevention of landslide disaster, semantic segmentation using high-resolution remote sensing images for relic landslides faces many challenges, including the object visual blur problem, due to the changes of appearance caused by prolonged natural evolution and human activities, and the small-sized dataset problem, due to difficulty in recognizing and labelling the samples. To address these challenges, a semantic segmentation model, termed mask-recovering and interactivefeature- enhancing (MRIFE), is proposed for more efficient feature extraction and separation. Specifically, to address the visual blur problem, a contrastive learning and mask reconstruction approach is designed under the guidance of remote sensing visual interpretation expert knowledge, which states the height variation at the landslide boundary contributing the most to landslide identification. This approach constructs local patches from the landslide boundary and background to perform supervised contrastive learning and applies mask reconstruction to local patches, guiding the model to focus on the landslide boundary and to extract the most contributive local salient features for reliable recognition. Meanwhile, to address the smallsized dataset problem, a self-distillation learning method is introduced, which uses a momentum encoder to update the teacher network with the average of the student network, suppressing overfitting caused by background interference. By constructing contrastive input pairs, the approach increases the diversity and combinations within the contrastive sample space and improves sample utilization. The proposed MRIFE is evaluated on a real relic landslide dataset, and experimental results show that it greatly improves the performance of relic landslide detection. For the semantic segmentation task, compared to the baseline, the precision increases from 0.4226 to 0.5347, the mean intersection over union (IoU) increases from 0.6405 to 0.6680, the landslide IoU increases from 0.3381 to 0.3934, and the F1-score increases from 0.5054 to 0.5646.

Despite advances in deep learning for remote sensing building extraction (RSBE), Multi-target Domain RSBE (MD-RSBE) remains challenging, as it requires transferring knowledge from a labeled source domain to multiple unlabeled target domains, with domain shifts in texture, style, and semantics. Existing domain adaptation (DA) and generalization (DG) methods face significant limitations: DA requires target-domain training, while DG needs multi-source training, leading to high training costs and low generalization in practical MD-RSBE scenarios. To address this, we propose a Multi-view Augmented Single-source Domain Generalization (MASDG) method, which effectively mitigates domain shifts across RS source and target domains for robust MD-RSBE performance by enriching the diversity of the source domain through multi-view augmentation and enforcing semantic consistency. Specifically, MASDG consists of three key components: Texture-level Domain Augmentation (TDA) module, Style-level Domain Augmentation (SDA) module and Semantic-invariant Representation Learning (SRL). To mitigate texture-level domain shift, TDA first introduces parameter-optimized multi-layer random convolution to modify the texture of source image, generating texture-augmented image pairs for simulating real-world texture diversity across various RS domains. Then, with each image pair from TDA, SDA employs two paralleled encoders, namely the general feature encoder and the batch-guided style encoder, to formulate multi-view building features, further mitigating style-level domain shift. Finally, SRL ensures semantic-invariant representation learning via a dual mechanism, including multi-view segmentation loss and semantic consistency loss. The former generates predictions from diverse feature views (original, texture-augmented, style-augmented, etc.), while the latter performs semantic alignment by minimizing distribution discrepancies among predictions, bridging semantic inconsistency to enable robust segmentation. Extensive experiments across three different MD-RSBE settings with 7 different target domains demonstrate that our MASDG outperforms existing state-of-the-art methods by a significant margin.

Hyperspectral Anomaly Detection (HAD) is of great significance in remote sensing by identifying spectrally distinct pixels as anomalies without prior information, while the majority of pixels with similar spectral characteristics are classified as background. While existing approaches combine the strengths of deep learning in feature extraction and background suppression with the effectiveness of low-rank representation in background modeling, they fail to fully exploit rich spatial information and long-range spectral dependencies due to the limitations of conventional convolutional operations. To address this issue, we propose a Geometric Algebra (GA)-based deep neural network for HAD, named GA-HAD. The network constructs an encoder-decoder architecture using GA convolutional layers to extract spectral-spatial features, capturing multi-dimensional spatial information while preserving the intricate spectral characteristics of hyperspectral images. A specialized reconstruction error is designed to train the GA feature extraction network with high efficiency and accuracy. The encoder features are integrated with the low-rank representation algorithm and a Gaussian mixture model-based dictionary to improve background modeling and robustness. Finally, the detection maps output by the low-rank detection module are refined through an edge-preserving filter to produce the final detection result. Extensive experiments on four datasets demonstrate the superiority of our proposed GA-HAD framework in overall detection effect compared to thirteen representative baselines, implying our potential application in the field of HAD.

In wireless communication adversarial scenarios, signals are easily intercepted by non-cooperative parties, exposing the transmission of confidential information. This paper proposes a true-and-false (T/F) frequency multiplexing based anti-intercepting transmission scheme capable of concealing truth while showing fake (CTSF), integrating both offensive and defensive strategies. Specifically, through multi-source cooperation, true and false signals are transmitted over multiple frequency bands using non-orthogonal frequency division multiplexing. The decoy signals are used to deceive non-cooperative eavesdropper, while the true signals are hidden to counter interception threats. Definitions for the interception and deception probabilities are provided, and the mechanism of CTSF is discussed. To improve the secrecy performance of true signals while ensuring decoy signals achieve their deceptive purpose, we model the problem as maximizing the sum secrecy rate of true signals, with constraint on the decoy effect. Furthermore, we propose a bi-stage alternating dual-domain optimization approach for joint optimization of both power allocation and correlation coefficients among multiple sources, and a Newton’s method is proposed for fitting the T/F frequency multiplexing factor. In addition, simulation results verify the efficiency of anti-intercepting performance of our proposed CTSF scheme.

The frequency-modulated continuous wave (FMCW) radar has received much attention in the field of noncontact vital signs monitoring. However, since vital signs are usually very weak, it can be easily buried by interference and noise, especially for the heartbeat signal. To tackle this challenge, this article proposes a novel systematic vital signs detection framework using the multiple-input multiple-output FMCW radar. First, the signal noise ratio of the vital signs signal is enhanced by combining the phase signals of multiple channels using the maximum ratio combining method. Then, to suppress noise and interference, we construct the vital signs signal with singular spectral analysis and propose a correlation-based selection criterion to select potential intrinsic mode functions of the respiration and heartbeat signals. Finally, a fast independent component analysis is applied to extract the respiration signal, and the second-order derivative based fast independent component analysis in conjunction with an infinite impulse response notch filter is further developed to extract the heartbeat signal. Simulations and experimental results validate the effectiveness of the proposed framework.

Recently, salient object detection (SOD) methods have achieved impressive performance. However, salient regions predicted by existing methods usually contain unsaturated regions and shadows, which limits the model for reliable fine-grained predictions. To address this, we introduce the uncertainty guidance learning approach to SOD, intended to enhance the model's perception of uncertain regions. Specifically, we design a novel Uncertainty Guided Refinement Attention Network (UGRAN), which incorporates three important components, i.e., the Multilevel Interaction Attention (MIA) module, the Scale Spatial-Consistent Attention (SSCA) module, and the Uncertainty Refinement Attention (URA) module. Unlike conventional methods dedicated to enhancing features, the proposed MIA facilitates the interaction and perception of multilevel features, leveraging the complementary characteristics among multilevel features. Then, through the proposed SSCA, the salient information across diverse scales within the aggregated features can be integrated more comprehensively and integrally. In the subsequent steps, we utilize the uncertainty map generated from the saliency prediction map to enhance the model's perception capability of uncertain regions, generating a highly-saturated fine-grained saliency prediction map. Additionally, we devise an adaptive dynamic partition (ADP) mechanism to minimize the computational overhead of the URA module and improve the utilization of uncertainty guidance. Experiments on seven benchmark datasets demonstrate the superiority of the proposed UGRAN over the state-of-the-art methodologies. Codes will be released at https://github.com/I2-Multimedia-Lab/UGRAN.

Radio map estimation (RME) is a crucial method for analyzing spectrum space utilization and network coverage, serving as an essential tool for the mobile communication. However, physical constraints, security, privacy, and other issues often render some areas inaccessible, resulting in extremely sparse and unevenly distributed measurement data. To address these challenges, we propose a multimodal feature fusion graph convolution network (MFFGCN). The model incorporates a dual-encoder architecture with an adaptive multi-feature fusion module to exploit environmental information and learn the shadowing effects of radio-signal propagation. We then convert the coarse estimation into regional feature patches and construct a graph over these patches. A graph neural network aggregates contextual information among them, thereby alleviating the impact of uneven spatial sampling. Extensive experiments on open datasets demonstrate that our method achieves state-of-the-art performance, effectively reducing the effects of uneven sampling.

Many point cloud completion methods typically rely on two steps: coarse generation and 2D Grid deformed fine output. However, in the fine generation, the expansion range (2D Grid Scale) required by each point cloud sample may be vastly different. For example, if the expansion range for a vessel shape is applied to a table shape, the final output may be blurry or sparse. To this end, we propose the RLGrid, Reinforcement Learning Controlled Grid Deformation. In detail, we firstly obtain two point cloud skeletons by two branches. One is to use an autoencoder, and the other is to convert the randomly generated normal distribution to coarse point cloud by GAN. We choose the one with smaller chamfer distance between coarse output and incomplete input as the input of the second stage. Then, a Reinforcement Learning (RL) agent is designed to select the appropriate expansion range based on the feature of each point cloud, and generate a 2D Grid. Finally, all the features are concatenated and sent into a Multilayer Perceptron to obtain the detailed complete point cloud. Experimental results show that RLGrid achieves state-of-the-art performance on various datasets. To the best of our knowledge, RL is not widely used in point cloud completion task due to lack of custom environment, and the proposed RLGrid provides an insight on how to formulate 2D Grid deformation as a sequential decision making problem. Further, it can also be plug-and-play on any 2D Grid features.

Pose-guided person image generation aims to synthesize images of human in various poses, often encountering issues such as occlusions and texture transfers. Previous methods have utilized attention mechanisms, flow field, normalization techniques, and diffusion model. Among them, flow field and attention are the two most commonly used methods. Flow fields are good at preserving detailed textures, while attention is better at generating reasonable semantic structures. Previous networks often used only one of the two and failed to make full use of their advantages. At the same time, the flow field and attention also showed complementary functions in the frequency domain. The flow field was good at preserving the high frequency information of the image with the detailed texture, while the semantic structure of attention was good at generating the image with the low frequency information, and few networks used this to improve the generation effect. Based on these facts, this paper introduces the AplusN network, which innovatively addresses the image generation problem by processing from low to high frequencies. For low-frequency information, a conditional large-kernel convolutional attention mechanism (CLA) is employed to capture the global information of the human body. High-frequency information is refined using a spatial-channel normalization module (SCN) to enhance the body's detailed textures. Additionally, we propose a wavelet loss function to align the frequency domain information of the generated images with the target images. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art (SOTA) methods, yielding better-defined overall body contours, local details, and higher-quality image generation.

Recently, generative models such as diffusion models (DMs) have gained prominence in various applications, and there is a growing demand for their deployment on resource-constrained devices. Model pruning provides an effective solution by reducing the model redundancy without significantly impacting performance. However, most existing model pruning methods are designed for classification models and often lead to substantial performance degradation when applied to generative models. To address this issue, we propose Comp-Diff, a novel two-stage framework of pruning and knowledge distillation tailored for diffusion models. In the pruning stage, we propose a new structured content-aware pruning (CaP) method within Comp-Diff to identify and preserve informative units (filters/channels) that actually contribute to the generative capability of the model. Specifically, we introduce input perturbations to the pre-trained model and measure each unit’s importance score using gradients induced by these perturbations. Units with higher importance scores are considered more informative and are retained to maintain the model’s generative power. In the fine-tuning stage of Comp-Diff, we propose the distribution-aware knowledge distillation (DaKD) method, which effectively transfers fine-grained knowledge from the original model to the pruned one on both attention and noise distribution levels. In addition, DaKD includes an adversarial loss to improve the quality and diversity of generated outputs. To verify and evaluate our method, we apply the proposed Comp-Diff on three representative tasks: unconditional image generation, conditional image generation, and text-to-image generation. Extensive experiments on both multi-step and one-step diffusion models demonstrate that the proposed framework consistently yields compact models and outperforms existing pruning techniques by a large margin.

In this paper, we propose a novel orthogonal frequency division multiplexing (OFDM) waveform framework by capitalizing on the benefits of maximum distance separable (MDS) code and the reconfigurable intelligent surface (RIS). The proposed scheme is referred to as MDS-OFDM-RIS. The proposed design scheme consists of (i) an MDS code based amplitude and phase modulation scheme for OFDM transmission, which helps increase the minimum Hamming distance among symbols and improve on the error detection capabilities, (ii) a RIS that is placed near the radio frequency (RF) source, (iii) as well as a reduced-complexity maximum likelihood (RC-ML) detection algorithm at the receiver by utilizing the error detection ability of the MDS codes. We derive an upper bound for the bit error rate (BER) and a closed-form expression of the mutual information. Using the obtained analytical expressions, we formulate two optimization problems and derive the corresponding optimal solutions for RIS phase shifts. It is found that the two optimization problems share the same optimal solution, which indicates that the obtained RIS phase shifts optimize the system BER and channel capacity simultaneously. Simulation results show that compared with conventional OFDM systems, the proposed system can better combat multipath fading and provide higher channel capacity, especially when the RIS phase shifts are optimal. Moreover, the accuracy and low complexity of the proposed RC-ML detection scheme are demonstrated by numerical results.

With its dual-functional advantages, integrated sensing and communications (ISAC) technologies can be further extended to satellite communications, enhancing global coverage services. However, achieving vast coverage would result in significant delays and considerable path losses. Motivated by this, in this paper, we focus on satellite-based ISAC (S-ISAC) systems and propose a general transceiver design framework incorporating both transmit waveform and receive filter. Unlike existing approaches, our approach uses a predictive joint transmit waveform and receive filter design that eliminates the need of channel estimation, thereby reducing time overhead. Additionally, a versatile weighting mechanism is designed to allow flexible prioritization between communications and sensing. To tackle the intractability of the ISAC transceiver design problem, we adopt a data-driven deep learning-based approach, where the model learns to design the transmit waveform and receive filter from historical channel data. Specifically, we propose a predictive optimization network (PONet), leveraging convolutional layers and a Transformer encoder to capture long-term spatial-temporal features and facilitate the learning capability. Numerical results demonstrate the effectiveness of the proposed PONet in terms of communications and sensing rates in S-ISAC networks in various system settings.

Space-Air-Ground integrated network (SAGIN) is a crucial component of the 6G, enabling global and seamless communication coverage. An efficient task offloading and resource allocation scheme is key in SAGIN to maximize resource utilization efficiency, meeting the stringent quality of service (QoS) requirements for different service types. In this paper, we introduce a dynamic SAGIN model featuring diverse antenna configurations, two timescale types, different channel models for each segment, and dual service types. We formulate a problem of sequential decision-making task offloading and resource allocation. Our proposed solution is an innovative online approach referred to as graphic deep reinforcement learning (GDRL). This approach utilizes a graph neural network (GNN)-based feature extraction network to identify the inherent dependencies within the graphical structure of the states. Simulation results validate that our proposed GDRL significantly outperforms state-of-the-art deep reinforcement learning (DRL) approaches by achieving the highest reward and lowest overall latency.

On-board distributed computing can provide more powerful computation capabilities for future low-earth-orbit (LEO) satellite constellations, serving intelligent information sensing and spatial large model through multi-satellite cooperation. On-board distributed computing depends on the efficient exchanging data flows between satellites termed coflow. The application of laser inter-satellite links (LISLs) will drastically improve the transmission capacity among the satellite distributed computing network (SDCN). However, due to the temporary interruptions of LISLs and the characteristics of optical circuit switching (OCS), the flow interruptions and conflicts significantly affect the coflow completion time (CCT). In this paper, we propose a conflict-aware coflow scheduling scheme to reduce the CCT in the OCS-based SDCN. Firstly, the time-varying LISLs and OCS-based coflow transmission are modeled and the problem of minimizing CCT is formulated. After that, we characterize the routing paths of coflow as the conflict graph and transform the coflow concurrent matching problem into the maximum independent set (MIS) problem in conflict graph. Based on this, we design the coflow polling greedy scheduling (CPGS) algorithm, which not only considers the sequence of coflow scheduling, but more importantly maximizes concurrent flows by MIS search. We deploy three different simulation scenarios to evaluate the algorithm performance. Simulation results show that our algorithm can significantly reduce the CCT by about 28.9% to 42.1% compared with existing works.

Low earth orbit (LEO) constellation network is a crucial component and paradigm for big data applications in the future satellite Internet. However, the characteristic of multi-hop transmission significantly increases the data retrieval delay and energy consumption depending on the inter-satellite communications. To mitigate this issue, this paper explores encoding redundancy by reed-solomon (RS) codes to generate the data and parity blocks, and store them in the satellite nodes of LEO constellation. We propose a fast data retrieval strategy, involving three stages: data collection, parity block placement, and data retrieval. Through the derivations of delay and energy consumption, we find that both are intensively related to the placement of parity blocks. To reduce energy consumption during the data retrieval process, we formulate a minimum problem under the delay constraint, which is an integer nonlinear programming problem. Then, we design an energy-efficient parity block placement based on genetic algorithm (PBP-GA), which is heuristic with fast convergence property. Simulation results show that, PBP-GA achieves a comprehensive performance improvement in average data retrieval delay and total energy consumption, compared to other placement schemes, i.e., random placement, retrieval cluster priority placement, nearby placement and non-coding. Specifically, PBP-GA can find the optimal number of parity blocks in a practical scenario of data retrieval in LEO constellation.

Low earth orbit (LEO) computing-aware networks (LCANs) are proposed as an intelligent information infrastructure providing a solution for delay-sensitive computing tasks worldwide. The utilization of distributed computing architecture in an LCAN is emerging as a prospective resolution to cope with the limited computational resources of single satellite. Distributed computing depends on the exchange of information between worker nodes, as a type of concurrent and interrelated data flows called coflow. However, huge delay of coflow transmission is caused by the time-varying network topology and dynamic ISL conditions in an LCAN. To solve this problem, we establish an LCAN topology model, elaborating the orbit movement and ISL connectivity. Then we propose a novel time-varying graph to depict coflow transmission, which can improve the adaptability of coflow routing. Based on the proposed time-varying graph, we formulate coflow routing problem as a path combinatorial optimization and present an iterative heuristic algorithm named dynamic priority coflow routing (DPCoR). The DPCoR can dynamically adjust the priorities of coflow according to their increments to CCT, and thereby ensure that flows with high priorities for better routing paths. Furthermore, we compare DP-CoR with traditional flow routing schemes, i.e., equal-cost multi-path routing (ECMP) and software defined routing algorithm (SDRA) in various LCAN scenarios with different numbers of worker nodes, workloads and link conditions. The simulation results demonstrated that DPCoR algorithm can reduce the coflow completion time (CCT) effectively.

The LEO storage constellation (LSC) has gained significant popularity thanks to its inter-satellite massive con-nectivity and space-terrestrial integrated data storage capability. However, the satellite disks will fail occasionally due to exhausting energy or space debris, which leads to data loss and network unavailable. In terrestrial data centers, aggregation coded repair (ACR) is an emerging data repair technique, which can reduce repair traffic by aggregating source data flows on intermediate nodes. However, existing ACR research does not focus on the problems of large propagation distance and energy consumption constraints in LSC. In this paper, we propose the coding path tree (CPT) model, which is a staged tree graph containing aggregation vectors and distance-related edge weights. For reducing repair delay and energy cost, we further propose the Delay-Sensitive Energy-Efficient ACR (DE-ACR) scheme, which is based on a CPT construction algorithm that combines the ideas of the shortest path and minimum Steiner tree. System-level experiment demonstrates that DE-ACR obtains a 7% reduction in repair delay compared to the single repair pattern tree (SRPT), and achieves a 55 % decrease in energy consumption compared to the shortest path ACR (SP-ACR) in LSC.

Coding techniques, known as coded distributed computing (CDC), have been investigated to alleviate the impact of heterogeneous straggler effects and reduce computation latency in distributed computing systems. However, in the multi-hop complicated network topology, the execution latency of the master's task includes both the computation latency and the communication latency, in which the imbalance computation loads and inadequate path selection will lead to the greater straggler effects extremely. In this paper, we focus on the issues of CDC application in a Two-Hop Heterogeneous Computation Network (THHCN). To make full use of the completed computing results of workers, we deploy Luby transform (LT) code to derive a total execution latency expression. Then, we formulate an optimization problem to minimize the total execution latency by selecting the relays and allocating the computation loads for different workers. Furthermore, a greedy minimum penalty relay selection and load allocation (GMPRS-LA) algorithm is proposed with lower complexity compared to the exhaustive searching to solve the integer nonlinear programming problem. Simulation results demonstrate GMPRS-LA achieves a significant reduction in the total execution latency and leads to a better performance than traditional CDC load allocation algorithms.

Abstract Within the federated learning (FL) framework, the client collaboratively trains the model in coordination with a central server, while the training data can be kept locally on the client. Thus, the FL framework mitigates the privacy disclosure and costs related to conventional centralized machine learning. Nevertheless, current surveys indicate that FL still has problems in terms of communication efficiency and privacy risks. In this paper, to solve these problems, we develop an FL framework with communication-efficient and privacy-preserving (FLCP). To realize the FLCP, we design a novel compression algorithm with efficient communication, namely, adaptive weight compression FedAvg (AWC-FedAvg). On the basis of the non-independent and identically distributed (non-IID) and unbalanced data distribution in FL, a specific compression rate is provided for each client, and homomorphic encryption (HE) and differential privacy (DP) are integrated to provide demonstrable privacy protection and maintain the desirability of the model. Therefore, our proposed FLCP smoothly balances communication efficiency and privacy risks, and we prove its security against “honest-but-curious” servers and extreme collusion under the defined threat model. We evaluate the scheme by comparing it with state-of-the-art results on the MNIST and CIFAR-10 datasets. The results show that the FLCP performs better in terms of training efficiency and model accuracy than the baseline method.

The dynamic mechanism of joint proactive caching and cache replacement, which involves placing content items close to cache-enabled edge devices ahead of time until they are requested, is a promising technique for enhancing traffic offloading and relieving heavy network loads. However, due to limited edge cache capacity and wireless transmission resources, accurately predicting users’ future requests and performing dynamic caching is crucial to effectively utilizing these limited resources. This paper investigates joint proactive caching and cache replacement strategies in a general mobile edge computing (MEC) network with multiple users under a cloud-edge-device collaboration architecture. The joint optimization problem is formulated as a markov decision process (MDP) problem with an infinite range of average network load costs, aiming to reduce network load traffic while efficiently utilizing the limited available transport resources. To address this issue, we design an Attention Weighted Deep Deterministic Policy Gradient (AWD2PG) model, which uses attention weights to allocate the number of channels from server to user, and applies deep deterministic policies on both user and server sides for Cache decision-making, so as to achieve the purpose of reducing network traffic load and improving network and cache resource utilization. We verify the convergence of the corresponding algorithms and demonstrate the effectiveness of the proposed AWD2PG strategy and benchmark in reducing network load and improving hit rate.

With the proliferation of RFID-enabled applications, multiple RFID readers (or reader antennas) must be used to provide full coverage to any deployment area beyond the communication range of a single reader. However, reader collision together with tag-to-tag collision seriously degrades the system performance or even blocks out some tags from being read. To address this problem, this paper proposes a time-efficient protocol stack that is tailored to the tag identification in a multi-reader RFID system, which consists of two protocols: one is for eliminating reader collision (RCE) and the other is for avoiding tag-to-tag collision (TCE). In RCE, we enable multiple readers to work in parallel for maximizing the number of tags to be read per unit of time. Where RCE shines is that it well addresses the problem of unbalanced load by each reader due to uneven tag distributions. Namely, in existing work, the readers with fewer tags covered will finish the tag identification earlier than other readers (with more tags). After that, these readers have to wait for all readers until they are done. This is a waste of time. The solution of RCE is to take the reader with the minimum number of tags as the reference and iteratively to update the set of concurrent readers. Besides, in TCE, we use bit-level tag response to resolve tag-to-tag collision and increase the number of useful slots, so does the read throughput. Theoretical analysis and simulation results show that the above two protocols can jointly improve the inventory efficiency and reduce the identification time by more than 50%, in comparison to the state-of-the-art. We validate TIMR’s performance by comparing its results on a real-world library data set with simulated data, demonstrating consistency across both settings.

Orthogonal chirp division multiplexing (OCDM) is a new multi-carrier scheme based on chirp spread spectrum (CSS) recently introduced and shown to be more robust to interference. In this paper, we propose a novel OCDM system based on index modulation (IM). In this scheme, information is conveyed not only byM-ary signal constellation in classic OCDM, but also by subchirp indices activated in accordance with the input bitstream. We design a receiver structure based on single-tap frequency domain equalization (FDE) and maximum likelihood (ML) detection. To address the exponential complexity growth caused by ML detection, we also propose a novel reduced-complexity maximum likelihood (RC-ML) detector. The new detector offers a comparable BER performance to the ML one with a substantially reduced complexity. A theoretical peak-to-average power ratio (PAPR) performance analysis of the new scheme is given to illustrate the advantages of combining OCDM with IM. We provide an extensive performance analysis of the new scheme in terms of bit error rate (BER), diversity gain, and minimum Euclidean distance (MED). Simulation results are presented to demonstrate that the PAPR and BER performances of the proposed scheme are significantly better than those of the OCDM scheme due to the information bits carried by the OCDM subchirp indices. Moreover, our numerical results verify the robustness of the system in the presence of carrier frequency offsets (CFO).

Change detection identifies surface changes on the earth by comparing two images from the same area at different times. To generate smooth change maps, a common method is fusing information from neighboring areas around each pixel. While the conventional fusion methods primarily rely on fixed regular-shaped neighboring areas, which may be inadequate in capturing the diverse and irregular geometric structures of changed ground objects. To address this limitation, we propose a novel Geometric Variation Adaptive Change Detector (GVA-CD), which adaptively adjusts the shape and size of neighboring areas based on the geometrical structure of ground objects. More specifically, we design a new geometric variation adaptive module (GVAM) as a component of GVA-CD. GVAM captures the structure of the ground objects to constructs geometrically flexible neighboring areas for each pixel, enabling the model to adapt to different ground object structures and generate discriminative difference features. We further propose a new difference measurement module to compute the difference between the features of pre-and post-change images by leveraging the adaptive neighboring areas. In addition, the GVA-CD introduces a multi-stage cross-scale fusion mechanism in both feature extraction and change map generation, to enhance the scale adaption ability of the feature extraction and change map generation. Extensive experiments on three large datasets demonstrate that our GVA-CD can outperform existing methods in change detection.

Pre-disaster information storage is crucial for effective disaster response. The discussion regarding deep learning-based Light Detection and Ranging (Lidar) semantic segmentation technology for indoor small items has been ongoing in recent years. However, the methods applicable to large-scale outdoor Lidar datasets for pre-disaster information storage remain limited. This study aims to propose a novel deep learning-based network for city-scale Lidar semantic segmentation to support pre-disaster information storage, called channel attention and normal-based local feature aggregation network (CNLNet). This network is designed to segment common urban land cover objects, including buildings and vegetation. This network incorporates surface normal information and the channel attention mechanism into the RandLA-Net backbone. Ablation studies have been devised to assess the performance of these two features. During the pre-processing step, color information from optical images is fused with Lidar data. The findings demonstrate that CNLNet can enhance the accuracy of the RandLA-Net backbone by improving mIoU at least 1-2%. Including one of these two features also contributes to the backbone’s improved accuracy. Notably, CNLNet outperforms other well-known networks in terms of accuracy with the test of the public Sementic3D dataset. The study further reveals that the proposed network excels in building segmentation, a crucial facet of pre-disaster information storage. Moreover, the results show that spatial resolution, whether at 0.5m or 10m per pixel for optical images, has limited influence on outcomes. One theoretical contribution of this study is the demonstration of the advantages of integrating either surface normal information or a channel attention mechanism to enhance large-scale outdoor Lidar semantic segmentation. Labeled Lidar datasets have been created for training. The practical contribution is that it can optimize disaster response by efficiently facilitating pre-disaster information storage.

Existing hyperspectral cross-domain few-shot learning (FSL) methods focus mainly on elaborating on training strategies or domain alignment algorithms, while paying less attention to the biased meta-knowledge introduced by a large amount of source data and the implicit encouragement of learning target domain-specific attributes. In this paper, from the perspective of disentangled representation learning, a novel cross-domain FSL method based on feature disentanglement (FDFSL) is proposed for hyperspectral image classification (HSIC). Specifically, to suppress the representation biased towards the source data and enable the model to implicitly focus on the inherent knowledge of the target domain, an orthogonal low-rank feature disentanglement method is employed to acquire desired features of source and target pipelines. Furthermore, to preserve more shared and discriminative information from the heterogeneous data space (i.e., the spectral dimensions of the source and target scenes are typically different), a multi-order spectral interaction block based on central position encoding (MICD) is proposed to fully integrate the respective features into the spectral domain, which allows the model to emphasize informative spectral dimensions in a data-driven manner. Finally, to diversify the feature representation space while preventing the model overfitting domain alignment task, a self-distillation scheme is developed to facilitate the acquisition of task-relevant feature components. Extensive experiments and analysis on three public HSI datasets suggest the superiority of the proposed method. The code will be available on the website at https://github.com/Qba-heu/FDFSL.

Unmanned aerial vehicle (UAV) orthoimages and digital surface models (DSMs) can provide valuable insights for semantic segmentation methods in comprehending gully erosion (GE) from diverse perspectives. While the integration of these two modalities has the potential to improve the GE extraction performance, the extent of enhancement primarily depends on the quality of modality-specific features and the synergistic fusion manner employed for integrating features from both modalities. Toward this end, we propose a novel multimodal segmentation method, which is called foreground-driven fusion network (FFNet). Guided by the prototypes of foreground objects (i.e., gullies), the network effectively tackles the challenges from the modality itself and between different modalities, ultimately achieving high-quality GE extraction results. Specifically, a foreground prototype sampling (FPS) module is first devised for precisely sampling foreground prototypes related to gullies from two modalities. Then, a local-global hybrid purification (LHP) module is proposed to effectively mitigate the erroneous activation within each modality at multiple dimensions by leveraging foreground prototypes. Finally, a multimodal foreground synergy (MFS) module is introduced to further activate foreground features and facilitate full complementarity between multimodal foreground features. To validate our network, a comprehensive multimodal dataset for GE extraction is constructed based on UAV orthoimages and DSMs from northeastern China. Furthermore, a public road extraction dataset is employed to evaluate the generalizability of this network. In the experiments conducted on these two datasets, the proposed FFNet exhibits obvious superiority, outperforming the second-best method with an average improvement of 2.55% in terms of intersection over union (IoU) and 2.77% in terms of$F1$-score. These experimental results not only demonstrate the practicality of FFNet in GE extraction tasks, but also highlight its significant advantage in similar road extraction tasks.

Change detection (CD) aims to identify differences in the same scene at different times. With the increasing amount of hyperspectral images (HSIs), more and more change detection techniques use HSIs as the raw data. HSIs often contain redundant bands, where only a few are crucial for CD while others may be detrimental. However, most existing HSI-CD methods extract features directly from full-dimensional HSIs, leading to a degradation of feature discrimination. To tackle this issue, in this paper, we propose an end-to-end hyperspectral image change detection network based on band selection (ECDBS), unlocking the potential synergy between band selection and CD. The network compromises a deep learning based band selection module and cascaded band-specific spatial attention (BSA) blocks. The band selection module selectively retains bands favourable to CD according to the importance of the bands measured based on band correlation. The BSA block tailors the feature extraction strategy for each band based on its feature distribution, allowing extracting sufficient features from each band. Experimental evaluations were conducted on three widely used HSI-CD datasets, demonstrating the effectiveness and superiority of our proposed method over other state-of-the-art techniques.

Recently, the reconfigurable intelligent surface (RIS), capable of adjusting the phase shifts (PSs) of the reflecting signals through its low-cost elements, has emerged as a promising technology for next-generation wireless communications. However, the RIS may be manipulated by an illegal passive attacker (Wyn) due to the shared nature of wireless channels. In this paper, a Wyn-controlled RIS is considered to attack multiple-input single-output (MISO) communications via passive beamforming based on existing localization and Rician factor estimation techniques. Specifically, we propose an alignment cancellation (AC) scheme to minimize the achievable rate (AR), where the closed-form expressions for location, reflecting element number, and PSs are derived. Furthermore, the computational complexity is quantified to evaluate the low-cost characteristics of this algorithm. Simulation results demonstrate that the proposed AC scheme outperforms other benchmark schemes in degrading the AR with efficient and low-complexity designs.

The channel hardening effect is less pronounced in the cell-free massive multiple-input multiple-output (mMIMO) system compared to its cellular counterpart, making it necessary to estimate the downlink effective channel gains to ensure decent performance. However, the downlink training inadvertently creates an opportunity for adversarial nodes to launch pilot spoofing attacks (PSAs). First, we demonstrate that adversarial distributed access points (APs) can severely degrade the achievable downlink rate. They achieve this by estimating their channels to users in the uplink training phase and then precoding and sending the same pilot sequences as those used by legitimate APs during the downlink training phase. Then, the impact of the downlink PSA is investigated by rigorously deriving a closed-form expression of the per-user achievable downlink rate. By employing the min-max criterion to optimize the power allocation coefficients, the maximum per-user achievable rate of downlink transmission is minimized from the perspective of adversarial APs. As an alternative to the downlink PSA, adversarial APs may opt to precode random interference during the downlink data transmission phase in order to disrupt legitimate communications. In this scenario, the achievable downlink rate is derived, and then power optimization algorithms are also developed. We present numerical results to showcase the detrimental impact of the downlink PSA and compare the effects of these two types of attacks.

Cloud data centers (CDCs) have been used as the basic platforms for data storage in industrial scenarios such as smart manufacturing. However, a lack of effective data storage schemes exacerbates reading latency and replicas' inconsistency in the machine tools of smart factories. In this article, we propose a full-replicas scheme (FRS) to attain the low-latency reading and high data consistency required in smart manufacturing. First, inspired by the susceptible–infectious–recovered epidemic model, the network bandwidth usage generated by the FRS is adjusted by the targeted immunization principle. Then, the final breakout rate is derived as a function of the immunization rate, which can reduce the complexity of target immunization implementation in scale-free networks. Finally, the experimental results confirm our theoretical analysis and show that the FRS provides strong consistency with lower client-side reading latency.

Driven by digital twin (DT) technology, the industrial Internet of Things (IIoT) is expanding to open up new frontiers in industrial applications. However, traditional DT modeling approaches require synchronizing massive amounts of data, resulting in high communications overhead and privacy vulnerability. To address this problem, this article proposes a novel DT architecture for IIoT, where the DT can showcase the real-time operating status of the industrial environment. Swarm learning (SL) is an emerging decentralized federated learning (FL) technique that eliminates the need of a centralized server. We present a novel credibility-weighted SL scheme to construct the DT models, which improves data security while ensuring the fairness of participants as opposed to conventional FL. In addition, we develop a DT-assisted deep reinforcement learning algorithm for simultaneously optimizing the system reliability and energy consumption of IIoT. Simulation comparisons demonstrate that the proposed scheme outperforms some state-of-the-art benchmarks in terms of both reliability and energy consumption.

A revolution in advanced manufacturing has been driven by digital technology in the fourth industrial revolution, also known as Industry 4.0, and has resulted in a substantial increase in profits for the industry. In a new paradigm of Industry 5.0, advanced manufacturing will step further and be capable of offering customized products and a better user experience. A number of key enabling technologies are expected to play crucial roles in assisting Industry 5.0 in meeting higher demands of data acquisition and processing, communications, and collaborative robots in the advanced manufacturing process. The aim of this survey is to provide novel insights into advanced manufacturing in Industry 5.0 by summarizing the latest progress of key enabling technologies, such as artificial intelligence of things (AIoT), beyond 5G communications, and collaborative robotics. Finally, key directions for future research to enable this vision to become a reality, such as the industrial metaverse, are outlined.

The use of fifth-generation (5G) communication technology by high-speed trains (HSTs) has a lot of potential to satisfy current needs for high data rates. Therefore, accurate modeling of the HST wireless channels is crucial for the design and performance assessment of the 5G systems. This paper proposes a general three-dimensional (3D) non-stationary small-scale fading model for 5G HST millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) channels, which captures the wireless channel characteristics in different HST operating scenarios. The proposed channel model has two characteristics. Firstly, it incorporates the distribution of overhead line poles along the railway to characterize the periodic scattering components from the poles. Secondly, it represents complex HST operating scenarios as combinations of five types of scattering clusters, namely hills, trees, lakes, buildings, and concrete. Furthermore, the impact of environmental complexity (EC) on channel statistical properties in the 5G HST massive MIMO scenarios is investigated. Afterwards, based on the birth-death process of scattering clusters, the proposed channel model can characterize the channel non-stationarity in the space-time-frequency domain. Simulation results demonstrate that the proposed model effectively captures the channel non-stationarity, the scattering characteristics of overhead line poles, and the impact of different ECs on system performance. The accuracy and practicality of the proposed model are validated through a comparison with measurement results.

Compared to CNN-based methods, Transformer-based methods achieve impressive image restoration outcomes due to their ability to model remote dependencies. However, how to apply Transformer-based methods to the field of blind super-resolution (SR) and further make an SR network adaptive to degradation information is still an open problem. In this paper, we propose a new degradation-aware self-attention-based Transformer model, where we incorporate contrastive learning into the Transformer network for learning the degradation representations of input images with unknown noise. In particular, we integrate both CNN and Transformer components into the SR network, where we first use the CNN modulated by the degradation information to extract local features, and then employ the degradation-aware Transformer to extract global semantic features. We apply our proposed model to several popular large-scale benchmark datasets for testing, and achieve the state-of-the-art performance compared to existing methods. In particular, our method yields a PSNR of 32.43 dB on the Urban100 dataset at ×2 scale, 0.94 dB higher than DASR, and 26.62 dB on the Urban100 dataset at ×4 scale, 0.26 dB improvement over KDSR, setting a new benchmark in this area. The source code is available at:https://github.com/I2-Multimedia-Lab/DSAT/tree/main.

Multivariate time-series anomaly detection is critically important in many applications, including retail, transportation, power grid, and water treatment plants. Existing approaches for this problem mostly employ either statistical models which cannot capture the nonlinear relations well or conventional deep learning (DL) models e.g., convolutional neural network (CNN) and long short-term memory (LSTM) that do not explicitly learn the pairwise correlations among variables. To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed ), for time-series anomaly detection. explicitly captures the pairwise correlations via a correlation learning (MTCL) module based on which a spatial-temporal graph neural network (STGNN) can be developed. Then, by employing a graph convolution network (GCN) that exploits one-and multihop neighbor information, our STGNN component can encode rich spatial information from complex pairwise dependencies between variables. With a temporal module that consists of dilated convolutional functions, the STGNN can further capture long-range dependence over time. A novel anomaly scoring component is further integrated into to estimate the degree of an anomaly in a purely unsupervised manner. Experimental results demonstrate that can detect and diagnose anomalies effectively in general settings as well as enable early detection across different time delays. Our code is available at https://github.com/huankoh/CST-GL.

Millimeter wave (mmWave) technology promises unprecedented capacity and ultra-low latency for wireless communications. However, mmWave systems confront challenges, including high costs, power consumption, and accurate carrier synchronization, significantly limiting mmWave-based applications. The emerging over-the-air modulation (OTAM) technique has recently demonstrated cost-effective and low-power mmWave communication by utilizing channel attenuation difference characteristics to achieve an ASK-like modulation effect. Despite these advancements, the wireless beam modulation (WBM) system based on the OTAM technique suffers from nonlinear interference caused by random phase offsets when supporting multi-node spatial division multiplexing (SDM) access. To address the challenges, we propose a moment-based analysis (MBA) framework to reduce carrier synchronization requirements, enabling the WBM system to linearize nonlinear spatial interference under coarse carrier synchronization. Within the MBA framework, we further develop a moment-based interference cancellation (MBML-IC) algorithm based on the maximum likelihood criterion. The MBML-IC algorithm eliminates interference in the energy domain, thereby supporting multi-node SDM access for the WBM system. Simulation experiments validate the performance improvements regarding the system bit error rate (BER). Besides, the proposed MBA framework and MBML-IC algorithm empower the WBM system to employ lower-precision, cost-effective, and low-power mmWave components, enhancing energy efficiency.

Rendering novel views from captured multi-view images has made considerable progress since the emergence of the neural radiance field. This paper aims to further advance the quality of view synthesis by proposing a novel approach dubbed the neural radiance feature field (NRFF). We first propose a multiscale tensor decomposition scheme to organize learnable features so as to represent scenes from coarse to fine scales. We demonstrate many benefits of the proposed multiscale representation, including more accurate scene shape and appearance reconstruction, and faster convergence compared with the single-scale representation. Instead of encoding view directions to model view-dependent effects, we further propose to encode the rendering equation in the feature space by employing the anisotropic spherical Gaussian mixture predicted from the proposed multiscale representation. The proposed NRFF improves state-of-the-art rendering results by over 1 dB in PSNR on both the NeRF and NSVF synthetic datasets. A significant improvement has also been observed on the real-world Tanks & Temples dataset. Code can be found at https://github.com/imkanghan/nrff.

Network slicing is key to enabling 6G and beyond networks to simultaneously meet the diverse quality of service (QoS) requirements of various services. In network slicing, radio access network (RAN) slicing is essential to establish a functional network slice by connecting mobile devices and mapping virtualized resource units to different slices. This demands an efficient resource allocation scheme that maximizes resource utilization while meeting diverse QoS requirements. In this paper, we propose a new dynamic resource allocation framework that encompasses three types of services. We formulate a dynamic resource allocation problem that features a mixed action space and has both long-term power and instantaneously available resource unit constraints. We propose a deep reinforcement learning (DRL)-based approach referred to as prediction-aided weighted DRL (PW-DRL), which infers the power allocation and user acceptance decisions to maximize a predefined reward function. Additionally, we propose a prediction network that significantly improves the DRL learning process under limited resources by supplying future state information. Simulation results validate that our proposed PW-DRL significantly outperforms state-of-art DRL approaches by achieving the highest long-term reward and fastest convergence.

Recently, coding techniques have been introduced in distributed computing systems, i.e., coded distributed computing (CDC), to alleviate the heterogeneous straggler effect. However, these techniques bring about additional decoding latency impacting on the task completion time. In this paper, we study the issues of load allocation and latency analysis of systematic CDC in heterogeneous computation and communication straggling networks (HCCSNs). In order to exploit the partial works completed by straggling workers, we use the method of block division to accelerate the sub-tasks' results returning from all workers. Moreover, we attempt to leverage the systematic MDS code, which needs fewer decoding operations, to reduce the decoding latency, but it requires prior determining of the systematic blocks and the parity blocks on the master not on the workers. Therefore, in order to minimize both of the execution (communication and computing) latency and decoding latency, we propose two algorithms, i.e., greedy-based binary search algorithm (GBSA) and proportional systematic block allocation (PSBA), to obtain the optimal numbers of blocks and systematic blocks assigned to each worker, respectively. Simulation results are presented to show that GBSA and PSBA outperforms other conventional block allocation schemes in both execution latency and decoding latency with various straggling parameters.

The rapid development of Internet of Things (IoT) applications requires efficient computing and communication resource allocation strategies to streamline the existing network operations. These strategies could be formulated as mixed-integer nonlinear programming (MINLP) problems, where the optimal branch-and-bound (B&B) with the full strong branching (FSB) variable selection policy features an extremely high complexity. We propose inverse reinforcement learning with graph neural networks (GNNIRL) to generate a new variable selection policy that closely matches the FSB variable selection. Without sacrificing the optimality, the GNNIRL can directly infer the variable selection with a significantly lower complexity, which is also verified by simulation.

Coded distributed computing (CDC) has been recently proposed as a promising technique to mitigate the straggler effect in the distributed computing cluster which consists of workers with different computing capabilities, and to reduce the end-to-end task execution latency. However, the heterogeneity of computing and transmission will critically impact the latency performance, especially in the wireless multiple-access network. In this paper, we use CDC over the heterogeneous wireless multipleaccess network (HWMAN) including both computation stragglers and transmission stragglers with various capabilities. In order to reduce the computing task completion latency (computing latency and transmission latency), the optimal stop computing time of workers and the sorting order of result transmission back are obtained via two designed algorithms, namely straggler detection and ordered transmission (SDOT) and worker sorting and ordered transmission (WSOT), respectively, which not only fully utilize the computing results of stragglers, but also improve the total latency performance compared with other existing state-of-theart algorithms.

Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently or transform queried learnable feature vector of a point to the expected color or density. With the aid of geometry guides either in the form of occupancy grids or proposal networks, the number of color neural network evaluations can be reduced from hundreds to dozens in the standard volume rendering framework. However, many evaluations of the color neural network are still a bottleneck for fast NeRF reconstruction. This paper revisits volume feature rendering (VFR) for the purpose of fast NeRF reconstruction. The VFR integrates the queried feature vectors of a ray into one feature vector, which is then transformed to the final pixel color by a color neural network. This fundamental change to the standard volume rendering framework requires only one single color neural network evaluation to render a pixel, which substantially lowers the high computational complexity of the rendering framework attributed to a large number of color neural network evaluations. Consequently, we can use a comparably larger color neural network to achieve a better rendering quality while maintaining the same training and rendering time costs. This approach achieves the state-of-the-art rendering quality on both synthetic and real-world datasets while requiring less training time compared with existing methods.

In smart ocean Internet of Things (IoT) systems, autonomous underwater vehicles (AUVs) are responsible for underwater information collection. Due to the nature of the medium, the acoustic communications for AUVs are of low bandwidth and adverse environmental conditions causing severe transmission problems. In order to realize cross-media transmission from AUVs to the offshore platform, unmanned surface vehicles (USVs) have been suggested to forward the collected information in a coordinated manner. Against this backdrop, this contribution develops a cooperative USV-to-USV (U2U) cross-media cooperative communications scheme. Then, we formulate a rate maximization problem with the objective of optimizing the reputation-aware USV selection strategy. Furthermore, to characterize the impact of the mobility of AUVs/USVs, a long-term dynamic process is constructed. Meanwhile, we also develop an efficient algorithm which transforms the reputation-aided dynamic USVs selection problem into the infinite-time horizon average one restricted by time average rate constraints in the collection of penalty processes with the help of the Lyapunov optimization framework and drift-plus-penalty method. Finally, numerical results are presented to validate the convergence behavior and the performance for the designed dynamic USVs selection algorithm.

With the aim of reducing the transmission latency, this article proposes a scheme of user-assisted base station (BS) caching and cooperative prefetching for high-speed railway (HSR) communications. In the model under consideration, neighboring BSs periodically exchange information, including the coverage area and communication rate, to facilitate content caching and prefetching. As an additional means, users can cache contents that are different from BSs. Specifically, we construct an optimization problem for content caching and prefetching that minimizes the overall transmission latency. Moreover, this problem is decomposed into two subproblems, namely, the one aiming to maximize the available throughput of BSs and the other attempting to maximize the user cache utilization subject to the constraint of the BS cache. We demonstrate that the objective function of the first subproblem is equivalent to a monotone submodular function subject to matroid constraints. Therefore, it can be efficiently solved with a greedy algorithm. Meanwhile, the user cache issue can be viewed as a weighted sum maximization problem. Simulation results are presented to verify that the proposed scheme can not only reduce the average transmission latency but also improve the hit probability and system throughput.

In real-world scenarios, partial information losses of multivariate time series degrade the time series analysis. Hence, the time series imputation technique has been adopted to compensate for the missing values. Existing methods focus on investigating temporal correlations, cross-variable correlations, and bidirectional dynamics of time series, and most of these methods rely on recurrent neural networks (RNNs) to capture temporal dependency. However, the RNN-based models suffer from the common problems of slow speed and high complexity when dealing with long-term dependency. While some self-attention-based models without any recurrent structures can tackle long-term dependency with parallel computing, they do not fully learn and utilize correlations across the temporal and cross-variable dimensions. To address the limitations of existing methods, we propose a novel so-called dual-branch cross-dimensional self-attention-based imputation (DCSAI) model for multivariate time series, which is capable of performing global and auxiliary cross-dimensional analyses when imputing the missing values. In particular, this model contains masked multi-head self-attention-based encoders aligned with auxiliary generators to obtain global and auxiliary correlations in two dimensions, and these correlations are then combined into one final representation through three weighted combinations. Extensive experiments are presented to show that our model performs better than other state-of-the-art benchmarkers on three real-world public datasets under various missing rates. Furthermore, ablation study results demonstrate the efficacy of each component of the model.

Content-based video moment retrieval (CVMR) aims to localize a successive sequence of frames in an untrimmed reference video, called target moment, that is semantically corresponding to a given query video. Current state-of-the-art CVMR methods are mainly developed using frame-level annotation, which is often quite expensive to collect. In this paper, we aim to develop a weakly-supervised CVMR method, which uses coarse-grained video-level annotations during training. Under weak supervision, video localizers require more discriminative frame-level video features. To achieve this goal, we proposed a novel prior, termed low-rank prior, based on an observation that the frame-level feature of a video should have low-rank properties. We demonstrated that the low-rank features are more discriminative and are beneficial to accurately localize the action boundaries. To produce a low-rank feature, we designed a low-rank feature reconstruction (LFR) operator. A new differentiable matrix decomposition approach is proposed to generate the low-rank reconstruction of the input matrix, meanwhile ensuring that the matrix decomposition process is differentiable. Based on the LFR, we developed a new weakly-supervised CVMR model which produces low-rank video representation and performs semantic consistency measures to discover the semantically matched segment in the reference video to the query video. Extensive experiments demonstrate that our method outperforms state-of-the-art weakly-supervised methods consistently and even achieves competing performance to fully-supervised baselines.

Remote sensing (RS) image dehazing is an effective means to enhance the quality of hazy RS images. However, existing dehazing methods are ineffective in dealing with nonhomogeneous RS haze scenes. To tackle this deficiency, we design a multi-model joint estimation (M2JE) module and a self-correcting (SC) module to construct a unified end-to-end network for RS image dehazing, termed the multi-model SC network (M2SCN). Specifically, the M2JE module regards the dehazing process as a multi-model ensemble problem, so as to improve the generalization ability of the model. The SC module can gradually correct the error in the intermedia features extracted by the network, thus enabling the network to deal with nonhomogeneous hazy images. Extensive experiments are conducted to demonstrate that our proposed M2SCN performs favorably against state-of-the-art methods on popular RS image dehazing benchmark datasets.

Recently vision transformer models have become prominent models for a multitude of vision tasks. These models, however, are usually opaque with weak feature interpretability, making their predictions inaccessible to the users. While there has been a surge of interest in the development of post-hoc solutions that explain model decisions, these methods can not be broadly applied to different transformer architectures, as rules for interpretability have to change accordingly based on the heterogeneity of data and model structures. Moreover, there is no method currently built for an intrinsically interpretable transformer, which is able to explain its reasoning process and provide a faithful explanation. To close these crucial gaps, we propose a novel vision transformer dubbed the eXplainable Vision Transformer (eX-ViT), an intrinsically interpretable transformer model that is able to jointly discover robust interpretable features and perform the prediction. Specifically, eX-ViT is composed of the Explainable Multi-Head Attention (E-MHA) module, the Attribute-guided Explainer (AttE) module with the self-supervised attribute-guided loss. The E-MHA tailors explainable attention weights that are able to learn semantically interpretable representations from tokens in terms of model decisions with noise robustness. Meanwhile, AttE is proposed to encode discriminative attribute features for the target object through diverse attribute discovery, which constitutes faithful evidence for the model predictions. Additionally, we have developed a self-supervised attribute-guided loss for our eX-ViT architecture, which utilizes both the attribute discriminability mechanism and the attribute diversity mechanism to enhance the quality of learned representations. As a result, the proposed eX-ViT model can produce faithful and robust interpretations with a variety of learned attributes. To verify and evaluate our method, we apply the eX-ViT to several weakly supervised semantic segmentation (WSSS) tasks, since these tasks typically rely on accurate visual explanations to extract object localization maps. Particularly, the explanation results obtained via eX-ViT are regarded as pseudo segmentation labels to train WSSS models. Comprehensive simulation results illustrate that our proposed eX-ViT model achieves comparable performance to supervised baselines, while surpassing the accuracy and interpretability of state-of-the-art black-box methods using only image-level labels.

The goal of human pose transfer is to transfer the human in the image from the original pose to the desired one. Existing methods utilizing progressive manner have achieved great success. However, they fail to remove background distraction and preserve appearance details in synthesized images since the correlation between the image and pose is not fully exploit. To this end, we propose a novel progressive cross-modal fusion network (PCFN), which consists of multiple cascaded cross-modal fusion blocks (CMFBs). Each CMFB comprises a feature fusion module (FFM) and a cross-modal module (CMM) to take full advantage of appearance and shape information. From an overall perspective, FFM fully exploits the correlation between image features and pose features through the residual gated convolution. Benefitting from feature integration and dynamic selection, CMFB can extract useful information from the image-pose stream. From a local perspective, CMM utilizes the feature-conditioned gated convolution and the pose-guided heterogeneous attention mechanism to update all codes in a crossing manner and enhance the interaction between fusion information and structural information. Qualitative and quantitative experiments demonstrate the superiority of PCFN compared to state-of-the-art methods, which can transfer the correct human features and increase the authenticity of the generated images. At the same time, PCFN can also be applied to supplement the dataset for person re-identification (ReID). PCFN works well for human pose transfer, and our usage of the gated convolution and the attention mechanism also provides references for other conditional generation tasks.

Landslide is one of the most dangerous and frequently occurred natural disasters. The semantic segmentation technique is efficient for wide area landslide identification from high-resolution remote sensing images (HRSIs). However, considerable challenges exist because the effects of sediments, vegetation, and human activities over long periods of time make visually blurred old landslides very challenging to detect based upon HRSIs. Moreover, for terrain features like slopes, aspect and altitude variations cannot be sufficiently extracted from 2-D HRSIs but can be from digital elevation model (DEM) data. Then, a feature-fusion based semantic segmentation network (FFS-Net) is proposed, which can extract texture and shape features from 2-D HRSIs and terrain features from DEM data before fusing these two distinct types of features in a higher feature layer. To segment landslides from background, a multiscale channel attention module is purposely designed to balance the low-level fine information and high-level semantic features. In the decoder, transposed convolution layer replaces original mathematical bilinear interpolation to better restore image resolution via learnable convolutional kernels, and both dropout and batch normalization (BN) are introduced to prevent over-fitting and accelerate the network convergence. Experimental results are presented to validate that the proposed FFS-Net can greatly improve the segmentation accuracy of visually blurred old landslides. Compared to U-Net and DeepLabV3+, FFS-Net can improve the mean intersection over union (mIoU) metric from 0.508 and 0.624 to 0.67, the F1 metric from 0.254 and 0.516 to 0.596, and the pixel accuracy (PA) metric from 0.874 and 0.906 to 0.92, respectively. For the detection of visually distinct landslides, FFS-NET also offers comparable detection performance, and the segmentation is improved for visually distinct landslides with similar color and texture to surroundings.

The geological characteristics of old landslides can provide crucial information for the task of landslide protection. However, detecting old landslides from high-resolution remote sensing images (HRSIs) is of great challenges due to their partially or strongly transformed morphology over a long time and thus the limited difference with their surroundings. Additionally, small-sized datasets can restrict in-depth learning. To address these challenges, this paper proposes a new iterative classification and semantic segmentation network (ICSSN), which can significantly improve both object-level and pixel-level classification performance by iteratively upgrading the feature extraction module shared by the object classification and semantic segmentation networks. To improve the detection performance on small-sized datasets, object-level contrastive learning is employed in the object classification network featuring a siamese network to realize global features extraction, and a sub-object-level contrastive learning method is designed in the semantic segmentation network to efficiently extract salient features from boundaries of landslides. An iterative training strategy is also proposed to fuse features in the semantic space, further improving both the object-level and pixel-level classification performances. The proposed ICSSN is evaluated on a real-world landslide dataset, and experimental results show that it greatly improves both the classification and segmentation accuracy of old landslides. For the semantic segmentation task, compared to the baseline, the F1 score increases from 0.5054 to 0.5448, the mIoU improves from 0.6405 to 0.6610, the landslide IoU grows from 0.3381 to 0.3743, the PA is improved from 0.945 to 0.949, and the object-level detection accuracy of old landslides surges from 0.55 to 0.90. For the object classification task, the F1 score increases from 0.8846 to 0.9230, and the accuracy score is up from 0.8375 to 0.8875.

The booming of the industrial Internet of Things (IIoT) brings an exponential increase in industrial devices, calling for more flexible and low-cost communications. The fifth generation and beyond (B5G) communication technologies provide a dedicated solution by supporting two industry-targeted technologies: Massive machine-type communications (mMTC) and ultra reliable low-latency communications (URLLC). In this article, we design a B5G-aided quality test system in advanced manufacturing, where various sensors are connected to the base station (BS) and send contextual information via mMTC. The BS and quality test machine transmit short length commands and small size feedback to each other, respectively, via URLLC. We formulate a long-term optimization problem to improve the product qualification rate by maximizing the expected average reward with limited testing capacity and changing configurations. To address this problem, we develop a novel context-aware combinatorial quality test (CC-QT) algorithm based on bandit learning (BL), which integrates contextual information to predict the product quality, and a combinatorial method to decrease the complexity of the BL process. Furthermore, we derive a performance upper bound of the proposed CC-QT and analyze its computational complexity. Experimental results illustrate the performance of CC-QT and substantiate its superiority over the existing algorithms.

The accelerated development of the Industrial Internet of Things (IIoT) is catalyzing the digitalization of industrial production to achieve Industry 4.0. In this article, we propose a novel digital twin (DT) empowered IIoT (DTEI) architecture, in which DTs capture the properties of industrial devices for real-time processing and intelligent decision making. To alleviate data transmission burden and privacy leakage, we aim to optimize federated learning (FL) to construct the DTEI model. Specifically, to cope with the heterogeneity of IIoT devices, we develop the DTEI-assisted deep reinforcement learning method for the selection process of IIoT devices in FL, especially for selecting IIoT devices with high utility values. Furthermore, we propose an asynchronous FL scheme to address the discrete effects caused by heterogeneous IIoT devices. Experimental results show that our proposed scheme features faster convergence and higher training accuracy compared to the benchmark.

Image dehazing is an effective means to enhance the quality of images captured in foggy or hazy weather conditions. However, existing image dehazing methods are either ineffective in dealing with complex haze scenes, or incurring too much computation. To overcome these deficiencies, we propose a progressive feedback optimization network (PFONet) which is lightweight yet effective for image dehazing. The PFONet consists of a multi-stream dehazing module and a progressive feedback module. The progressive feedback module feeds the output dehazed image back to the intermedia features extracted by the network, thus enabling the network to gradually reconstruct a complex degraded image. Considering both the effectiveness and efficiency of the network, we also design a lightweight hybrid residual dense block serving as the basic feature extraction module of the proposed PFONet. Extensive experimental results are presented to demonstrate that the proposed model outperforms its state-of-the-art single-image dehazing competitors for both synthetic and real-world images.

Grant-free random access is an effective solution to enable massive access for future Internet of Vehicles (IoV) scenarios based on massive machine-type communication (mMTC). Considering the uplink transmission of grant-free based vehicular networks, vehicular devices sporadically access the base station, the joint active device detection (ADD) and channel estimation (CE) problem can be addressed by compressive sensing (CS) recovery algorithms due to the sparsity of transmitted signals. However, traditional CS-based algorithms present high complexity and low recovery accuracy. In this manuscript, we propose a novel alternating direction method of multipliers (ADMM) algorithm with low complexity to solve this problem by minimizing the$\ell _{2,1}$norm. Furthermore, we design a deep unfolded network with learnable parameters based on the proposed ADMM, which can simultaneously improve convergence rate and recovery accuracy. The experimental results demonstrate that the proposed unfolded network performs better performance than other traditional algorithms in terms of ADD and CE.

Integrating mobile edge computing (MEC) in the ultra-dense network (UDN) is a key enabler to meet the service demand by allowing smart devices to perform uninterrupted task offloading via densely deployed MEC servers. In most cases, the smart devices randomly move around the whole network. Consequently, the popular ‘`MEC-centralized decision’' offloading approach could be inapplicable, as joint decision-making among multiple MEC servers becomes difficult due to time synchronization and information exchange overhead. In this paper, we take a user-centric approach to minimize a long-term delay for a given task duration under a price budget constraint. To address this problem, we develop a novel contextual sleeping bandit learning (CSBL) algorithm, which integrates contextual information and sleeping characteristic to accelerate the learning convergence and leverage Lyapunov optimization to deal with the price budget constraint. Furthermore, we extend to a multiple offloading scenario where multiple MEC servers can be selected in each offloading round and propose a CSBL-multiple (CSBL-M) algorithm to address the exponential increase of the offloading selections. For both CSBL and CSBL-M, we derive the upper bounds of learning regret and provide rigorous proofs that they asymptotically approach the Oracle algorithm within bounded deviations for finite task duration.

Considering that the human brain always follows a coarse-to-fine (low-to-high spatial frequency) visual processing and fusion mechanism, we propose a coarse-to-fine feedback guidance based stereo image quality assessment (SIQA) network which considers a coarse-to-fine feedback guidance and adaptive dominant eye mechanism. The proposed network consists of two main sub-network streams, each of which has three branches to extract low, middle and high spatial frequency information in parallel. To better realize the guidance of the high-level features in the low spatial frequency branch to the low-level features in the high spatial frequency branch, an information feedback guidance module (IFGM) is proposed, which realizes a top-down guidance mechanism in each sub-network stream. Simultaneously, according to the theory of ocular dominance in human visual system (HVS), we design an adaptive bi-directional parallax-based binocular fusion module (BPBFM), which synthesizes two types of fusion feature by taking the left and right view features as dominant eye input. Furthermore, in order to obtain the better perceptual quality of stereo images, we design a weighted fusion strategy to weigh the quality scores from the two types of fusion features obtained by using an ensemble model with two multi-layer perceptrons (MLPs). The experimental results on four public stereo image datasets show that the proposed method is superior to the mainstream metrics and achieves an excellent performance.

The task of video-query based video moment retrieval (VQ-VMR) aims to localize the segment in the reference video, which matches semantically with a short query video. This is a challenging task due to the rapid expansion and massive growth of online video services. With accurate retrieval of the target moment, we propose a new metric to effectively assess the semantic relevance between the query video and segments in the reference video. We also develop a new VQ-VMR framework to discover the intrinsic semantic relevance between a pair of input videos. It comprises two key components: a Fine-grained Feature Interaction (FFI) module and a Semantic Relevance Measurement (SRM) module. Together they can effectively deal with both the spatial and temporal dimensions of videos. First, the FFI module computes the semantic similarity between videos at a local frame level, mainly considering the spatial information in the videos. Subsequently, the SRM module learns the similarity between videos from a global perspective, taking into account the temporal information. We have conducted extensive experiments on two key datasets which demonstrate noticeable improvements of the proposed approach over the state-of-the-art methods.

In this paper, we propose a novel maximum distance separable (MDS) code based and reconfigurable intelligent surface (RIS) assisted wireless communication system with orthogonal frequency division multiplexing (OFDM). Specifically, input bits are firstly divided into groups and their MDS codes are utilized to decide the amplitudes and phases of subcarriers. The introduction of the MDS code helps to increase the minimum Hamming distance between symbols and improve on the capability of error detection. Besides, the RIS is adopted to create additional paths between the radio frequency (RF) and the receiver as well as alter the signal phases with derived optimal solution. Benefiting from the strength of the RIS, the proposed system can better overcome multipath fading compared with conventional systems. Simulation results are presented to demonstrate the efficacy of the proposed system in terms of reducing bit error rate (BER) through multipath channels.

The industrial Internet of Things (IIoT) interconnects an exponential number of industrial devices, and more flexible and low-cost communications are widely in demand. The fifth-generation (5G) communication provides two industrial-target technologies, massive machine-type communications (mMTC) and ultra-reliable low-latency communications (URLLC), to meet the demand. We design a 5G-aided quality test system, where various sensors are connected to the base station (BS) and send contextual information via mMTC. The BS and quality test machine transmit short-length commands and small-size feedback to each other via URLLC. The problem is formulated as a long-term optimization one with the purpose of improving the product qualification rate. We develop a novel contextual combinatorial quality test (CC-QT) algorithm to solve the problem. We further derive a performance upper bound of the proposed CC-QT and analyze its computational complexity. Experimental results illustrate the performance of CC-QT and substantiate its superiority over the existing algorithms.

The Internet of Vehicles (IoV) can offer safe and comfortable driving experience, by the enhanced advantages of space–air–ground-integrated networks (SAGINs), i.e., global seamless access, wide-area coverage, and flexible traffic scheduling. However, due to the huge popular traffic volume, limited cache/power resources, and the heterogeneous network infrastructures, the burden of backhaul link will be seriously enlarged, degrading the energy efficiency of IoV in SAGIN. In this article, to implement the popular content severing multiple vehicle users (VUs), we consider a cache-enabled satellite-UAV-vehicle-integrated network (CSUVIN), where the geosynchronous Earth orbit (GEO) satellite is regard as a cloud server, and unmanned aerial vehicles are deployed as edge caching servers. Then, we propose an energy-aware coded caching strategy employed in our system model to provide more multicast opportunities, and to reduce the backhaul transmission volume, considering the effects of file popularity, cache size, request frequency, and mobility in different road sections (RSs). Furthermore, we derive the closed-form expressions of total energy consumption both in single-RS and multi-RSs scenarios with asynchronous and synchronous services schemes, respectively. An optimization problem is formulated to minimize the total energy consumption, and the optimal content placement matrix, power allocation vector, and coverage deployment vector are obtained by well-designed algorithms. We finally show, numerically, our coded caching strategy can greatly improve energy efficient performance in CSUVINs, compared with other benchmarked caching schemes under the heterogeneous network conditions.

Oceanic temperature has a great impact on global climate and worldwide ecosystems, as its anomalies have been shown to have a direct impact on atmospheric anomalies. The major parameter for measuring the thermal energy of oceans is the sea surface temperature (SST). SST prediction plays an essential role in climatology and ocean-related studies. However, SST prediction is challenging due to the involvement of complex and nonlinear sea thermodynamic factors. To address this challenge, we design a novel ensemble of two stacked deep neural networks (DNNs) that uses air temperature, in addition to water temperature, to improve the SST prediction accuracy. To train our model and compare its accuracy with the state-of-the-art, we employ two well-known datasets from the national oceanic and atmospheric administration as well as the international Argo project. Using DNNs, our proposed method is capable of automatically extracting required features from the input time series and utilizing them internally to provide a highly accurate SST prediction that outperforms state-of-the-art models.

Capturing the directions of light by light field cameras powers next-generation immersive multimedia applications. A critical problem in taking advantage of the rich visual information in light field images is depth estimation. Conventional light field depth estimation methods build a cost volume that measures the photo-consistency of pixels refocused to a range of depths, and the highest consistency indicates the correct depth. This strategy works well in most regions but usually generates blurry edges in the estimated depth map due to occlusions. Recent work shows that integrating occlusion models to light field depth estimation can largely reduce blurry edges. However, existing occlusion handling methods rely on complex edge-aided processing and post-refinement, and this reliance limits the resultant depth accuracy and impacts on the computational performance. In this paper, we propose a novel occlusion-aware vote cost (OAVC) which is able to accurately preserve edges in the depth map. Instead of using photo-consistency as an indicator of the correct depth, we construct a novel cost from a new perspective that counts the number of refocused pixels whose deviations from the central-view pixel are less than a small threshold, and utilizes that number to select the correct depth. The pixels from occluders are thus excluded in determining the correct depth. Without the use of any explicit occlusion handling methods, the proposed method can inherently preserve edges and produces high-quality depth estimates. Experimental results show that the proposed OAVC outperforms state-of-the-art light field depth estimation methods in terms of depth estimation accuracy and computational complexity.

Sparse code multiple access (SCMA) is a promising non-orthogonal multiple access technique to support massive connectivity for future wireless Internet of Things (IoT) networks. As the main feature of SCMA, modulation and spread spectrum is embedded into codebook mapping, offering significant codebook shaping gains to mitigate inter-cell interference. Maximizing the constellation-constrained average mutual information (AMI) is an effective way for SCMA codebook optimization. However, deriving a closed-form expression of the AMI is analytically intractable, while it is computationally costly to estimate the AMI by numerical methods. To address this challenge, this paper first derives a lower bound of the AMI with a closed-form expression. On this basis, we propose a novel codebook optimization method referred to as joint bare bones particle swarm optimization (JBBPSO) through maximizing the AMI lower bound. The proposed low-complexity method jointly optimizes the mother codebook including basic constellation and other non-zero-dimensional constellations, and the rotation angles of multiple users. Numerical results show that our proposed optimized codebooks outperform the state-of-the-art SCMA codebooks in terms of both the lower bound and the error performance.

Sparse code multiple access (SCMA) technology has been widely studied thanks to its outstanding overload performance, which provides greater device access on limited time-frequency resources. We propose a variational learning based end-to-end SCMA network model termed as V-SCMA. In our model, SCMA codebooks are generated by a deep neural network (DNN) encoder. Motivated by the idea of variational learning, we derive the posterior probability of SCMA codeword send by each user from the point view of binary coding using the variational method. Then, we design an SCMA decoding network to learn this process of approaching the real posterior probability. The SCMA decoding network designed by us is a truncated recurrent neural network, which is simpler than other networks. In addition, a novel loss function is proposed to optimize V-SCMA. Compared with previous works, the new loss function is a tighter variational lower bound which improves the BER performance. Simulation results show that the proposed V-SCMA offers a better bit error rate (BER) performance and a lower computational complexity than conventional schemes.

This paper presents a novel deep learning-aided scheme dubbed$PR\rho $-net for improving the bit error rate (BER) of the Time Reversal (TR) Ultra-Wideband (UWB) Multiple Input Multiple Output (MIMO) system with imperfect Channel State Information (CSI). The designed system employs Frequency Division Duplexing (FDD) with explicit feedback in a scenario where the CSI is subject to estimation and quantization errors. Imperfect CSI causes a drastic increase in BER of the FDD-based TR-UWB MIMO system, and we tackle this problem by proposing a novel neural network-aided design for the conventional precoder at the transmitter and equalizer at the receiver. A closed-form expression for the initial estimation of the channel correlation is derived by utilizing transmitted data in time-varying channel conditions modeled as a Markov process. Subsequently, a neural network-aided design is proposed to improve the initial estimate of channel correlation. An adaptive pilot transmission strategy for a more efficient data transmission is proposed that uses channel correlation information. The theoretical analysis of the model under the Gaussian assumptions is presented, and the results agree with the Monte-Carlo simulations. The simulation results indicate high performance gains when the suggested neural networks are used to combat the effect of channel imperfections.

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in hyperspectral images (HSIs) classification, which is widely used for the analysis of remotely sensed images. HSI includes spectral and spatial information from several hundreds of spectral data channels. Recent CNN models deal with various bands of HSIs as independent channels, which may lead to the loss of dependencies between different channels or the loss of associated information between each channel and the global. This article proposes a novel CNN model based on geometric algebra (GA), dubbed GA-CNN, to process the HSIs in a holistic way without losing the interrelationship among channels. Specifically, taking advantage of GA, different band images are represented as GA multivectors to capture the inherent structures and preserve the correlation of those channels. In particular, all the basic modules of our model, such as convolutional layers and the backpropagation algorithm, are extended to the GA domain. We evaluate the performance of the proposed GA-CNN model in classification tasks on four well-known HSI datasets. The experimental results indicate that our GA-CNN model outperforms traditional and state-of-the-art real-valued CNNs with higher classification accuracy and fewer model parameters.

Soil moisture is a crucial parameter of hydrological processes as it affects the exchange of water and heat at the land/atmosphere interface. Regional hydrological applications (floods and modeling of small basins) and agricultural applications (irrigation and agricultural land mapping) require daily soil moisture (SM) values having a spatial resolution of at least 1-km. This requirement is currently unmet by existing satellite missions. Notably, SM has variability over three dimensions. As such, accurate prediction of satellite SM requires multiple bidirectional spectra-spatiotemporal analyses. However, current state-of-the-art SM downscaling models can not yet fulfill this requirement. This paper proposes a new bi-directional LSTM model dubbed the three-dimensional bi-directional LSTM (3D-Bi-LSTM), which downscales the Soil Moisture Active Passive (SMAP) global daily 9-km SM to daily 1-km SM. In the proposed downscaling model, the region-specific soil moisture indices (SMIs) are first extracted using a covariance-adaptive convolutional neural network (CNN) to support the extraction of important distinctive information from multispectral data. Next, the CNN output is provided to the 3D-Bi-LSTM to perform the bi-directional analysis of spatial correlation within a feature and spectral correlation between features over multiple time instants. Experimental results demonstrate the proposed model outperforms state-of-the-art networks. An ablation study, transferability assessment, and feature importance study further demonstrate the proposed 3D-Bi-LSTM’s efficiency.

Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation. Due to the long and thin shape as well as the shades induced by vegetation and buildings, small-sized roads are more difficult to discern. In order to improve the reliability and accuracy of small-sized road extraction when roads of multiple sizes coexist in an HRSI, an enhanced deep neural network model termed Dual-Decoder-U-Net (DDU-Net) is proposed in this paper. Motivated by the U-Net model, a small decoder is added to form a dual-decoder structure for more detailed features. In addition, we introduce the dilated convolution attention module (DCAM) between the encoder and decoders to increase the receptive field as well as to distill multi-scale features through cascading dilated convolution and global average pooling. The convolutional block attention module (CBAM) is also embedded in the parallel dilated convolution and pooling branches to capture more attention-aware features. Extensive experiments are conducted on the Massachusetts Roads dataset with experimental results showing that the proposed model outperforms the state-of-the-art DenseUNet, DeepLabv3+ and D-LinkNet by 6.5%, 3.3%, and 2.1% in the mean Intersection over Union (mIoU), and by 4%, 4.8%, and 3.1% in the F1 score, respectively. Both ablation and heatmap analysis are presented to validate the effectiveness of the proposed model. Moreover, the designed small decoder and introduced DCAM can be used as a portable module to be embedded in other U-Net-like models with encoder-decoder structure to enhance the road detection performance, especially for small-sized roads. The high portability of the designed module is validated by embedding in the LinkNet, which greatly improves the road segmentation performance.

Light field cameras can capture the radiance and direction of light rays by a single exposure, providing a new perspective to photography and 3D geometry perception. However, existing sub-aperture based light field cameras are limited by their sensor resolution to obtain high spatial and angular resolution images simultaneously. In this paper, we propose an inference-reconstruction variational autoencoder (IR-VAE) to reconstruct a dense light field image out of four corner reference views in a light field image. The proposed IR-VAE is comprised of one inference network and one reconstruction network, where the inference network infers novel views from existing reference views and viewpoint conditions, and the reconstruction network reconstructs novel views from a latent variable that contains the information of reference views, novel views, and viewpoints. The conditional latent variable in the inference network is regularized by the latent variable in the reconstruction network to facilitate information flow between the conditional latent variable and novel views. We also propose a statistic distance measurement dubbed the mean local maximum mean discrepancy (MLMMD) to enable the measurement of the statistic distance between two distributions with high-resolution latent variables, which can capture richer information than their low-resolution counterparts. Finally, we propose a viewpoint-dependent indirect view synthesis method to synthesize novel views more efficiently by leveraging adaptive convolution. Experimental results show that our proposed methods outperform state-of-the-art methods on different light field datasets.

The rapid development of 5G and Internet-of-Things catalyzes ever-increasing computation-intensive and delay-sensitive applications demanding ubiquitous computation services. Integrating mobile edge computing (MEC) in the ultra-dense network (UDN) is a key enabler to meet the service demand by allowing smart devices to perform uninterrupted task offloading via densely deployed MEC servers. In this paper, we take a user-oriented approach to minimize a long-term delay for a given task duration under a price budget constraint. To address this problem, we develop a novel contextual sleeping bandit learning (CSBL) algorithm, which integrates context information and sleeping bandit theory to handle the fast changing environment and leverages Lyapunov optimization to deal with the price budget. We derive the upper bound of learning regret and provide a rigorous proof that CSBL asymptotically approaches the Oracle algorithm within bounded deviations for finite task duration. Simulation results illustrate that CSBL significantly outperforms existing algorithms.

The unpredictability of seizures continues to distress many people with drug-resistant epilepsy. On account of recent technological advances, considerable efforts have been made using different hardware technologies to realize smart devices for the real-time detection and prediction of seizures. In this paper, we investigate the feasibility of using Memristive Deep Learning Systems (MDLSs) to perform real-time epileptic seizure prediction on the edge. Using the MemTorch simulation framework and the Children's Hospital Boston (CHB)-Massachusetts Institute of Technology (MIT) dataset we determine the performance of various simulated MDLS configurations. An average sensitivity of 77.4% and a Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.85 are reported for the optimal configuration that can process Electroencephalogram (EEG) spectrograms with 7,680 samples in 1.408ms while consuming 0.0133W and occupying an area of 0.1269mm2in a 65nm Complementary Metal-Oxide-Semiconductor (CMOS) process.

Ultra-dense computation services are widely distributed in various application scenarios with the rapid development of artificial intelligence and machine learning. Relying on the existing ground cellular networks, it is challenging to satisfy the 6G vision of full coverage and massive machine connectivity. Satellite-terrestrial integrated network (STIN) has abundant computation resources and seamless coverage ability, which can be served as an effective supplementary for the task allocating in cellular networks. Nevertheless, STIN has the characteristic of architecture complexity, unavoidable stragglers and high economic costs. The rational computation resource allocation among distributed on-orbit satellites becomes an urge problem, synthesizing these drawbacks in STINs. In this paper, to address these issues, we attempt to design a coded computation offloading strategy (CCOS) to migrate ground ultra-dense computing tasks to distributed satellite constellations in space. Considering the effect of unpredictable computation resource occupation on satellites, we investigate two coded computation methods, i.e., maximum distance separable (MDS) code and rateless code, to resist the random stragglers occurring on satellite nodes. Then, we formulate the optimization problem about minimizing the delay-energy tradeoff cost with different CCOSs under the tolerant time constraints, and obtain the optimal task offloading decisions (i.e., executing locations and coding parameters) using a proposed low-cost offloading decision searching algorithm (LODSA). Numerical simulation results show that, our coded computation strategies can significantly eliminate the effect of stragglers, and improve the cost performance obviously compared with the un-coded strategies in typical application cases.

Orthogonal time frequency space (OTFS) is a multi-carrier technique where a time-varying channel can be converted into a time-invariant channel in the delay-Doppler (DD) domain through a two-dimensional transformation. In practical wireless systems, due to the non-biorthogonal waveforms, the inter-carrier interference (ICI) will bring up phase shifts related to Doppler shifts, so that the channel in the DD domain is no longer invariant. Moreover, the limited frame durations will lead to channel dispersion, which makes it more difficult to estimate Doppler shifts. However, existing channel estimation schemes for OTFS are unable to accurately estimate the Doppler shifts. In this paper, we propose a novel channel estimation scheme. Firstly, we estimate Doppler shifts by linear fitting based on the channel dispersion in the DD domain. Then we calculate the power of dispersion paths as combining coefficients to obtain channel fading. Simulation results show that the proposed scheme can significantly reduce the normalized mean square error compared with conventional schemes, especially if Doppler shifts are large.

Unmanned aerial vehicles (UAVs) have been widely used in wireless edge networks for task offloading, with the advantages of their agile management and high-flexibility deployment. However, due to limited computation capability and restricted battery life, processing computation-intensive tasks on board may cause the excessive cost of latency and energy. In this paper, we propose a novel framework with coded distributed computing (CDC) for the task offloading from multi-UAV to ground edge servers, which can save transmitting and flying energy consumption in the air, and reduce computation latency in the terrestrial distributed server networks with stragglers. Specifically, we formulate a latency-energy cost minimization problem, to obtain the optimal the UAVs' trajectory schedule and the appropriate CDC's parameters. Moreover, we divide this problem into two sub-optimization problems, which are solved by a cost optimal trajectory schedule (COTS) algorithm and a cost optimal code parameter design (COCPD) algorithm, respectively. Finally, numerical results indicate the feasibility and the effectiveness of our proposed framework, which also validate that CDC can significantly reduce the cost in the UAV edge computing network.

Abstract In clustered distributed storage systems (CDSSs), one of the main design goals is minimizing the transmission cost during the failed storage nodes repairing. Generalized regenerating codes (GRCs) are proposed to balance the intra‐cluster repair bandwidth and the inter‐cluster repair bandwidth for guaranteeing data availability. The trade‐off performance of GRCs illustrates that, it can reduce storage overhead and inter‐cluster repair bandwidths simultaneously. However, in practical big data storage scenarios, GRCs cannot give an effective solution to handle the heterogeneity of bandwidth costs among different clusters for node failures recovery. This paper proposes an asymmetric bandwidth allocation strategy (ABAS) of GRCs for the inter‐cluster repair in heterogeneous CDSSs. Furthermore, an upper bound of the achievable capacity of ABAS is derived based on the information flow graph (IFG), and the constraints of storage capacity and intra‐cluster repair bandwidth are also elaborated. Then, a metric termed global repair bandwidth cost (GRBC), which can be minimized regarding of the inter‐cluster repair bandwidths by solving a linear programming problem, is defined. The numerical results demonstrate that, maintaining the same data availability and storage overhead, the proposed ABAS of GRCs can effectively reduce the GRBC compared to the traditional symmetric bandwidth allocation schemes.

Microgrids (MGs) are small, local power grids that can operate independently from the larger utility grid. Combined with the Internet of Things (IoT), a smart MG can leverage the sensory data and machine learning techniques for intelligent energy management. This article focuses on deep reinforcement learning (DRL)-based energy dispatch for IoT-driven smart isolated MGs with diesel generators (DGs), photovoltaic (PV) panels, and a battery. A finite-horizon partial observable Markov decision process (POMDP) model is formulated and solved by learning from historical data to capture the uncertainty in future electricity consumption and renewable power generation. In order to deal with the instability problem of DRL algorithms and unique characteristics of finite-horizon models, two novel DRL algorithms, namely, finite-horizon deep deterministic policy gradient (FH-DDPG) and finite-horizon recurrent deterministic policy gradient (FH-RDPG), are proposed to derive energy dispatch policies with and without fully observable state information. A case study using real isolated MG data is performed, where the performance of the proposed algorithms are compared with the other baseline DRL and non-DRL algorithms. Moreover, the impact of uncertainties on MG performance is decoupled into two levels and evaluated, respectively.

Rainfall event forecasting is prominently done using climate models (CMs) to produce multiple forecasts for the same rainfall event. The best forecast is complicated to find and hence has not yet been explored in the CMs. Recent advances in deep learning methods have provided an exceptional ability to investigate intricate weather patterns from big climate data. In this article, a hybrid climate learning model (HCLM) is proposed that utilizes both the CM and the deep learning models for improving the rainfall forecast. More specifically, a probabilistic multilayer perceptron (PMLP) network evaluates multiple forecasts from the CM-generated forecasts and selects the best one. The selected forecast is next passed onto a hybrid deep long short-term memory (HD-LSTM) network, which looks back and learns the relationship of the selected forecast with corresponding rainfall and temperature observations to produce the next-day rainfall forecast. The experimental results from various climate zones in Australia show that the HCLM outperforms existing state-of-the-art climate and deep learning models.

As a promising technology in the Internet of Underwater Things, underwater sensor networks (UWSNs) have drawn a widespread attention from both academia and industry. However, designing a routing protocol for UWSNs is a great challenge due to high energy consumption and large latency in the underwater environment. This article proposes a Q-learning -based localization-free anypath routing (QLFR) protocol to prolong the lifetime as well as reduce the end-to-end delay for UWSNs. Aiming at optimal routing policies, the Q-value is calculated by jointly considering the residual energy and depth information of sensor nodes throughout the routing process. More specifically, we define two reward functions (i.e., depth-related and energy-related rewards) for Q-learning with the objective of reducing latency and extending network lifetime. In addition, a new holding time mechanism for packet forwarding is designed according to the priority of forwarding candidate nodes. Furthermore, mathematical analyses are presented to analyze the performance and computational complexity of the proposed routing protocol. Extensive simulation results demonstrate the superiority performance of the proposed routing protocol in terms of the end-to-end delay and the network lifetime.

This paper proposes a precoded optical space-domain index modulation scheme for indoor visible light communications, which is based on the optimization of the minimum Euclidean distance of optical spatial modulation (OSM) with real-valued modulation constellations. We find that the precoding matrix design can be formulated as a non-convex quadratically constrained quadratic program (QCQP), whose solution is generally intractable. To tackle this problem, we first consider the case of two optical transmit antennas ( Nt= 2) in the precoded OSM and derive a closed-form solution for arbitrary M-order pulse amplitude modulation (PAM). Based on the derived solutions and the error vector reduction method, we then propose a low-complexity iterative (LCI) algorithm to identify the precoding matrix for the setup Nt> 2. To strike a flexible complexity-BER (bit error rate) tradeoff, we propose a successive convex approximation (SCA)-assisted matrix-based optimization method to transform the non-convex QCQP problem into a series of linear convex subproblems, which can be solved by low-complexity solvers. Simulation results show that these proposed algorithms are capable of substantially improving the system error performance compared with conventional OSM systems. Besides, a symbol-based SCA algorithm is introduced and it is shown to outperform the matrix-based SCA and the suboptimal LCI algorithm in terms of the BER.

Massive MIMO systems are vulnerable to pilot spoofing attacks (PSAs) since the estimated channel state information can be contaminated by the eavesdropping link, thus incurring severe information leakage in downlink transmission. To safeguard legitimate communications, this paper proposes a PSA detection method which relies on pilot manipulation. Specifically, users randomly partition pilot sequences into two parts, where the first part remains unchanged and the second one is multiplied with a diagonal matrix. Although a malicious node may follow the same way to send pilots, this makes it more likely to be detected. According to the principle of the likelihood-ratio test, the proposed detector is designed based on a decision metric that does not include the legitimate channel. This feature differentiates our scheme from existing ones and remarkably improves the detection accuracy. Besides, the possibility of performance enhancement by joint detection is discussed. Furthermore, based on pilot manipulation, a jamming-resistant receiver is designed. The key of this receiver is a new channel estimator that is robust to the PSA. Finally, extensive simulations are carried out to validate our proposed algorithms.

Solar forecasting is one of the most promising approaches to address the intermittent photovoltaic (PV) power generation by providing predictions before upcoming ramp events. In this article, a novel multistep forecasting (MSF) scheme is proposed for PV power ramp-rate control (PRRC). This method utilizes an ensemble of deep ConvNets without additional time series models (e.g., recurrent neural network (RNN) or long short-term memory) and exogenous variables, thus more suitable for industrial applications. The MSF strategy can make multiple predictions in comparison with a single forecasting point produced by a conventional method while maintaining the same high temporal resolution. Besides, stacked sky images that integrate temporal-spatial information of cloud motions are used to further improve the forecasting performance. The results demonstrate a favorable forecasting accuracy in comparison to the existing forecasting models with the highest skill score of 17.7%. In the PRRC application, the MSF-based PRRC can detect more ramp-rates violations with a higher control rate of 98.9% compared with the conventional forecasting-based control. Thus, the PV generation can be effectively smoothed with less energy curtailment on both clear and cloudy days using the proposed approach.

The visual quality of magnetic resonance images (MRIs) is crucial for clinical diagnosis and scientific research. The main source of quality degradation is the noise generated during MRI acquisition. Although denoising MRI by deep learning methods shows great superiority compared with traditional methods, the deep learning methods reported to date in the literature cannot simultaneously leverage long-range and hierarchical information, and cannot adequately utilize the similarity in 3D MRI. In this paper, we address the two issues by proposing a deep adaptive blending network (DABN) characterized by a large receptive field residual dense block and an adaptive blending method. We first propose the large receptive field residual dense block that can capture long-range information and fuse hierarchical features simultaneously. Then we propose the adaptive blending method that produces denoised pixels by adaptively filtering 3D MRI, which explicitly utilizes the similarity in 3D MRI. Residual is also considered as a compensating item after adaptive filtering. The blending adaptive filter and residual are predicted by a network consisting of several large receptive field residual dense blocks. Experimental results show that the proposed DABN outperforms state-of-the-art denoising methods in both clinical and simulated MRI data.

While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to be desired. Conventional BNN hardware training accelerators perform forward and backward propagations with parameters adopting binary representations, and optimization using parameters adopting floating or fixed-point real-valued representations-requiring two distinct sets of network parameters. In this paper, we propose a hardware-friendly training method that, contrary to conventional methods, progressively binarizes a singular set of fixed-point network parameters, yielding notable reductions in power and resource utilizations. We use the Intel FPGA SDK for OpenCL development environment to train our progressively binarizing DNNs on an OpenVINO FPGA. We benchmark our training approach on both GPUs and FPGAs using CIFAR-10 and compare it to conventional BNNs.

The large amount of deployed smart devices put tremendous traffic pressure on networks. Caching at the edge has been widely studied as a promising technique to solve this problem. To further improve the successful transmission probability (STP) of cache-enabled cellular networks (CEN), we combine the cooperative transmission technique with CEN and propose a novel transmission scheme. Local channel state information (CSI) is introduced at each cooperative base station (BS) to enhance the strength of the signal received by the user. A tight approximation for the STP of this scheme is derived using tools from stochastic geometry. The locally optimal content placement strategy of this scheme is obtained using a numerical method to maximize the STP. Simulation results demonstrate the optimal strategy achieves significant gains in STP over several comparative baselines with the proposed scheme.

In this paper, the security issue of cache-enabled wireless networks is considered, where data transmission from the small base station (SBS) to the user is interfered by denial-of-service (DoS) attacks. To deal with this type of DoS attacks, we firstly investigate the energy dispatch problem from the perspective of the SBS. We further establish an optimization model by using the average number of subfiles requested from the macro base station (MBS) to measure the system performance, and then present the corresponding algorithm to derive the optimal scheduler. Additionally, numerical simulations are carried out to validate the effectiveness of the proposed algorithm.

Energy efficiency (EE) performance of millimeter-wave (mmWave) large-array systems attracts a lot of attention. And insertion loss is an inherent characteristic of hybrid precoding systems, which greatly reduces the system performance. EE analysis considering the insertion loss based on the dynamic array architecture is still an open issue. This paper researches the ergodic EE of mmWave hybrid pre-coding system with the insertion loss, based on the adaptive overlapped subarray (OSA) architecture. The ergodic EE is a more valuable indicator than the instantaneous EE for the system under dynamic architecture. However, it is difficult to directly calculate the precise ergodic EE due to the intractable relationship between EE and the channel matrix. Instead, we simplify the precise ergodic EE to get a lower bound, and analyze the ergodic EE performance based upon the lower bound. By this way, we analyze the ergodic EE performance of two typical hybrid pre-coding schemes taking the dynamic architectures. Simulation results verify the effectiveness of analyses.

Sparse code multiple access (SCMA) is an attractive non-orthogonal multiple access scheme for wireless communications. Meanwhile, space-time block coding (STBC) can achieve high diversity gains in fading channels. This paper proposes an uplink SCMA-STBC with a space-time-based message-passing algorithm (ST-MPA). Moreover, precoding is employed in the proposed SCMA-STBC to reduce the complexity of the receiver. The BER lower bound is derived for the proposed system. Simulation results show that the system with precoding provides a better BER performance than the case without precoding.

The large amount of devices deployed for the Internet of Things (IoT) cause a tremendous traffic burden on the cloud server. Caching content at the edge of IoT networks is a promising technology to alleviate the traffic load. However, how to further improve the successful transmission probability (STP) of cache‐enabled IoT networks is still an open issue. In this study, the authors propose a novel local channel state information based joint transmission (LC‐JT) scheme for cache‐enabled IoT networks and design the optimal content placement probability at the cooperative edge base stations, correspondingly. First, they derive an upper bound and a tight approximation for the STP of LC‐JT scheme using stochastic geometry. Next, an algorithm is proposed to maximise the approximation of STP in LC‐JT by optimising the placement probability vector, which is a non‐convex optimisation problem. By utilising some properties of the STP, they obtain the globally optimal solutions in specific cases. Moreover, the locally optimal solutions in general cases are obtained by using the gradient projection method. Finally, numerical results show the optimised content placement strategy can achieve significant gains in STP over several comparative baselines. It verifies that the strategy with LC‐JT can considerably enhance the STP in cache‐enabled IoT networks.

In this study, secure communications in a two‐way relaying wiretap system with a silent eavesdropper are studied. Under the assumption that the channel state information relating to the eavesdropper is unknown at legitimate nodes, the precoding vectors at the two source nodes are jointly designed to decrease the wiretap capacity at the eavesdropper. The derived relationship between the two precoding vectors is partially similar in nature to the linear minimum mean squared error (MMSE) equaliser. An iterative process is proposed to jointly achieve two precoding vectors, and its convergence is proved. Simulation results are presented to demonstrate that the proposed MMSE‐based precoding algorithm can be used for source nodes with any number of antennas, and outperforms its conventional zero‐forcing‐ and matched‐filter‐based counterparts. Signal leakage from the relay node to the eavesdropper is nearly completely suppressed by the proposed precoding design.

Artificial noise (AN) is considered as a new physical layer technology to improve the security of wireless systems. In this paper, we investigate secure transmission of AN-aided generalized spatial modulation (GSM), which maintains the same hardware requirements at the transmitter as the conventional GSM. In order to further improve the jamming intensity of conventional AN scheme, we propose an Euclidean distance optimized AN (ED-AN) scheme by minimizing the Euclidean distance between the transmit signal and the jamming signal, which also avoids the power waste of conventional AN scheme. The secrecy capacities of both the AN-GSM and EDAN-GSM schemes are analyzed, and the optimal power allocation of AN-GSM is further investigated by maximizing the secrecy capacity. Furthermore, the upper bounds of the theoretical bit error rates (BERs) of both the legitimate receiver and the illegal eavesdropper over the Rayleigh fading channel are derived. Simulation results validate our derived analysis and demonstrate that the ED-AN scheme offers better secrecy and BER performance.

In this paper, a new class of online fountain codes is proposed to provide high intermediate symbol recovery rates (ISRRs) with low overhead. The encoder consists of two phases. In the first phase, a zigzag decodable online fountain (ZDOF) is proposed to provide a high ISRR. We utilize the characteristics of zigzag decodable codes so that the online fountain codes start decoding in the first phase without having to wait for the receipt of symbols of degree one. In the second phase, the buffer decoding method (BDM) is proposed to utilize a buffer to hold discarded symbols so as to generate useful symbols and improve the decoding performance. In addition, we provide a theoretical analysis based on random graph theory to analyze the performance of the proposed scheme. The theoretical analysis and simulation results show that the proposed scheme outperforms conventional online fountain codes, and that the buffer size does not have to be large.

An N-continuous generalized frequency division multiplexing (GFDM) transceiver architecture is studied with the objective of striking a balanced trade-off between the bit error rate (BER) and the sidelobe suppression performance. More specifically, in the proposed N-continuous GFDM signaling, the basis signals constructed allow one to make the GFDM signal N-continuous and attain a compact spectrum as an explicit benefit of sidelobe suppression. We further reveal that compared to conventional N-continuous orthogonal frequency division multiplexing (NC-OFDM), N-continuous GFDM introduces relatively low interference through evaluating the signal-to-interference ratio (SIR). Secondly, a signal recovery algorithm is presented by constructing a recovery matrix to eliminate the interference. Finally, it is demonstrated that the proposed N-continuous GFDM scheme outperforms its N-continuous OFDM counterpart in terms of sidelobe suppression, while achieving moderate BER performance degradation as opposed to original OFDM.

In remote sensing, micro-Doppler signatures are widely used in moving target detection and automatic target recognition. However, since Doppler signatures are easily affected by the moving direction of the target, prior information of aspect angle is essential for spectral analysis. Thus, a micro-Doppler-based classifier is considered to be “angle-sensitive.” In this article, we propose an angle-insensitive classifier for the omnidirectional classification problem using the monostatic radar through a proposed new convolutional neural network. We further provide a sensible definition of “angle sensitivity,” and perform experiments on two data sets obtained through simulations and measurements. The results demonstrate that the proposed algorithm outperforms both feature-based and existing deep-learning-based counterparts, and resolve the issue of angle sensitivity in micro-Doppler-based classification.

In large-array millimeter-wave (mmWave) systems, hybrid pre-coding is one of the most attractive research topics. This paper first presents a flexible adaptive overlapped subarray (OSA) architecture for the analog precoder, whose architecture can be adjusted by a connection network. An objective function is formulated to maximize the energy efficiency (EE) in consideration of the insertion loss for the proposed adaptive OSA based hybrid precoder. The optimal scheme is intractable to achieve, so that we present a heuristic hybrid pre-coding scheme, where the digital precoder is designed based on the zero-forcing (ZF) rule and the analog precoder is designed based on simplified EE optimization in consideration of the insertion loss. We discuss the effect of non-ideal factors on the EE performance, such as quantized phases, imperfect channel state information (CSI), and faulty switches. Simulation results show that, when the initial transmit power is large, our proposed scheme offers a better EE performance than the fully digital pre-coding scheme and many other popular hybrid pre-coding schemes. Moreover, it is found that faulty switches make the double-edged effect on the EE performance when the numbers of activated phase shifters and combiners are pre-defined.

In this paper, we consider the secure generalised precoding aided spatial modulation (GPSM) scheme, which is combined with artificial noise (AN) to resist unknown malicious eavesdropping. Given a strict power constraint for the transmit signal and a wiretap Rayleigh fading channel, the BER performances of both the desired receiver and malicious eavesdropper are derived. Simulation results validate the accuracy of the theoretical analysis and demonstrate the secrecy performance of the secure GPSM system.

Designing a routing protocol for underwater sensor networks is a great challenge due to characteristics of high energy consumption and high latency. This paper investigates a Q-learning-based localization-free routing protocol (QLFR) to prolong the lifetime as well as reduce the end-to-end delay for underwater sensor networks. Aiming to seek optimal routing policies, Q- value is calculated by jointly considering residual energy and depth information of sensor nodes throughout the routing process. More specifically, we define two cost functions (depth-related cost and energy-related cost) for Q-learning, in order to reduce delay and extend the network lifetime. In addition, a holding time mechanism for packet forwarding is designed according to the priority of forwarding nodes. The key contribution lies in: 1) a novel Q-learning-based routing protocol for UWSNs; 2) a new holding time mechanism for packet forwarding; and 3) a packet- delivery-ratio-based scheme to further reduce unnecessary transmissions. Extensive simulation results demonstrate superiority performance of our routing protocol in terms of reducing end-to-end delay and extending the network lifetime.

In 5G cellular networks, device‐to‐device (D2D) communications help greatly improve spectral efficiency and reduce communication latency. However, interference is intrinsic to D2D communications when sharing spectral resources with cellular users (CUs). On the other hand, D2D is able to bear more and more services, which help user‐centred and personalised services become development trends in 5G networks. Against this background, the authors propose a user‐priority‐based resource allocation scheme in consideration of interference. The scheme first divides the service priority of D2D into four levels based on the principle of satisfying the quality‐of‐service (QoS) requirements of D2D as much as possible and then performs admission control allowing a D2D pair to use the CU spectral resources according to different priority levels. Next, they develop a maximum throughput scheme for the admissible D2D pair to select a suitable CU partner. Finally, a maximum weighted bipartite matching scheme is adopted. The proposed scheme is compared with a benchmark QoS‐aware scheme in terms of the cell radius, distance, and maximum power of the D2D pair. Simulation results show that the proposed scheme is able to notably improve system throughput.

In this study, the authors consider multi‐user millimetre wave (mmWave) multiple‐input multiple‐output (MIMO) downlink communications for multi‐carrier scenarios, e.g. orthogonal frequency‐division multiplexing (OFDM) a common analogue precoder and combiner for the transmitter and receiver to maximise spectral efficiency is the main challenge for multi‐carrier MIMO systems, they propose two methods to solve this problem. The first method designs the analogue precoder and combiner based on the channel average of all subcarriers, which helps reduce computational complexity. Moreover, the channels of all subcarriers can be viewed as a third‐order tensor, and the second method is based on tensor unfolding, which makes full use of the channel information of all subcarriers. When the common analogue precoder and combiner are fixed, they consider designing a digital precoder to maximise the signal‐to‐leakage‐plus‐noise ratio of each user in every subcarrier, which leads to closed‐form solutions compared with the block diagonal method. Simulation results demonstrate that the performance of the proposed methods is close to that of the fully digital precoding method, and increasing the number of RF transceiver chains helps improve the performance of the proposed methods.

The Internet of Things (IoT) connects a huge number of resource-constraint IoT devices to the Internet, which generate massive amount of data that can be offloaded to the cloud for computation. As some of the applications may require very low latency, the emerging mobile edge computing (MEC) architecture offers cloud services by deploying MEC servers at the mobile base stations (BSs). The IoT devices can transmit the offloaded data to the BS for computation at the MEC server. Narrowband-IoT (NB-IoT) is a new cellular technology for the transmission of IoT data to the BS. In this paper, we propose a joint computation offloading and multiuser scheduling algorithm in NB-IoT edge computing system that minimizes the long-term average weighted sum of delay and power consumption under stochastic traffic arrival. We formulate the dynamic optimization problem into an infinite-horizon average-reward continuous-time Markov decision process (CTMDP) model. In order to deal with the curse-of-dimensionality problem, we use the approximate dynamic programming techniques, i.e., the linear value-function approximation and temporal-difference learning with post-decision state and semi-gradient descent method, to derive a simple algorithm for the solution of the CTMDP model. The proposed algorithm is semi-distributed, where the offloading algorithm is performed locally at the IoT devices, while the scheduling algorithm is auction-based where the IoT devices submit bids to the BS to make the scheduling decision centrally. Simulation results show that the proposed algorithm provides significant performance improvement over the two baseline algorithms and the MUMTO algorithm which is designed based on the deterministic task model.

By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing. However, due to the resource constraint of IoT devices and wireless network, both communications and computation resources need to be allocated and scheduled efficiently for better system performance. In this article, we propose a joint computation off-loading and multiuser scheduling algorithm for IoT edge computing system to minimize the long-term average weighted sum of delay and power consumption under stochastic traffic arrival. We formulate the dynamic optimization problem as an infinite-horizon average-reward continuous-time Markov decision process (CTMDP) model. One critical challenge in solving this MDP problem for the multiuser resource control is the curse-of-dimensionality problem, where the state space of the MDP model and the computation complexity increase exponentially with the growing number of users or IoT devices. In order to overcome this challenge, we use the deep reinforcement learning (RL) techniques and propose a neural network architecture to approximate the value functions for the post-decision system states. The designed algorithm to solve the CTMDP problem supports semi distributed auction-based implementation, where the IoT devices submit bids to the BS to make the resource control decisions centrally. The simulation results show that the proposed algorithm provides significant performance improvement over the baseline algorithms, and also outperforms the RL algorithms based on other neural network architectures.

Missing data are unavoidable in wireless sensor networks, due to issues such as network communication outage, sensor maintenance or failure, etc. Although a plethora of methods have been proposed for imputing sensor data, limitations still exist. First, most methods give poor estimates when a consecutive number of data are missing. Second, some methods reconstruct missing data based on other parameters monitored simultaneously. When all the data are missing, these methods are no longer effective. Third, the performance of deep learning methods relies highly on a massive number of training data. Moreover in many scenarios, it is difficult to obtain large volumes of data from wireless sensor networks. Hence, we propose a new sequence-to-sequence imputation model (SSIM) for recovering missing data in wireless sensor networks. The SSIM uses the state-of-the-art sequence-to-sequence deep learning architecture, and the long short-term memory network is chosen to utilize both past and future information for a given time. Moreover, a variable-length sliding window algorithm is developed to generate a large number of training samples so the SSIM can be trained with small data sets. We evaluate the SSIM by using real-world time series data from a water quality monitoring network. Compared to methods like ARIMA, seasonal ARIMA, matrix factorization, multivariate imputation by chained equations, and expectation–maximization, the proposed SSIM achieves up to 69.2%, 70.3%, 98.3%, and 76% improvements in terms of the root mean square error, mean absolute error, mean absolute percentage error (MAPE), and symmetric MAPE, respectively, when recovering missing data sequences of three different lengths. The SSIM is therefore a promising approach for data quality control in wireless sensor networks.

In this paper, we propose a novel framework of low-cost link adaptation for spatial modulation multiple-input multiple-output (SM-MIMO) systems-based upon the machine learning paradigm. Specifically, we first convert the problems of transmit antenna selection (TAS) and power allocation (PA) in SM-MIMO to ones-based upon data-driven prediction rather than conventional optimization-driven decisions. Then, supervised-learning classifiers (SLC), such as the K -nearest neighbors (KNN) and support vector machine (SVM) algorithms, are developed to obtain their statistically-consistent solutions. Moreover, for further comparison we integrate deep neural networks (DNN) with these adaptive SM-MIMO schemes, and propose a novel DNN-based multi-label classifier for TAS and PA parameter evaluation. Furthermore, we investigate the design of feature vectors for the SLC and DNN approaches and propose a novel feature vector generator to match the specific transmission mode of SM. As a further advance, our proposed approaches are extended to other adaptive index modulation (IM) schemes, e.g., adaptive modulation (AM) aided orthogonal frequency division multiplexing with IM (OFDM-IM). Our simulation results show that the SLC and DNN-based adaptive SM-MIMO systems outperform many conventional optimization-driven designs and are capable of achieving a near-optimal performance with a significantly lower complexity.

Micro-Doppler-based human motion classification has become a topical area of research recently. However, the current research is limited by the lack of labeled training data. Domain adaptation, namely, the ability to take advantage of knowledge from an available source data set and apply it to an unlabeled target data set, is useful in this situation. A typical strategy for this transfer learning technique is to extract domain-invariant feature representations. In this letter, an unsupervised domain adaptation method for micro-Doppler classification is proposed. Given no available measurement training samples, we creatively utilize the motion capture database as an auxiliary and adapt its interior knowledge to the measurement data set. To achieve domain-invariant features, three types of features are extracted and fused including low-level deep features from the convolutional neural network, empirical features, and statistical features. After feature fusion, a k-nearest neighbor classifier is applied to the measurement data to classify seven human activities. Experimental results show that our approach outperforms several state-of-the-art unsupervised domain adaptation methods. The impact of the output from different convolution layers is further investigated, and ablation studies of the efficacy of each feature are also carried out in this letter.

Hybrid pre-coding design is a promising research direction in large antenna array millimeter wave (mmWave) systems. The insertion loss is an inherent and significant feature of hybrid pre-coding, resulting in lower energy efficiency and inferior bit error rate (BER) performance. This paper takes the minimum sum-mean-square-error (Min-SMSE) considering the insertion loss as the optimization objective function, which aims at increasing the sum-rate and improving the BER performance. Then a hybrid pre-coding is designed based on this criterion with an adaptive overlapped subarray (OSA) architecture. It is proved that the optimization problem is non-convex. Thus, we decompose the optimization problem into two sub-optimum ones. One is to design the digital pre-coding based on the Min-SMSE criterion under the equivalent channel condition. The other one is to design the analog pre-coding based on the simplified Min-SMSE with the insertion loss objective function. Theoretical analyses of the proposed scheme are conducted, including the upper bound of the average BER, the lower bound of the average sum-rate, and the computational complexity. Simulation results show that our proposed scheme outperforms three representative hybrid pre-coding schemes with different architectures in both BER and sum-rate, when the numbers of the phase shifters and combiners are relatively small.

In this paper, a novel scheme dubbed space-time block coded rectangular differential spatial modulation (STBC-RDSM) is proposed for multiple-input and multiple-out (MIMO) systems, which combines space-time block coding (STBC) and rectangular differential spatial modulation (RDSM) to reap their respective benefits while avoiding the drawbacks of conventional differential spatial modulation (DSM) systems. More specifically, in the proposed STBC-RDSM scheme, information bits are conveyed via the rectangular differentially encoded antenna index matrices, as well as the STBC blocks. Furthermore, a low-complexity detection scheme is proposed. Our simulation results demonstrate that STBC-RDSM outperforms its conventional DSM counterparts in various spectral efficiencies. Finally, a closed-form union bound on the bit error rate (BER) is derived and validated by our simulation results.

A novel joint source and channel coding scheme tailored to 3D video is proposed in this paper to minimize the end-to-end view synthesis distortion within a given total bit rate for both texture and depth as well as a maximum tolerable distortion constraint for texture. First, we formulate a joint texture and depth coding mode selection strategy for error-resilient source coding of multi-view video plus depth-based 3D video through using the Lagrange multiplier method. Then, by considering the effect of residual errors after channel coding, we evolve to a more general formulation that jointly optimizes error-resilient source coding and channel coding in an integrated manner for unequal error protection between texture and depth, for which a theoretic solution using a proposed dual-trellis is derived. Finally, we extend the general formulation by including the texture distortion constraint. We show how to optimize the view synthesis quality while simultaneously catering to the texture quality constraint. Experimental results demonstrate the proposed algorithm has much better performance than existing related work.

Underwater images typically suffer from low visibility and severe colorcast due to scattering and absorption. In this letter, a novel method is proposed to handle the scattering and absorption problems of light with different wavelengths based on the color-line model. We filter out image patches that exhibit the characteristics of the color-line prior and recover the color line of the patches. Then, the local transmission for each patch is estimated based on the offsets of the color lines along the background-light vector from the origin. We also develop an optimization function to derive the local transmission and to obtain the solution in the underwater environment. Experimental results are presented to show that the proposed method can produce high-quality underwater images with relatively genuine colors, natural appearance, and improved contrast and visibility.

To overcome the challenging problems in saliency detection, we propose a novel semi-supervised classifier which makes good use of a linear feedback control system (LFCS) model by establishing a relationship between control states and salient object detection. First, we develop a boundary homogeneity model to estimate the initial saliency and background likelihoods, which are regarded as the labeled samples in our semi-supervised learning procedure. Then in order to allocate an optimized saliency value to each superpixel, we present an iterative semi-supervised learning framework which integrates multiple saliency cues and image features using an LFCS model. Via an innovative iteration method, the system gradually converges an optimized stable state, which is associating with an accurate saliency map. This paper also covers comprehensive simulation study based on public datasets, which demonstrates the superiority of the proposed approach.

Many Internet of Things and embedded projects are event driven, and therefore require asynchronous and concurrent programming. Current proposals for C++20 suggest that coroutines will have native language support. It is timely to survey the current use of coroutines in embedded systems development. This article investigates existing research which uses or describes coroutines on resource-constrained platforms. The existing research is analysed with regard to: software platform, hardware platform, and capacity; use cases and intended benefits; and the application programming interface design used for coroutines. A systematic mapping study was performed, to select studies published between 2007 and 2018 which contained original research into the application of coroutines on resource-constrained platforms. An initial set of 566 candidate papers, collated from on-line databases, were reduced to only 35 after filters were applied, revealing the following taxonomy. The C 8 C++ programming languages were used by 22 studies out of 35. As regards hardware, 16 studies used 8- or 16-bit processors while 13 used 32-bit processors. The four most common use cases were concurrency (17 papers), network communication (15), sensor readings (9), and data flow (7). The leading intended benefits were code style and simplicity (12 papers), scheduling (9), and efficiency (8). A wide variety of techniques have been used to implement coroutines, including native macros, additional tool chain steps, new language features, and non-portable assembly language. We conclude that there is widespread demand for coroutines on resource-constrained devices. Our findings suggest that there is significant demand for a formalised, stable, well-supported implementation of coroutines in C++, designed with consideration of the special needs of resource-constrained devices, and further that such an implementation would bring benefits specific to such devices.

In this paper, we propose a novel iterative optimization model for bottom-up saliency detection. By exploring bottom-up saliency principles and semisupervised learning approaches, we design a high-performance saliency analysis method for wide ranging scenes. The proposed algorithm consists of two stages: 1) we develop a boundary homogeneity model to characterize the general position and the contour of the salient objects and 2) we propose a novel iterative optimization model, termed gradual saliency optimization, for further performance improvement. Our main contribution falls on the second stage, where we propose an iterative framework with self-repairing mechanisms for refining saliency maps. In this framework, we further develop a more comprehensive optimization function applying a novel semisupervised learning scheme to enhance the traditional saliency measure. More elaborately, the iterative method can gradually improve the output in each iteration and finally converge to high-quality saliency maps. Based on our experiments on four different public data sets, it can be demonstrated that our approach significantly outperforms the state-of-the-art methods.

This paper designs a distributed state estimation scheme considering cyber attacks using the internet of things (IoT) technologies. The IoT sensors are utilised to get synchronous generator information. After locally estimating the system states, the attack occurs during transmission of sensors information to the remote estimator. In the fusion center, the convex optimization problem is developed to estimate the generator states. Lastly, the feedback controller is proposed to regulate the generator states. Numerical results demonstrate that the developed algorithm can properly estimate and regulate the generator states.

This paper develops a state estimation and stabilisation scheme for monitoring and controlling the wind turbine. Basically, the estimation scheme is designed considering the Bayesian tree network. The estimated system states are corrected in the forward and backward direction of this network where the estimation errors are enforced to minimise. Therefore, the estimated system state converges to the actual states as time goes by. Furthermore, the optimal feedback controller is designed. Interestingly, the proposed algorithms are applied to the environment-friendly wind turbine, and it shows that the developed methods can effectively estimate and stabilise the turbine states.

This paper develops a distributed state estimation approach for smart grids. Particularly, the designed filter is developed in an interconnected way where the packet dropouts take place between estimators. The error function between true and estimated states is written in compact form, then it can be transformed into the linear matrix inequality (LMI). After solving the LMI problem, the desired gains are determined for the smart grid state estimation. The proposed method is applied to the IEEE 14-bus system where system state and input matrices are obtained from the Holt-Winters approach.

We investigate the design of the optimal routing path in a moving vehicles involved the Internet of Things (IoT). In our model, jammers are present to interfere with the information exchange between wireless nodes, leading to a worsened quality of service (QoS) in communications. In addition, the transmit power of each battery-equipped node is constrained to save energy. We propose a three-step optimal routing path algorithm for reliable and energy-efficient communications. Moreover, results show that with the assistance of moving vehicles, the total energy consumed can be reduced to a large extend. We also study the impact on the optimal routing path design and energy consumption which is caused by the path loss, maximum transmit power constrain, QoS requirement, etc.

The latency and reliability of single‐relay and multi‐relay systems are investigated in this study. In a single‐relay system with the amplify‐and‐forward protocol, a new approximation analytical method is proposed for the outage probability, which can also be extended to be used in the multi‐relay system. The latency‐reliability trade‐off degree (LRTD) of single‐ and multi‐relay systems, i.e. the slope of the latency‐outage probability curve with logarithmic scales, is analysed and proved to be the same as the number of relay nodes. In the multi‐relay system, the relationship between the system LRTD and the channel state information overhead is investigated. The optimum number of relay nodes can be derived according to the approximate expression of the outage probability. A simple iterative method is proposed to obtain the optimum number of relay nodes. The convergence of the iterative method is also proved.

Sparse code multiple access (SCMA), as one of the most promising candidate techniques for the fifth generation communications system, is a nonorthogonal multiple access scheme which can provide large scale connections. Its philosophy is to map coded bits directly to multidimensional sparse codewords, and the message passing algorithm (MPA) is utilized to detect the multiuser signals. However, the relatively high computation of MPA detection may lower the performance when SCMA is implemented in practical applications. The partial marginalization MPA (PM-MPA) helps to reduce the computation of original MPA detection. In this paper, an improved detection scheme based on PM-MPA is proposed. Our analysis and simulation shows that compared with PM-MPA, the improved PM-MPA (IPM-MPA) can obtain a lower bit error ratio. Besides, the simulation also shows that, to achieve the same performance, the IPM-MPA is less complex than PM-MPA.

Wireless energy harvesting has emerged as an appealing solution to prolong the lifespan of energy-constrained wireless networks and been regarded as a main functional unit for almost all perpetual communications. This paper proposes a channel coding-based Internet of Things communication network, and state estimation as well as stabilization algorithms for wireless power transfer systems. After modeling the energy harvesting module like wireless energy transfer systems as a state-space framework, Web-enabled smart sensors are deployed to obtain measurements. The sensing information is transmitted to the nearby base station for collection and digital communication under the condition of packet losses. A recursive systematic convolutional code is used to add redundancy into the quantize system states. After digital modulation, the signal is transmitted to a control center for system state estimation and stabilization. The optimal gain of the state estimation scheme is determined after minimizing the mean squared errors. Afterward, a stabilization algorithm is designed considering packet losses in the communication networks using the semidefinite programming approach. Furthermore, the convergence of the developed estimation algorithm is proved. Numerical simulation results demonstrate, considering packet loss, sensor faults, disturbances, and delay into account, that the proposed algorithms can estimate and stabilize the system states within a short period of time.

In contrast to traditional centralized estimation methods, this letter proposes a distributed dynamic state estimation method for microgrids incorporating distributed energy resources. Specifically, distributed filter structure is designed in an interconnected way, where packet losses obviously occur between them. Then the error function is written in a compact form using the matrix property of the Kronecker product. Afterwards, it can be transformed into a linear matrix inequality. Finally, the local and neighboring gains for the distributed estimator are effectively computed after solving the convex optimization problem. Simulation result shows that the proposed method can well estimate the system state within 10 iterations.

As a promising non-orthogonal multiple access scheme, sparse code multiple access (SCMA) technology has attracted much attention. Because inter-user interference is present in code domain and multi-user iterative detection is required, user capacity and outage probability analysis for uplink SCMA systems are challenging and have not been presented in the literature. In this paper, the capacity region for uplink SCMA systems is analyzed, based on which the common and individual outage probability regions are calculated. Optimizing the outage probability within the outage probability region can be casted as an Lagrangian duality problem and solved by an iterative descent algorithm, which however imposes high complexity since the expectation operation is required in each iteration. To reduce the computational complexity of solving this Lagrangian duality problem, an adaptive algorithm is developed, which is capable of providing the optimal outage probability and adaptively updating it. Furthermore, a power allocation policy is naturally obtained to achieve the optimized outage probability in the outage probability region.

In this paper, we propose a hybridly connected structure for hybrid beamforming in millimeter-wave (mmWave) massive MIMO systems, where the antenna arrays at the transmitter and receiver consist of multiple sub-arrays, each of which connects to multiple radio frequency (RF) chains, and each RF chain connects to all the antennas corresponding to the sub-array. In this structure, through successive interference cancelation, we decompose the precoding matrix optimization problem into multiple precoding sub-matrix optimization problems. Then, near-optimal hybrid digital and analog precoders are designed through factorizing the precoding sub-matrix for each sub-array. Furthermore, we compare the performance of the proposed hybridly connected structure with the existing fully and partially connected structures in terms of spectral efficiency, the required number of phase shifters, and energy efficiency. Finally, simulation results are presented to demonstrate that the spectral efficiency of the hybridly connected structure is better than that of the partially connected structure and that its spectral efficiency can approach that of the fully connected structure with the increase in the number of RF chains. Moreover, the proposed algorithm for the hybridly connected structure is capable of achieving higher energy efficiency than existing algorithms for the fully and partially connected structures.

The distribution power subsystems are usually interconnected to each other, so the design of the interconnected optimal filtering algorithm for distributed state estimation is a challenging task. Driven by this motivation, this paper proposes a novel consensus filter based dynamic state estimation algorithm with its convergence analysis for modern power systems. The novelty of the scheme is that the algorithm is designed based on the mean squared error and semidefinite programming approaches. Specifically, the optimal local gain is computed after minimizing the mean squared error between the true and estimated states. The consensus gain is determined by a convex optimization process with a given suboptimal local gain. Furthermore, the convergence of the proposed scheme is analyzed after stacking all the estimation error dynamics. The Laplacian operator is used to represent the interconnected filter structure as a compact error dynamic for deriving the convergence condition of the algorithm. The developed approach is verified by using the renewable microgrid. It shows that the distributed scheme being explored is effective as it takes only 0.00004 seconds to properly estimate the system states and does not need to transmit the remote sensing signals to the central estimator.

Being able to provide a relatively easy and inexpensive way to collect data, portable readers have gained increasing popularity in wide-ranging RFID applications. In order to maximize the reader’s battery life, efficient tag identification protocols are of paramount importance in large-scale passive radio frequency identification (RFID) systems. This paper proposes a time- and energy-aware protocol based on$M$-ary collision tree (MCT) for efficient RFID tag identification. Thanks to Manchester encoding, the proposed MCT protocol recursively divides colliding tags into$M$subsets with at least two nonempty ones according to the information of$\log _2 M$colliding bits. Through the new MCT recognition process, MCT can effectively identify all the tags within its reading range. Theoretic analysis demonstrates that it takes the proposed MCT protocol fewer numbers of collision slots and message bits to identify all the tags, which reduces not only the identification time but also the energy cost. Simulation results are also presented to show that compared with other benchmark works, the proposed MCT protocol is able to reduce the average identification time and energy cost by at least 16.12% and 15.73%, respectively.

In a mobile RFID system, a large number of tags move in and out of the system continuously, so that the reader has very limited time to recognize all the tags. As a result, the effective and efficient identification of tags in mobile environments is a more challenging problem compared to conventional static RFID systems. In this paper, we propose an efficient bit-detecting (EBD) protocol to accelerate the reading process of large-scale mobile RFID systems. In these systems, some previously recognized tags, i.e., known tags, may stay in the reader's reading range for two consecutive reading cycles, and some unknown tags may newly participate in the current reading cycle. In the proposed EBD protocol, a new bit monitoring method is proposed to detect the presence of known tags using a small number of slots, and to retrieve their IDs from the back-end database. Next, an$M$-ary bit-detecting tree recognition method is proposed to rapidly recognize unknown tags without generating any idle slots. This new protocol is shown to perform better than existing methods reported in the literature. Both theoretic and simulation results are present to demonstrate that the proposed protocol is superior to existing protocols in terms of lower time cost.

Coordinated multipoint (CoMP) communications are considered for the fifth-generation (5G) small-cell networks as a tool to improve the high data rates and the cell-edge throughput. The average achievable rates of the small-cell base stations (SBS) cooperation strategies with distance and received signal power constraints are respectively derived for the fractal small-cell networks based on the anisotropic path loss model. Simulation results are presented to show that the average achievable rate with the received signal power constraint is larger than the rate with a distance constraint considering the same number of cooperative SBSs. The average achievable rate with distance constraint decreases with the increase of the intensity of SBSs when the anisotropic path loss model is considered. What's more, the network energy efficiency of fractal small-cell networks adopting the SBS cooperation strategy with the received signal power constraint is analyzed. The network energy efficiency decreases with the increase of the intensity of SBSs which indicates a challenge on the deployment design for fractal small-cell networks.

This paper explores the optimal filtering problem for microgrid state estimation considering packet losses in the internet of things (IoT) networks. The considered IoT networks collect microgrid information from smart sensors and send control messages to actuators where sensors and actuators are linked over a lossy network. Explicitly, the distribution power system incorporating renewable distributed energy resources such as wind turbine is represented as a state-space model where IoT element such as smart sensors are deployed to obtain measurements. This sensing information is transmitted to the fusion center through a lossy IoT communication network where measurements are lost. This paper proposes an optimal estimator based on the mean squared error between the actual states and its estimate. Afterwards, a state feedback controller is designed based on the semidefinite programming approach under the condition of packet dropouts in the IoT network. The efficacy of the proposed approaches are demonstrated by presenting an environment-friendly microgrid model incorporating distributed energy resources.

This paper considers hybrid beamforming (HBF) for the point-to-point (P2P) millimeter wave (mmWave) massive MIMO systems. The optimal hybrid precoding and combining matrices that maximizes the system capacity can be obtained based on the singular value decomposition (SVD) of the channel matrix. Then, the optimal unconstrained hybrid digital and analog precoders (combiners) are designed according to the polar decomposition of the optimal hybrid precoding (combining) matrix. Considering the actual hardware constraints, we propose a joint transmitter and receiver HBF algorithm based upon polar decomposition. In this algorithm, the hybrid analog constrained precoding and combining matrices can be derived without having to incur an excessive computational complexity of an iterative approach. Simulation results show that the proposed algorithm can approach the performance of optimal unconstrained precoding, and is insensitive to the accuracy of the channel state information (CSI).

This paper addresses the problem of error-resilient source coding for 3-D video transmission over packet-loss networks. The proposed approach jointly optimizes the texture coding mode and the depth coding mode for each macroblock in the reference views. Firstly, a distortion model is developed to capture the effect of the texture distortion and depth distortion on the synthesized view. Then, joint optimization of texture and depth coding modes is derived based upon an operational rate-distortion framework using Lagrange multiplier method. In particular, a dual trellis-based algorithm is introduced in order to overcome the macroblock interdependencies of texture and depth map in the optimization procedure. Simulation results demonstrate that significant and consistent gains can be achieved over currently used techniques.

This paper considers hybrid beamforming (HBF) for a downlink multiuser millimeter-wave (mmWave) multiple input multiple output (MIMO) system. For this system, we propose a signal-to-leakage-and-noise (SLNR) based HBF algorithm. In this algorithm, we first consider jointly designing the analog precoder and combiner to maximize the RF chain gain between the BS and each user. Then, the digital precoder is designed with the aim at maximizing SLNR, when the analog precoder and combiner are fixed. This optimization problem can be further equivalent to generalized eigenvalue problem, and the optimal digital precoding vector for each stream can be obtained one by one by using generalized Rayleigh-Ritz quotient. Simulation results demonstrate that the performance of the proposed algorithm outperforms the existing algorithms, and are extremely close to the hypothetical single-user (no interference) case.

In this paper, a novel multiple-input multiple-output (MIMO) transmission scheme, termed as receive antenna selection (RAS)-aided spatial modulation MIMO (SM-MIMO), is proposed for millimeter-wave (mmWave) communications. It employs the spatial modulation (SM) concept and the RAS technique to tackle the costs of the multiple radio frequency (RF) chains at both link ends. Moreover, we develop a pair of RAS algorithms for the proposed mmWave RAS-SM scheme based on the capacity maximization (max-capacity) and the bit-error rate (BER) minimization criteria, which are formulated as two combinatorial optimization problems. The theoretical gradients of the capacity and the BER with respect to RAS variables are derived and the convexities of these problems are discussed. Furthermore, a novel iterative algorithm through jointly designing the log-barrier algorithm (LbA) and the simplified conjugate gradient method is proposed for RAS optimization. Our simulation results show that the proposed RAS-SM schemes are capable of achieving considerable performance gains over conventional norm-based and eigenvalue-based schemes in mmWave MIMO channels, while avoiding an overwhelming complexity imposed by exhaustive search.

Impairments such as time varying phase noise (PHN) and carrier frequency offset (CFO) result in loss of synchronization and poor performance of multi-relay communication systems. Joint estimation of these impairments is necessary in order to correctly decode the received signal at the destination. In this paper, we address spectrally efficient multi-relay transmission scenarios where all the relays simultaneously communicate with the destination. We propose an iterative pilot-aided algorithm based on the expectation conditional maximization for joint estimation of multipath channels, Wiener PHNs, and CFOs in decode-and-forward-based multi-relay orthogonal frequency division multiplexing systems. Next, a new expression of the hybrid Cramér-Rao lower bound (HCRB) for the multi-parameter estimation problem is derived. Finally, an iterative receiver based on an extended Kalman filter for joint data detection and PHN tracking is employed. Numerical results show that the proposed estimator outperforms existing algorithms and its mean square error performance is close to the derived HCRB at different signal-to-noise ratios for different PHN variances. In addition, the combined estimation algorithm and the iterative receiver can significantly improve average bit-error rate (BER) performance compared with existing algorithms. In addition, the BER performance of the proposed system is close to the ideal case of perfect channel impulse responses, PHNs, and CFOs estimation.

This paper studies robust energy optimization for the cloud radio access network (C-RAN). The objective of this paper is to jointly minimize network power consumption through optimizing the base station (BS) mode, multi-user (MU)-BS association, and beamforming vectors given imperfect channel state information (CSI). To solve this non-trivial problem, we first transform the problem to a semi-definite programming (SDP) one using the S-lemma with the aid of the semi-definite relaxation technique, and then propose a SDP-based group sparse beamforming approach to solve it iteratively. Since the computational complexity of solving SDP problems is intractable, we propose to translate the uncertainty in the CSI to the uncertainty in its covariance matrix, and then recast the original problem as a mixed-integer second-order cone programming problem. We further propose a two-stage rank selection framework to determine the BS mode and MU-BS association separately and successively. Simulation results demonstrate the convergence of our proposed algorithms, and validate the effectiveness of the proposed algorithms in minimizing the network power consumption of the C-RAN.

Radio frequency identification (RFID) technology has been employed in wide-raging application domains. In most RFID applications, time-efficient identification of missing tags is one of the most fundamental objectives, especially for asset management and anti-theft purposes. In this paper, we propose a time-efficient pair-wise collision-resolving missing tag identification (PCMTI) protocol for large-scale RFID systems. In the protocol, two novel strategies, i.e., the pair-reply and two-collision slot (i.e., a slot with two exact tag responses) resolving strategies, are proposed. The pair-reply strategy can verify two tags in one short response slot simultaneously, while the two-collision slot resolving strategy further increases the number of tags verified in each frame. Both theoretical analysis and simulated results are presented to demonstrate the superiority of the proposed PCMTI protocol, which is capable of outperforming the state-of-the-art comparative protocols with at least a 30% reduction in average identification time for verifying one tag.

Cross-layer forward error correction (FEC) aims at utilizing available bandwidth more efficiently, which has been applied to error-prone video transmission over imperfect wireless channels. In this paper we propose a new near-optimal cross-layer FEC scheme in which systematic Raptor codes are used at the application layer and rate compatible punctured convolutional (RCPC) codes are used at the physical layer for H.264/AVC encoded video streaming with channel bandwidth constraints. In the proposed scheme, in order to fully exploit the unequal importance of compressed video data, we assign each source packet a different priority according to its contribution to the reconstructed video quality. We first obtain the transmission parameters, which satisfies the conditions for optimal video transmission, for the optimal cross-layer Raptor-RCPC FEC in the ideal situation through a theoretical analysis, and then we propose a heuristic algorithm searching from the optimal solution point to obtain the transmission parameters, which are near optimal in the practical situation. Computer simulation results show that the proposed scheme can achieve significant performance improvements in both the additive white Gaussian noise and Rayleigh channels compared with the previous work.

This paper studies secrecy communications in a multi-antenna two-way relaying wiretap system. Each source node transmits user and jamming signals with distinct precoding vectors. Based on the assumption that the channel state information relating to the eavesdropper is unknown by the legitimate nodes, new precoding design algorithms are proposed. The jamming signals are designed to ensure that minimum interference is perceived by the other source node. The precoding vectors of the user signals are designed to form two parallel vectors in the equivalent wiretap channel at the eavesdropper. Two algorithms are proposed based upon the zero-forcing and matched-filter schemes, which are dubbed the selective zero-forcing-based precoding (SZFP) and matched-filter-based precoding schemes. Analytical and simulation results are presented to demonstrate that the SZFP algorithm is more applicable when the eavesdropper is equipped with a large number of antennas or the eavesdropper's channels are in good condition.

View synthesis prediction (VSP) is a crucial coding tool for improving compression efficiency in the next generation 3D video systems. However, VSP is susceptible to catastrophic error propagation when multi-view video plus depth (MVD) data are transmitted over lossy networks. This paper aims at accurately modeling the transmission errors propagated in the inter-view direction caused by VSP. Toward this end, we first study how channel errors gradually propagate along the VSP-based inter-view prediction path. Then, a new recursive model is formulated to estimate the expected end-to-end distortion caused by those channel losses. For the proposed model, the compound impact of the transmission distortions of both the texture video and depth map on the quality of the synthetic reference view is mathematically analyzed. Especially, the expected view synthesis distortion due to depth errors is characterized in the frequency domain using a new approach, which combines the energy densities of the reconstructed texture image and the channel errors. The proposed model also explicitly considers the disparity rounding operation invoked for the sub-pixel precision rendering of the synthesized reference view. Experimental results are presented to demonstrate that the proposed analytic model is capable of effectively modeling the channel-induced distortion for MVD-based 3D video transmission.

One of the fundamental problems in cryptography is the generation of a common secret key between two legitimate parties to prevent eavesdropping. In this paper, we propose an information-theoretic secret key generation (SKG) method for time division duplexing (TDD)-based orthogonal frequency-division multiplexing (OFDM) systems over multipath fading channels. By exploring physical layer properties of the wireless medium, i.e., the reciprocity, randomness, and privacy features of the radio channel, an SKG method is proposed to maximize the number of secret bits given a target secret key disagreement ratio (SKDR). In the proposed SKG method, the phase information of the estimated channel state information (CSI) is distilled for SKG, and a special guard band (GB) scheme is designed to achieve the target SKDR with a small phase information loss. The proposed GB consists of both the amplitude GB (AGB) and phase GB (PGB), where the AGB is determined by the average signal-to-interference plus noise ratio (SINR), whereas the PGB adapts itself to the instantaneous SINR and thus incurs a smaller phase information loss in the higher SINR region. Analyses show that this GB scheme trades off a small loss of channel phase information for a better SKDR performance, and achieves a much larger number of quantization levels for a given SKDR due to the fact that the PGB decreases quickly as the SINR increases. Based on the performance analysis on the SKDR, the average secret key length, the phase information loss percentage (PILP), and the optimal GB and quantization level of the adaptive quantizor are derived for a given target SKDR. Both analytical and simulation results are presented to demonstrate the superiority of the proposed scheme for TDD-OFDM systems over frequency-selective fading channels.

In this paper, low-complexity time-domain turbo equalization (TDTE) detectors based upon soft-interference-cancellation (SIC)-aided minimum mean-square error (MMSE) criterion are proposed for single carrier generalized spatial modulation (SC-GSM) systems. First, a symbol-by-symbol-aided TDTE detector for application to the small-scale GSM systems is proposed, where the zero symbols are considered as constellation points when performing SIC. Then, vector-by-vector-aided TDTE (VV-TDTE) detectors for application to larger-scale antenna systems are introduced, where the GSM symbol is treated as an entire vector when performing SIC. As for the proposed VV-TDTE detectors, in addition, different time-varying filter coefficients are designed, in order to strike a flexible tradeoff between complexity and performance. By relying upon extrinsic information transfer chart analysis, we show that the proposed TDTE detectors are capable of providing considerable bit error rate performance gains over existing TDTE detectors and over the classic frequency-domain equalization-based MMSE detector, especially for the unbalanced antenna configurations.

This paper proposes a new frequency-domain pre-coding algorithm for the downlink multi-user MIMO system in a frequency-selective fading channel, where each user is equipped with multiple antennas. The proposed algorithm is based on the minimum sum-mean-square-error (Min-SMSE) criterion, which is able to eliminate both the multi-user and multi-antenna interferences, resulting in an improved bit error rate (BER) performance. Compared with the traditional optimal Min-SMSE algorithm, the proposed algorithm can reduce the computational complexity through simplifying the iterative and power allocation processes. Furthermore, the theoretical BER and ergodic sum-rate are derived in detail. In addition, we define and analyze the complexity of the pre-coding algorithms. Simulation results show that the proposed algorithm compares favorably with the optimal Min-SMSE and traditional block diagonalization (BD) algorithms in the sense of the ergodic sum-rate due to the approximately equal power allocation. The BER performance of the proposed algorithm is close to that of the optimal one and much better than that of the BD algorithm in both the uncorrelated and correlated channels. Moreover, the computational complexity of the sub-optimal Min-SMSE algorithm is significantly less than that of its optimal counterpart, especially in the low SNR region.

Maximizing the lifetime is an important issue in the design of applications and protocols for wireless sensor networks (WSNs). Clustering sensor nodes is an effective topology control approach helping achieve this goal. In this paper, we present an energy efficiency protocol to prolong the network lifetime based on an improved particle swarm optimization (PSO) algorithm. The protocol takes both energy efficiency and transmission distance into consideration, and the relay nodes are used to balance the heavy consumption of cluster heads. In this way, the network results in better distributed sensors and a well-balanced clustering system enhancing the network's lifetime. We compare the proposed protocol with comparative protocols in different scenarios. Simulation results show that the proposed protocol performs well over other comparative protocols in various scenarios.

In Mars-to-Earth communications, data transmission suffered severe losses due to the huge path-loss, extremely long propagation delay and lack of line-of-sight link in rovers-to-Earth. Based on delay/disruption tolerant networks (DTN), we proposed a systematic Raptor Network Coding (RNC) scheme for the multi-rovers transform data through an orbiter to Earth station communication scenarios. To enhance the reliability of rover-to-Earth file delivery, and considering the limited capacity of the relaying orbiter, a simplified network coding scheme is designed for the orbiter. We analyzed the asymptotic performance of RNC scheme. Moreover, an improved RNC (IRNC) scheme is optimized in a finite code-length and limited coding complexity. Simulation results show that, our RNC and IRNC schemes can achieve better performance in comparison with existing distributed rateless erasure codes.

A distributed antenna system (DAS) is very attractive, since it can reduce transmit power by shortening the distance between antenna elements (AEs) and the mobile station. This paper investigates the channel capacity of the DAS over a multi-path frequency-selective fading channel. We first show that the optimal power allocation solution to approaching the channel capacity is unrealistic for the practical DAS. Then, a near-optimal scheme is given through maximally tightening the upper bound of the channel capacity. Approximate analytical results are obtained through the use of the central-limit theorem. Both simulation and theoretical results are presented to show that the channel capacity can be greatly enhanced by the proposed power allocation schemes. Moreover, the bit error rate performance is analyzed for the proposed scheme.

Light field (LF) technology has been popularly adopted by a wide range of conventional industries. However, one problem when dealing with LFs is the sheer size of data volume. There have been many multi-view video coding (MVC)-based LF video coding methods reported in the literature, aiming at finding the best prediction structure for LF video coding. It is clear that the number of possible prediction structures is unlimited, and it is also observed that the coding bit-rate can be reduced by increasing the number of bi-directionally encoded views in the prediction structure. However, none work has been conducted to analyze the relationship of the prediction structure with its coding performance. In light of this observation, we first design a new LF-MVC prediction structure by extending the inter-view prediction into a two-directional parallel structure. Analytical models for source coding rate and encoding time are developed to analyze their relationships with the prediction structure, and are proven to be well-matched to our experimental results. Experimental evaluation of two LF video sequences demonstrates that the proposed LF-MVC prediction structure can achieve a factor of 26% bit-rate reduction against the conventional MVC prediction structure for an LF video with 5×5 views, and a further 34% bit-rate reduction for an LF video with a larger 10×10 views. Compared with the state-of-the-art MVC-based LF video coding prediction structures in the literature, LF-MVC can achieve the best coding performance, and with its high encoding efficiency, is well suited for deployment in practical LF-based 3D systems.

The physical-layer network coding (PNC) becomes a popular research topic, and the multiuser PNC network is still an open issue. This paper investigates the uniquely-decodable codes (UDC) by using Iterative construction algorithm, and applies the generated UDC to the multiuser PNC network that based on amplify-and- forward (AF) criterion. Due to the attractive features of UDC, the sum data rate can increase with the number of users log-linearly. Moreover, only two time slots are needed for any user node to obtain the data sequences transmitted by an arbitrary user, no matter of the users' number. It is also illustrated that the theoretical bit error rate (BER) of the proposed scheme, which can compare with the traditional PNC scheme in both simulated and theoretical results.

View synthesis prediction (VSP) is an important tool for improving the coding efficiency in the next generation three-dimensional (3-D) video systems. However, VSP will result in a new type of inter-view error propagation when the multi-view video plus depth (MVD) data are transmitted over the lossy networks. In this paper, this new type of error propagation is characterized and modeled. Firstly, a new analytic model is formulated to estimate the expected transmission distortion caused by error propagation from the synthesized reference view. Then, the compound impact of the transmission distortions of both the texture video and the depth map on the quality of the synthetic reference view is mathematically analysed. Our extensive simulation results demonstrate that the proposed transmission distortion model is very accurate.

The performance of RFID MAC protocols greatly influences RFID systems. Previous research work concentrates on reducing either the recognition time or the energy consumption of tags. In this work, we develop an efficient RFID MAC protocol which shows good performance in terms of both low energy consumption at tags and average recognition time to recognize one tag. We propose an efficient M-ary detecting tree RFID MAC protocol which uses a specially designed bit-detecting mechanism to recognize tags. Simulation results proves that the proposed protocol outperforms existing schemes in the literature in both energy consumption at the tag side and average recognition time.

This paper analyzes how transmission errors in the texture and depth map jointly affect the synthesized virtual view in 3-D video coding. In particular, we propose a framework that decouples the effects attributed to transmission errors in texture and depth to facilitate theoretical analysis. The synthesis distortion due to depth map errors is characterized in the frequency domain using a new approach that combines the energy density of the reconstructed texture and channel errors. Experimental results show that our analytical model can accurately estimate the rendering view quality.

View synthesis prediction (VSP) is an important tool for enhancing the coding efficiency in the next-generation three- dimensional (3-D) video systems. However, VSP will lead to prediction position errors when the depth maps are corrupted by packet losses during transmission. In order to mitigate the prediction position errors, a novel disparity vector correction algorithm is proposed in this paper. Firstly, we investigate the relationship between the rendering position errors and the depth errors according to the VSP procedure. The depth map errors due to packet losses are then recursively estimated at the decoder without the use of the error-free reconstructed frames. Finally, based on the estimation of the reconstructed depth errors, the received disparity vectors can be corrected to find the matching synthesized pixels as those used at the encoder, and thereby the view synthesis-based inter-view error propagation can be effectively stopped. Experimental results show that the proposed methods with the estimated and actual depth errors can provide significant improvements in terms of both objective and subjective evaluations.

In this paper, we considered a practical system where the number of base station antennas serving tens users is large but finite. The signal must be collected before detection, and the optimal maximum a posteriori (MAP) detector has high computational complexity that grows exponentially with the number of users. Even the suboptimal MMSE-SIC (soft interference cancellation) requires complexity proportional to the cube of the number of the antenna units. In this paper, we proposed a distributed detection scheme done at each antenna unit separately, termed complex Gaussian belief propagation algorithm (CGaBP), for multicell multi-user detection. The multiuser detection problem is reduced to a sequence of scalar estimations, and detecting each individual user using CGaBP is asymptotically equivalent to detecting the same user through a scalar additive Gaussian channel with some degradation in the signal-to-noise ratio (SNR) of the desired user due to the collective impact of interfering users. The degradation is determined by the unique fixed-point of state evolution equations. Numerical results show that CGaBP has low complexity and overhead, and achieves optimal data estimates for Gaussian symbols, and is better than MMSE-SIC for finite-alphabet symbols.

Cooperative communication systems employ cooperation among nodes in a wireless network to increase data throughput and robustness to signal fading. However, such advantages are only possible if there exist perfect synchronization among all nodes. Impairments like channel multipath, time varying phase noise (PHN) and carrier frequency offset (CFO) result in the loss of synchronization and diversity performance of cooperative communication systems. Joint estimation of these multiple impairments is necessary in order to correctly decode the received signal in cooperative systems. In this paper, we propose an iterative pilot-aided algorithm based on expectation conditional maximization (ECM) for joint estimation of multipath channels, Wiener PHNs, and CFOs in amplify-and-forward (AF) based cooperative orthogonal frequency division multiplexing (OFDM) system. Numerical results show that the proposed estimator achieves mean square error performance close to the derived hybrid Cramer-Rao lower bound (HCRB) for different PHN variances.

In this paper, we proposed a distributed detection scheme done at each antenna unit separately, termed complex Gaussian belief propagation algorithm (CGaBP), for multicell multi-user detection in imperfect channel state information (CSI) scenarios. The multi-user detection problem is reduced to a sequence of scalar estimations, and detecting each individual user using CGaBP is asymptotically equivalent to detecting the same user through a scalar additive Gaussian channel with some degradation in the signal-to-noise ratio (SNR) of the desired user due to the collective impact of interfering users. The degradation is determined by the unique fixed-point of state evolution equations. We demonstrate the performance of the CGaBP through simulations. The performance of the CGaBP algorithm is better than that of the MMSE-SIC (soft interference cancellation) detector. However, the CGaBP algorithm degrades in the presence of imperfect CSI due mainly to pilot contamination in channel estimation.

Joint decoding of all users' data symbols can be distributed across a network of interacting base stations by message passing techniques. Unfortunately, for discrete belief propagation, the computational complexity grows exponentially with the number of interfering users at each base station, and the messaging overhead grows linearly with the order of modulation constellation. In this paper, the complex Gaussian belief propagation algorithm (CGaBP) is proposed for finite-alphabet symbols. The multi-user detection problem is reduced to a sequence of scalar estimation, and detecting each individual user using CGaBP is asymptotically equivalent to detecting the same user through a scalar additive Gaussian channel with some degradation in the signal-to-noise ratio (SNR) of the desired user due to the collective impact of interfering users. Numerical results show that the proposed method is of low complexity and overhead, and achieves near-optimal data estimates for Gaussian symbols. Moreover, for finite-alphabet symbols, the performance is better than limited cooperation via clustering in the sense of the bit error rate.

Power consumption and costs of analogue front‐end (AFE) chains are often not negligible for large‐scale antenna array systems. A low‐complexity hardware architecture is to use a number of AFE chains that are less than the number of antennas. Beamforming for this low‐complexity hardware architecture involves both digital and analogue beamforming, which is termed hybrid analogue/digital beamforming. In this study, minimising the transmit power subject to signal‐to‐interference‐plus‐noise ratio (SINR) constraints and maximising the minimal SINR under the constraint of the transmit power, are investigated, respectively, for hybrid analogue/digital beamforming. Properties on the feasibility and optimality of the two problems are derived. Numerical algorithms based on semi‐definite positive relaxation are proposed in an attempt to solve the two optimisation problems. The performance of the proposed algorithms is evaluated under the Gaussian and 60 GHz channel models. It is shown that the performance of hybrid analogue/digital beamforming is highly related to the correlation of the channel coefficients of subcarriers. Additionally, for different extents of the users’ spatial separability, some heuristics ways of designing analogue beamforming are shown to be able to approach to at least the local optimums under the 60 GHz channel model.

This study proposes a novel adaptive network‐coded rateless coding scheme for an erasure multiple‐access relay system with two distributed sources and an asymmetric network topology. To increase transmission efficiency, a two‐dimensional degree distribution, as part of network‐coded relay protocol, is designed based on the AND–OR tree analysis technique. The degree distributions of rateless coding at the sources and network coding at the relay are optimised by the linear programming approach under asymmetric channel conditions. Simulation results demonstrate that the proposed scheme outperforms existing classical relay protocols under time‐varying channel conditions, and achieves a significantly better performance.

This study investigates the security of the two‐way relaying system with untrusty relay nodes. Cooperative jamming schemes are considered for bi‐directional secrecy communications. The transmit power of each source node is divided into two parts corresponding to the user and jamming signals, respectively. Two different assumptions of the jamming signals are considered. When the jamming signals are a priori known at the two source nodes, closed‐form power allocation expressions at two source nodes are derived. Under the assumption of unknown jamming signals, it is proven that the cooperative jamming is useless for the system secrecy capacity, because that all the power should be allocated to the user signals at each source node. Relay selection is also investigated based on the analysis of cooperative jamming. Simulation results are presented to compare the system secrecy capacities under the two jamming signal assumptions.

Carrier aggregation has been accepted as a means of bandwidth extension in the third generation long‐term evolution‐advanced (LTE‐advanced) network, in an effort to support high data rate transmission with backwards compatibility. Since there are two or more component carriers (CCs) to be aggregated, it is crucial to design efficient carrier scheduling schemes. In this study, the authors propose a novel dynamic aggregation carrier (DAC) scheme for downlink transmission, which enables CCs to aggregate with each other in a dynamic manner. The dynamic nature of the new scheme allows the total capacity of all CCs to be fully utilised to serve flows, whereas the number of aggregated supplementary CCs is decreased so as to lower the computational complexity at user equipment (UE). Furthermore, the performances of the new scheme and two other carrier scheduling schemes are evaluated thoroughly through both analytical and simulation results. It is demonstrated that the DAC scheme offers good performances in terms of delay and throughput while reducing energy consumption and the signalling overhead at UEs.

Energy efficiency is of vital importance for telecommunications equipment in future networks, especially battery-constrained mobile devices. In the long term evolution-Advanced (LTE-Advanced) network, the carrier aggregation (CA) technique is employed to allow user equipment (UE) to use multiple carriers for high data rate communications. However, multi-carrier transmission entails increased power consumption at user devices in uplink networks. In this paper, we propose a new dynamic carrier aggregation (DCA) scheduling scheme to improve the energy efficiency of uplink communications. Two scheduling methods, i.e., serving the longest queue (SLQ) and round-robin with priority (RRP), are designed to reduce transmit power while maximizing the utilization of wireless resources. The proposed scheme is analyzed in terms of both the data rate and energy conservation. We build an ideally balanced system (IBS) to investigate the performance upper bound of the DCA scheme, and derive closed-form expressions. Simulation results demonstrate that the proposed scheme can not only enhance the energy efficiency but also perform closely to the optimal IBS.

Oscillator phase noise (PHN) and carrier frequency offset (CFO) can adversely impact the performance of orthogonal frequency division multiplexing (OFDM) systems, since they can result in inter carrier interference and rotation of the signal constellation. In this paper, we propose an expectation conditional maximization (ECM) based algorithm for joint estimation of channel, PHN, and CFO in OFDM systems. We present the signal model for the estimation problem and derive the hybrid Cramér-Rao lower bound (HCRB) for the joint estimation problem. Next, we propose an iterative receiver based on an extended Kalman filter for joint data detection and PHN tracking. Numerical results show that, compared to existing algorithms, the performance of the proposed ECM-based estimator is closer to the derived HCRB and outperforms the existing estimation algorithms at moderate-to-high signal-to-noise ratio (SNR). In addition, the combined estimation algorithm and iterative receiver are more computationally efficient than existing algorithms and result in improved average uncoded and coded bit error rate (BER) performance.

In this paper, a rate-distortion optimized coding mode switching scheme is proposed to improve error resilience for multi-view video plus depth (MVD) based 3-D video transmission over lossy networks. First, we derive a new end-to-end distortion model for MVD-based 3-D video transmission. As compared with the previous MVD-based video distortion models in which distortion is measured by only investigating the expected texture video errors and depth errors on the synthesized virtual view, the proposed scheme characterizes both the end-to-end distortions in the rendered virtual view and the coded texture video due to packet losses. Moreover, inter-view error propagation for the texture video and depth map is also considered. Based on the proposed distortion model, an optimal mode decision algorithm is then performed in the texture video and depth map coding process. Experimental results show that the proposed method provides significant improvements in terms of both objective and subjective evaluations.

Due to the overwhelming complexity of multihop transmission and intermessage interference, only a limited amount of research has been carried out in the implementation of wireless network coding (WNC) for generalized multihop two-way relay channels (MH-TRCs), let alone the generalization of multihop WNC (MH-WNC) schemes. Our recent paper has showed that the MH-WNC scheme with fixed two transmission time intervals (TTIs) was unable to always outperform conventional non-NC schemes in outage performance for the MH-TRC with an arbitrary number of nodes. In view of this fact, a generalized MH-WNC scheme with multiple TTIs is designed for the L-node K-message MH-TRC in this paper. Closed-form expressions for the upper bound of the outage probability for two prominent relaying network coding strategies (i.e., analog network coding and compute-and-forward network coding) are derived. Moreover, by investigating the relationships between the outage probability and the numbers of nodes, messages, and TTIs, we obtain an optimal MH-WNC scheme that can achieve the best outage probability and always outperform non-NC in the MH-TRC with an arbitrary number of nodes.

Antenna calibration to enhance the channel reciprocity between the uplink and downlink channels is necessary for the practical wireless system operating in the time division duplexing (TDD) mode. This paper investigates on the computation of the antenna calibration coefficients of the cooperative base stations' antennas in the network multiple-input and multiple-output (MIMO) system. An efficient scheme for computing the calibration coefficients for an arbitrary number of distributed antennas is proposed. In addition, we also propose two methods of refining the calibration coefficients for the proposed scheme. The evaluations of the proposed scheme and methods are performed through computer simulations.

An electromagnetic relay test system is designed based on the 32-bit floating-point Microcontrollers (MCU): TMS320F28335. In the test system, the relay characteristic parameters, such as the coil resistance, pull-in voltage, release voltage and time parameters, can be tested by sampling of the relay coil current, electric shock voltage and drive supply voltage. The tested results can be displayed on the LCD and transmitted to PC. The sampling frequency of the system is 10 M Hertz, which is higher than the other relay test system. The whole system is portable and has low power consumption. Finally, the experimental results verify that the required parameters of the relay can be tested accurately using the designed system.

Orthogonal frequency division multiplexing (OFDM) has been adopted as a promising technique to mitigate multi-path fading and provides high spectral efficiency in broadband communications. In this paper, we investigate resource allocation and sub-carrier permutation in OFDM-based hybrid relay protocol over frequency-selective channels. Selective multicarrier-adaptive hybrid relay protocol (MC-AHRP), involves the sub-carrier utilizing an amplify-and-forward (AF) scheme when the instantaneous signal-to-noise ratio (SNR) is larger than threshold value and an adaptive decode-and-forward (ADF) scheme when the instantaneous SNR is less than threshold value. The proposed protocol exploits the benefits of adaptive hybrid relay protocol, OFDM, resource allocation, and sub-carrier permutation to provide a substantial enhancement in the system performance. The simulation results show that when the protocol performs resource allocation (RA) and sub-carrier permutation (SP) can provide an excellent improvement in the capacity of the system. It also demonstrate that the proposed protocol can achieve a significant improvement in throughput compared with conventional protocols.

The security of the two-way relaying system with an eavesdropper is investigated in this paper. A cooperative jamming and power allocation scheme is proposed to enhance the system secrecy capacity. Both user and pre-defined jamming signals are transmitted by each source node simultaneously. The optimum power allocation between the user and jamming signals at each source node is derived. Our analytical results suggest that the proposed cooperative jamming scheme improves on the system secrecy capacity, especially when the channel gains of the two source-relay links are of large difference. Simulation results in close agreement with analytical results clearly demonstrate the advantage of the proposed cooperative jamming scheme.

Wireless network coding for multi-hop two-way relay channels (MH-TRC) has been proven to achieve a significantly improved network throughput than non- network coding (Non-NC) schemes. Our previous work showed that the multi-hop compute-and-forward (MH- CPF) scheme for the MH-TRC with fixed two transmission time intervals was unable to outperform Non-NC in the MH-TRC with an arbitrary number of nodes. In view of this fact, we propose anI-time- interval (I-TI) MH-CPF scheme (Irepresents the number of transmission time intervals) for the MH- TRC with arbitrary numbers of nodes and messages. By converting the transmission pattern to a corresponding characteristic matrix, the outage probability of theI-TI MH-CPF scheme is derived. We investigate the relationships between the numbers of nodes, messages and TIs with the outage probability. It is proven thatL-1-TI MH-CPF can outperform 2-TI MH-CPF when the number of messages is large, while the MH-CPF scheme with a larger number of TIs has better outage performance than 2-TI MH-CPF in the MH-TRC with a small number of nodes.

The security of the three-phase two-way relaying system with an eavesdropper is investigated in this paper. A cooperative jamming and power allocation scheme is proposed to enhance the system secrecy capacity. When a source node transmits user signals to the relay node, the other source node interferes the relay node with pre-defined jamming signals simultaneously. Optimum power allocation between the user and jamming signals at each source node is analyzed. Our analytical results suggest that the proposed cooperative jamming scheme improves on the system secrecy capacity, especially when the channel gains of the two source-relay links are of large difference. Simulation results in close agreement with analytical results clearly demonstrate the advantage of the proposed cooperative jamming scheme.

In this paper, we propose a new unequal error protection (UEP) scheme, called video packet partitioning for three-dimensional (3-D) video transmission. We also propose a new 3-D video transceiver structure that adopts various UEP schemes based on the packet partitioning. The proposed schemes are applied for the modern 3-D video techniques, i.e., multiview video coding (MVC) and color plus depth (VpD). The schemes for MVC and VpD are tested over cooperative multiinput multi-output-orthogonal division multiplexing (MIMOOFDM) systems. For channel adaptation, we propose switching operations between the proposed schemes to achieve a trade-off between the system complexity and performance. Experimental results show that the proposed schemes significantly achieve high video quality at different signal-to-noise ratios (SNRs) in the wireless channel with the lowest possible bandwidth and system complexity compared to the direct transmission schemes.

With the advent of small‐cell networks (SCNs) to support growing wireless data volumes and thus reduced cell sizes, cooperative communications are significantly facilitated. Applicable to Third Generation Partnership Project long‐term evolution‐A, the authors propose a novel channel/queue‐aware user pairing and scheduling scheme in a cooperative virtual multiple‐input–multiple‐output (VMIMO) system. The queueing performance of the VMIMO system with the scheduling scheme is analysed based on the finite‐state Markov model (FSMM), and compared with that of non‐cooperative systems. Bounds on the average queuing delay of users are derived by using a semi‐definite programming (SDP) approach. The presented analyses are validated through comparing the analytical and simulation results. It is found that the introduced VMIMO pairing process is able to significantly reduce service delays, bringing on a positive impact of cooperative techniques on next generation wireless systems.

Analog to digital converters (ADC) and cascade integrator-comb (CIC) filters are the basic modules in a digital intermediate frequency (IF) spectrum analyzer. The optimal output signal-to-noise ratio (SNR) of the digital IF spectrum analyzer with the Gaussian input signal is considered in this letter. The idea is to strike a trade-off between the saturation error and granular error when quantizing the Gaussian input signal. This letter firstly derives a relationship among the maximum allowed input signal amplitude, input signal power, ADC quantization bits and optimal quantization SNR. Besides, an optimal clipping strategy for the CIC decimation filter with variable decimation rates is proposed. Both numerical and simulation results are presented to demonstrate that the proposed clipping method is able to achieve significant SNR gain compared with the traditional rounding or truncation method.

The secrecy capacity of relay communications is investigated in this paper, where an eavesdropper is present. Distributed precoding through multiple relay nodes can be used to enhance the received signal power at the destination node and to mitigate the signal leakage to the eavesdropper, simultaneously. Due to individual power constraints at relay nodes, the distributed precoding scalar at each relay node is equivalent to a distributed precoding angle. An iterative algorithm is proposed to find the suboptimum distributed precoding angles at all the relay nodes, where the channel state information (CSI) sharing overhead among the relay nodes can also be substantially reduced. Each relay node receives the equivalent CSI from its preceding relay node, computes its distributed precoding angle, and updates the equivalent CSI for the next relay node. Compared with the simple decode-and-forward relaying protocol with random distributed precoding, the proposed iterative distributed precoding algorithm is able to further improve on the secrecy capacity of the multirelay wiretap system with an acceptable CSI sharing overhead.

The two-way multiple-input and multiple-output relay system is investigated in this paper, where bi-directional communications between two source nodes are supported by a relay node with multiple antennas. The achievable diversity order of the three-phase two-way relaying protocol based on zero-forcing is derived. It is found in this paper that the upper bound of the diversity order is related to the number of antennas at the relay node and the number of data streams. Numerical and simulation results are presented to validate theoretical analysis.

Carrier aggregation is one of the key techniques for the advancement of long-term evolution (LTE- Advanced) networks. This article proposes a quality- of-experience (QoE)-based carrier scheduling scheme for networks with multiple services. The proposed scheme aims at maximizing the user QoE, which is determined by both the application-level and network-level quality of services. Packet delay, as an essential factor affecting QoE, is first discussed under the context of QoE optimization as well as the data rate. The component carriers are dynamically scheduled according to the network traffic load by the proposed novel scheme. Simulation results show that our approach can achieve significant improvement in QoE and fairness over conventional approaches.

In this paper, we propose a novel method suitable for unequal error protection(UEP) and unequal recovery time (URT) properties, namely the Duplicating-Expanding Window Fountain(D-EWF) codes. We implement duplicating windows and expanding windows techniques to improve the performance of both more important bits (MIB) and less important bits (LIB). We analyze the proposed method over binary erasure channels (BEC) by using asymptotic analysis. The D-EWF codes inherit the advantages of both EWF codes and the duplicating windows method. Therefore the UEP property of D-EWF codes is more obvious. Furthermore BER performance of LIB of D-EWF codes converges very fast. Compared with the previous UEP schemes, simulation results show that the D-EWF codes can provide better UEP performance.

Recently, distributed resource allocation for relay enhanced cellular networks has gained increasing attention. However, it poses a new challenge for the backhaul link scheduling. In this paper, we propose a queue-status-based resource allocation scheme for the backhaul link in a distributed manner in relay enhanced networks. By applying this scheme, the evolved Node B (eNB) adjusts the data rate for each user equipment (UE) in the backhaul link according to its queue status at the relay node (RN). It can guarantee the rate match between the backhaul and access links while minimizing feedback signaling. Simulation results show that the proposed scheme can achieve a good tradeoff between the spectral efficiency and the signaling overhead.

Unlike conventional cellular networks where the evolved Node B (eNB) performs centralised scheduling, future relay-enhanced cellular (REC) networks allow relay nodes (RNs) to schedule users independently. This decentralised nature of the REC networks brings about challenges to maintain fairness. In this study, we formulate the generalised proportional fair (GPF) resource allocation problem, where resource partition and routing are included as part of the overall radio resource management aiming to provide fairness across all users served by the eNB and its subordinate RNs. Although the traditional proportional fair scheduling algorithm is executed independently at the eNB and each RN to maintain local fairness, we propose efficient resource partition and routing algorithms to maintain global fairness by optimising the GPF objective for the whole relay-enhanced cell. Through system level simulations, the proposed algorithms are evaluated and compared with both non-relaying and relaying systems with benchmark resource partition and routing algorithms. The simulation results show that the proposed algorithms outperform the existing algorithms in providing a better trade-off between system throughput and fairness performance.

This paper presents a new face detection approach which is capable of detecting human faces from complex backgrounds. A new skin color modeling process is applied to the face segmentation process. Image enhancement is then used to improve the features of face candidates before feeding to the face object classifier which is based on a modified Hausdorff distance. The overall performance of the face detection system is evaluated and achieved a success rate of 87.5 %.

In 3GPP LTE-Advanced networks deployed with type I relay nodes (RNs), resource partition is required to support in-band relaying. This paper focuses on how to partition system resources in order to attain improved fairness and efficiency. We first formulate the generalized proportional fair (GPF) resource allocation problem to provide fairness for all users served by the evolved node B (eNB) and its subordinate RNs. Assuming traditional proportional fair scheduling is executed independently at the eNB and each RN to achieve local fairness, we propose the proportional fair resource partition algorithm to tackle the GPF problem and ensure global fairness. Through system level simulations, the proposed algorithm is evaluated and compared with both non-relaying and relaying systems with the fixed resource partition approach. Simulation results demonstrate that the proposed algorithm can achieve a good trade-off between system throughput and fairness performance.

Diversity is an effective technique to enhance link quality and increasing network capacity. In this paper, we propose a generalized distributed turbo codes (DTC)-based coded cooperation protocol for two-hop relay networks with an arbitrary number of relays. This scheme aims at achieving improved diversity over the classical coded cooperation method in Rayleigh fading channels. We develop a closed-form expression for the pairwise error probability (PEP) and a tight upper bound for the bit error rate (BER) using DTC. The results demonstrate the merits of DTC-based coded cooperation with multiple relays, under various relay and uplink channel conditions. Moreover, the analytical upper bounds are validated with simulation results.

In real environments, channel reciprocity cannot be directly exploited between uplink and downlink in time-division duplex (TDD) due to antenna gain mismatch. Previous work about antenna calibration mainly focused on single cell. This work proposes an adaptive scheme for antenna calibration between two cooperative BSs. The proposed scheme aims at achieving an equal ratio between antenna transmitter and receiver analog gains among cooperative BSs in flat fading channels. The essential idea is to relay calibration parameter through a calibration path. This procedure can be controlled by a certain BS dubbed primary BS. Evaluation of the proposed scheme is carried out by computer simulation.

Cooperative communications enable single antenna mobiles in a multi-user environment to share their antennas and form a virtual multiple antenna array that allows them to achieve transmit diversity. In order to achieve improved diversity over the classical coded cooperation method in fading channels, we consider a coded cooperation diversity strategy that is suitable for multiple relays channels. We derive a finite range single integral solution for the outage probability, which characterize the coded performance with multiple relays at various rates. Numerical results demonstrate the merits of coded cooperation and other repetition-based methods, under various relay and uplink channel conditions, and show that it achieves the full diversity order.

Antenna gain mismatch between transmitter and receiver circuits has been regarded as an obstacle for exploiting channel reciprocity between uplink and downlink channels in time-division duplex (TDD) multiple-input multiple-output (MIMO) systems. To the best knowledge of the authors, little work to date has been on about the impact of antenna mismatches on the precoding vector. Motivated by this fact, this paper investigates some characteristics of downlink precoding in the presence of non-ideal antenna gains. Specifically, properties about inter-MS interference when mismatches exist at the base station (BS) side are presented as well as the perturbation of non-normalized precoding vector caused by mismatches at the mobile station (MS) side under two kinds of linear precoding algorithms. These properties are mostly irrelevant to specific distributions of antenna mismatch parameters and can help to provide a deeper insight into the antenna gain mismatch problem and the corresponding calibration.

This paper focuses on how to associate users with serving nodes in order to achieve improved fairness and efficiency for the cellular networks enhanced with multiple relay nodes (RNs). We first formulate the generalized proportional fair (GPF) problem with the aim of providing fairness for all users served by the evolved node B (eNB) and its subordinate RNs. Routing is incorporated into the GPF problem as part of the resource allocation strategy. Assuming traditional proportional fair (PF) scheduling algorithm is executed independently at the eNB and each RN, we propose efficient PF-based routing algorithm aiming at optimizing the GPF objective, which also takes into account the impact of relay link resource allocation. Through system-level simulations, the proposed algorithm is evaluated and compared with both non-relaying and relaying systems with benchmark routing algorithms. Simulation results demonstrate that the proposed algorithm can achieve better system throughput and fairness performance.

This paper investigates a novel relaying strategy for cooperative networks over Nakagami-m fading channel, namely selection incremental relaying (SIR), which combines selection relaying (SR) with incremental relaying (IR) based on decode-and-forward (DF). The closed-form expression for the outage probabilities of both single relay and opportunistic relay strategies are derived. Simulation results confirm the presented mathematical analysis and show that the proposed SIR strategy outperforms DF, SR and IR strategy over all signal-to-noise ratio (SNR) values.

We investigate the performance of analog network coding (ANC) for multi-hop networks in this paper. With the amplify-and-forward (AF) protocol, relays broadcast the sum of two colliding signals to neighboring nodes, while the source node can subtract its own signal from the colliding signal to obtain the received information. We first give the transmission scheme expressions for the n-node m-frame two-way multi-hop network. For this scheme, we derive the end-to-end signal-to-noise ratio (SNR) expression. Without loss of generality, the closed-form expression of the outage probability for the generalized multi-hop network is evaluated. Numerical results demonstrate that the outage performance with ANC is better than the traditional scheme without ANC.

Channel distortion modeling for generic multi-view video transmission remains a unfilled blank, despite that intensive research efforts have been devoted to model traditional 2-D video transmission. This paper aims to fill this blank through developing a recursive distortion model for multi-view video transmission over lossy packet-switched networks. Based on the study on the characteristics of multi-view video coding and the propagating behavior of transmission error due to random frame losses, a recursive mathematical model is derived to estimate the expected channel-induced distortion at both the frame and sequence levels. The model we develop explicitly considers both temporal and inter-view dependencies, induced by motion-compensated and disparity-compensated coding, respectively. The derived model is applicable to all multi-view video encoders using the classical block-based motion-/disparity-compensated prediction framework. Both objective and subjective experimental results are presented to demonstrate that the proposed model is capable of effectively model channel-induced distortion for multi-view video.

In this paper, we propose a distributed turbo product code (DTPC) with soft information relaying over cooperative network using block extended bose Chaudhuri Hochquenghem (EBCH) codes as component codes. The source broadcasts extended EBCH coded frames to the destination and to a preassigned relay. After soft-decoding the received sequences and obtaining the log-likelihood ratio (LLR) values, the relay constructs a product code by arranging the decoded bit sequences in rows and re-encoding them along the columns using a novel soft block encoding technique to obtain soft parity bits with different reliabilities that can be used as soft incremental redundancy (IR) for source's data which is forwarded to the destination. A modified turbo product decoder to cope with the data received over different channels and thus having different reliabilities is used at the destination. We compared the simulation results in additive white Gaussian noise (AWGN) channel using network scenarios with our previous work for decode and forward (DF) DTPC and with non-cooperative case. Results show 0.5 dB gain improvement over the non-cooperative turbo product codes (TPC) at bit error rate (BER) 10-4. In addition, the BER performance is less affected by the decoding errors at the relay.

In this paper, a mathematical model is proposed to estimate the distortion caused by random packet losses for multi-view video transmission. Based on the study of multi-view video coding, the proposed model takes into account the disparity/motion compensation which relates the channel-induced distortion in the current frame with that in the previous frame or the adjacent view, and allows for any motion-compensated and disparity-compensated concealment method at the decoder. Comparative studies between the modeled and simulated distortion results demonstrates that the proposed model is able to estimate the transmission distortion of multi-view video with high accuracy.

In this paper, a field-programmable gate array (FPGA) based enhanced architecture of the arithmetic coder is proposed, which processes two symbols per clock cycle as compared to the conventional architecture that processes only one symbol per clock. The input to the arithmetic coder is from the bit-plane coder, which generates more than two context-decision pairs per clock cycle. But due to the slow processing speed of the arithmetic coder, the overall encoding becomes slow. Hence, to overcome this bottleneck and speed up the process, a two-symbol architecture is proposed which not only doubles the throughput, but also can be operated at frequencies greater than 100 MHz. This architecture achieves a throughput of 210 Msymbols/sec and the critical path is at 9.457 ns.

Incremental selection amplify-and-forward relaying (ISAF) has the best performance of outage probability among relaying strategies and has been identified as the best protocol. This paper proposes to jointly optimize power allocation (PA) and best-relay position based on cooperative diversity for ISAF in order to minimize outage probability. The closed-form solution to the adaptive allocation algorithm based on high signal-to-noise ratio (SNR) approximation of outage probability is presented, assuming maximum ratio combining (MRC) at the destination. Simulation results have shown that the system performance of outage probability with the proposal outperforms the fixed PA algorithms, and much less power is needed to achieve the same outage probability at the same effective rate. The power saving can be as much as 9 dB compared to the equal power allocation scheme.

In this paper, we propose a novel 2-D layered multiple description coding (2DL-MDC) for error-resilient video transmission over unreliable networks. The proposed 2DL-MDC scheme allocates multiple description sub-bitstreams of a 2-D scalable bitstream to two network paths with unequal loss rates. We formulate the 2-D scalable rate-distortion problem and derive the expected distortion for the proposed scheme. To minimize the end-to-end distortion given the total rate budget and packet loss probabilities, we need to optimally allocate source and channel rates for each hierarchical sublayer of the scalable bitstream. The conventional Lagrangian multiplier method can be utilized to solve this problem but with overwhelming computational complexity. Therefore, we consider the use of the genetic algorithm to solve the rate-distortion optimization problem. The simulation results verify that the proposed method is able to achieve significant performance gain as opposed to the conventional equal rate allocation method.

This paper studies the system stability of a Model-Based Networked Control System in the cases where packet losses follow a certain distributions. In this study, the unreliable nature of network links is modelled as a stochastic process. This process provides us two system structures, representing packets dropped and received respectively. This new system with two structures is asymptotically stable, if the plant model is updated with the data from plant within the maximum interval and the packet drop follows discrete distributions with finite expectations such as Uniform Distribution and Bernoulli distribution. If the packet loss follows discrete distributions with infinite expectation such as Poissonian Distribution, the stochastic system is stable when the biggest interval is limited to the maximal update time interval. These results are verified in simulations.

We investigate the capacity of various ISI channels with adaptive white Gaussian noise. Previous papers showed a minimum E/sub b//N/sub 0/ of -4.6 dB, 3 dB below the capacity of a flat channel, is obtained using water pouring capacity formulas for the 1 + D channel. However, these papers did not take it into account that the channel power gain can be greater than one when water pouring is used. We present a generic power normalisation method of the channel frequency response, namely peak bandwidth normalisation, to facilitate the pair capacity comparison of various ISI channels. Three types of ISI channel, i.e., adder channels, RC channels and magnetic recording channels, are examined. By using our channel power gain normalisation, the capacity curves of these ISI channels are shown.

We investigate the capacity of various intersymbol interference (ISI) channels with additive white Gaussian noise (AWGN). Previous papers showed a minimum E/sub b//N/sub 0/ of -4.6 dB, 3 dB below the capacity of a flat channel, is obtained using water-pouring capacity formulas for the 1+D channel. However, these papers did not take into account that the channel power gain can be greater than one when water-pouring is used. We present a generic power normalization method of the channel frequency response, namely, peak bandwidth normalization (PBN), to facilitate the fair capacity comparison of various ISI channels. Three types of ISI channel, i.e., adder channels, RC channels, and magnetic recording channels, are examined. By using our channel power gain normalization, the capacity curves of these ISI channels are shown.

An investigation of unequal error protection (UEP) methods applied to JPEG image transmission using turbo codes is presented. The JPEG image is partitioned into two groups, i.e., DC components and AC components according to their respective sensitivity to channel noise. The highly sensitive DC components are better protected with a lower coding rate, while the less sensitive AC components use a higher coding rate. Simulation results are given to demonstrate how the UEP schemes outperforms the equal error protection (EEP) scheme in terms of bit error rate (BER) and peak signal to noise ratio (PSNR).