In Artificial Intelligence of Things (AIoT)-enabled edge sensing systems, unmanned aerial vehicles have emerged as the dominant low-altitude monitoring platform owing to their wide-area coverage. However, in large-scale surveillance scenarios, sensor limitations and the inherent difficulty in preserving discriminative features for tiny targets hinder robust small object detection. Therefore, we propose the MSFR-DEF-YOLO framework, which combines densely efficient flow YOLO (DEF-YOLO) with multi-scale feature reconstruction (MSFR) auxiliary branches. We first enhance fine-grained feature extraction by optimizing the network structure and integrating an efficient downsampling module (EDM). Next, a dynamic dense feature pyramid (DDFP) is designed to incorporate dense cross-layer connections and bidirectional feature flows, enhancing multi-scale context consistency. Additionally, the introduction of the MSFR auxiliary branch integrates shallow and deep features from the backbone network, enabling feature reconstruction and information compensation, thereby further improving small object detection capabilities. To verify the improvements, we tested a range of network configurations on different YOLO versions. Our model outperforms other versions in the YOLO series. Moreover, on four public datasets, MSFR-DEF-YOLO achieves mAP50 improvements of 8.8%, 6.9%, 1.8%, and 6% compared to YOLOv8n, all while using only 20% of the parameters of YOLOv8n. To further reduce the computational overhead, this paper proposes a lightweight MSFR-L-YOLO model that utilizes a unidirectional path neck design. Compared to MSFR-DEF-YOLO, this model reduces the number of parameters by 15% while maintaining high efficiency, thereby reducing computational requirements and achieving comparable accuracy. This provides an efficient solution for AIoT-enabled airborne sensing systems.

Intelligent reflecting surfaces (IRSs) mounted on maneuverable aerial platforms to form aerial IRS (AIRS) relays represent a novel paradigm for large-scale downlink transmission in smart cities. However, the challenge of multivariate dynamic coupling hinders most existing studies due to high computational complexity and limited scalability. To address these issues, this paper proposes a soft-attention-actor-critic (SAAC) optimization framework that efficiently decomposes the joint optimization of multi-AIRS deployment, passive beamforming, and active beamforming at the base station into two sequential subproblems. The objective is to maximize average downlink spectral efficiency and service fairness, while minimizing deployment energy consumption. In the first stage, a conservative lower bound of spectral efficiency is formulated to guide multiple AIRSs toward near-optimal deployment positions. In the second stage, refined optimization is performed for both passive and active beamforming matrices. Furthermore, multi-head attention modules are incorporated into the critic and actor networks in each phase, enabling AIRS to adaptively attend to the observations and actions of other agents, and enhancing the ability to handle high-dimensional observation-action spaces. Extensive simulation results validate that the proposed SAAC framework consistently outperforms mainstream deep reinforcement learning baselines across diverse network conditions, highlighting its superior performance and scalability.

In this work, we generalize the Stochastic Hybrid Systems (SHSs) analysis of Age of information (AoI) to the Age of Incorrect Information (AoII) metric. Hierarchical ageing processes are adopted using the continuous AoII for the first time. Two different hierarchy schemes are considered: 1). A hierarchy of zero and linear ageing processes with different slopes; 2). A hierarchy of zero, linear and exponential ageing processes. We first modify the main result in Yates (2020) to provide a systematic way to analyze the continuous hierarchical AoII over unslotted real-time systems. The closed-form expressions of average hierarchical AoII are obtained in two typical scenarios with different channel conditions, i.e., an M/M/1/1 queue over noisy channels and two M/M/1/1 queues over collision channels. Moreover, under each scenario, we analyze the stability issue regarding positive recurrence and provide the stability conditions that ensure a steady-state average AoII. Finally, we compare the closed-form results between average AoI and AoII in the M/M/1/1 queue. The effects of different channel parameters on the average hierarchical AoII are also evaluated.

Vehicular edge computing (VEC) enhances computational efficiency by strategically offloading tasks from vehicles to edge servers. Integrating semantic communication into vehicular networks introduces further benefits by leveraging semantic information to reduce task transmission delays. However, semantic-aware computation offloading encounters dual challenges: adaptively selecting semantic features to preserve task-critical meaning and dynamically allocating communication and semantic resources under varying network conditions. To cope with these challenges, we propose an importance-based hybrid-action multi-agent proximal policy optimization (I-HAMAPPO) algorithm for the semantic-aware vehicular computation offloading system in this paper. By assessing the importance scores of semantic features, an importance evaluation module (IEM) is designed to selectively transmit task-relevant information. A utility function, integrating task delay, energy consumption, and semantic similarity, is developed to provide a multi-dimensional performance evaluation of the system. Subsequently, the optimization problem is formulated with the objective of maximizing system utility by optimizing communication resources and semantic compression ratios. Considering the presence of mixed decision variables in the formulated problem, we employ the proposed I-HAMAPPO algorithm to optimize the continuous and discrete actions jointly. Based on real-world vehicle trajectories from the highD dataset, extensive experimental results demonstrate the convergence of I-HAMAPPO and its efficacy in maximizing system utility.

Mobile crowdsensing (MCS) enables data collection by leveraging the sensing capabilities of distributed mobile devices (MDs). However, its performance is often constrained by limited coverage and connectivity of ground-based sensors. To overcome these limitations, this paper presents an efficient data collection framework in unmanned aerial vehicle (UAV)-assisted MCS systems. The proposed framework leverages the aerial mobility of UAVs to enhance the spatial coverage of MCS. By optimizing flight trajectories of UAVs, we aim to balance the age of information (AoI) and energy consumption. Specifically, this work considers the mobility of MDs and introduces a communication-enhanced trajectory optimization (CETO) algorithm to improve UAV coordination and adaptability in dynamic environments. Simulation results demonstrate that the proposed algorithm significantly outperforms other mainstream baseline methods employing deep reinforcement learning (DRL).

Low-light image enhancement (LLIE) can be reformulated as an image-specific curve estimation (CE) problem. Traditional CE-based methods struggle with issues such as uniform processing across different regions, static parameter estimation, and lack of effective global semantic enhancement. To address these limitations, we propose a novel unsupervised learning framework, Patch-wise Dynamic Curve Estimation (PDCE), which dynamically adjusts and optimizes enhancement curves according to local patch brightness and the iteration process. Specifically, we present a Vision-Language Curve Discriminator (VLCD), which dynamically determines the curve type for each patch, avoiding uniformly applying the curve on the whole image. We introduce a Curve Parameter Estimator (CPE), which dynamically updates curve parameters and adjusts enhancement effects based on the output of the previous iteration. Furthermore, we design a Visual State Space-based Semantic Enhancement Module (VSEM), which captures global receptive fields and enriches semantic features through the Mamba-based U-Net architecture. Extensive experimental results show the superiority of our PDCE over state-of-the-art methods for LLIE.

Low-light images are commonly present due to imaging factors such as insufficient light, night shooting and back lit. Existing low-light image enhancement (LLIE) methods typically rely on a low-light input image for enhancement, which seldom leverage information contained in its high-light counterpart to restore image structures and handle complex lighting, leading to unsatisfactory image quality. In view of this, in this paper we propose a Collaborative Dual-Branch Spatial-Frequency Enhancement Network (CDSE-Net). Specifically, we apply the inversion operation to low-light images to self-generate high-light images and build a collaborative dual-branch network which enhances images sequentially in spatial and frequency domains. In the spatial domain, we leverage adaptive curve estimation and multi-direction convolutions to restore lightness and structure information, respectively. In the frequency domain, we perform amplitude interactions on dual-branch images and 1×1 convolution on phase features to adjust image lightness and structures, respectively. Finally, we introduce an illumination-aware attention module to fuse two branches. Experiments on several widely used datasets quantitatively and qualitatively demonstrate the advantages of our network over state-of-the-art methods for LLIE.

This paper investigates the joint design of the transmit beamforming matrix and the intelligent reflecting surface (IRS) phase shift matrix in a multi-user, multiple-input singleoutput (MU-MISO) system integrated with an aerial IRS. The proposed approach leverages the high mobility and flexibility of unmanned aerial vehicles (UAVs) to enhance the probability of a line-of-sight (LoS) link, thereby maximizing the sum spectral efficiency of the user equipments. Specifically, to adapt to the time-varying nature of real-world communication environments, we propose a twin delayed deep deterministic policy gradient (TD3) algorithm incorporating self-attention mechanisms for the joint optimization of beamforming and phase shift strategies. Furthermore, the batch normalization technique is employed to improve the algorithm's capability to process extensive state and action spaces, thereby accelerating convergence. Simulation results demonstrate that the proposed algorithm outperforms other mainstream deep reinforcement learning (DRL)-based baseline methods.

We introduce the hybrid ageing problem in gossip networks, where each node has different ageing processes. This generalization brings two new issues: i) the traditional subset recursion method in [1] fails; ii) the existence of stationary average age penalty needs to be re-examined. To resolve issue i) and ii), we leverage a node-by-node SHSs analysis by introducing splitting Poisson processes to evaluate the average age penalty. We first analyze the hybrid ageing problem in two types of line networks, i.e., one-way and two-way gossip lines. In one-way gossip lines, we derive the closed-form expression of average age penalty in two different cases, where the ageing process of each node can be ordered or disordered (Definition 1). The closedform expressions of average age penalty are also derived in the two-way gossip line. Moreover, we show that the growth rate of age penalty is bounded by the arrival rates between gossip nodes in the one-way line to ensure the existence of average age penalty.

The expansion of the Internet of vehicles (IoV) has spurred a significant increase in the demand for vehicular computation tasks, posing challenges for in-vehicle task processing. Multi-access edge computing (MEC), which is intended for low-latency task execution, experiences sub-band competition and workload imbalance due to the uneven distribution of vehicle densities. This paper presents a novel IoV architecture leveraging multi-roadside-unit (RSU) capabilities to facilitate efficient load balancing among RSUs through edge-to-edge collaboration. The optimization problem of computation offloading is formulated by minimizing overall task delay, which is further decoupled into two sub-problems: communication resource allocation and load balancing. We devise a two-stage deep reinforcement learning-based communication resource allocation and load balancing (DRLCL) algorithm to tackle these sub-problems sequentially. Based on real-world vehicle trajectories, experimental evaluations reveal that our proposed algorithm outperforms the baselines in reducing overall delay.

In recent years, semantic communication has received a lot of attention due to its ability to solve the challenges faced by traditional communication systems. However, little attention has been paid to the fact that during data compression and transmission, the lost data can be reconstructed by neural networks to improve transmission efficiency. In order to solve the impact of the loss of semantic information on the transmission performance in vehicular networks, this paper proposes a goal-oriented communication based on semantic reconstruction (GOCSR). By designing a semantic reconstruction network at the receiver, the lost semantic information is predicted and reconstructed, and then the complete semantic information is used to perform downstream tasks. To evaluate the efficiency of GOCSR, extensive simulation experiments are conducted using the Cityscapes dataset. Simulation results show that GOCSR can achieve higher target execution performance than the existing semantic communication schemes.

In the realm of the Internet of Things (IoT), computation offloading confronts challenges in remote areas due to scarce general-purpose edge/cloud infrastructure and insufficient terrestrial network coverage. To address this, we introduce a novel space-air-ground integrated network (SAGIN) computing architecture, designed for the efficient offloading of computationintensive applications. Within this architecture, unmanned aerial vehicles (UAVs) conduct edge computing near users, while satellites act as a bridge to cloud computing resources. Given the limitations of UAVs in terms of battery capacity and dynamic network topology, their deployment strategy is crucial for maintaining service quality. Due to the impracticality of collecting global user information for centralized control of UAVs, we have conducted research on the adaptive deployment of UAVs under the condition that they rely solely on local observations. We propose a multi-agent softmax deep double deterministic policy gradient (MASD3) algorithm and comprehensively consider maximizing the uplink transmission rate of terrestrial IoT devices and reducing the energy consumption of UAVs during flight and communication in the optimization objective. Simulation results demonstrate that our proposed solution outperforms existing state-of-the-art baselines.

Task-oriented semantic communication has gained notable interest for its capacity to minimize transmitted data volume without sacrificing task performance. Previous research has mainly concentrated on random masking, which may obscure critical features and hinder the model's ability to learn transferable representations. In this paper, a robust semantic communication system based on semantic-aware masking and discrete codebook (SAMDC) is proposed. Specifically, we develop a semantic-aware sampling strategy, which can selectively mask image patches with low semantic importance instead of random masking, to enhance the model's capacity to learn semantic information and boost training efficiency. Moreover, we also apply an improved robust discrete codebook, shared between the transmitter and receiver. This codebook comprises orthogonal and trainable basis vectors that symbolize the encoded features, thereby enhancing the system's robustness. Experimental results demonstrate that our proposed robust SAMDC significantly enhances the processing efficiency of semantic information. This improvement leads to better performance in communication tasks, particularly in challenging low signal-to-noise ratio (SNR) situations.

The performance benefits of reconfigurable intelligent surfaces (RISs) in enhancing communication capability and coverage are constrained by the static placement of the RIS. However, aerial-RIS, where the RIS is deployed on an unmanned aerial vehicle (UAV), has demonstrated superior potential to improve system performance due to the mobility and adaptability of the UAV. In this paper, we investigate a UAV-mounted RIS (UAV-RIS) relaying system and formulate an optimization problem aimed at maximizing the system sum rate. To address this, we propose a novel algorithm named DL-UTBO, that integrates deep reinforcement learning with a deep neural network (DNN) to jointly optimize the UAV trajectory, base station (BS) active beamforming, and RIS passive beamforming. The simulation results underscore the effectiveness and superiority of the proposed algorithm compared to existing baseline methods.

The integration of semantic communication technology into intelligent vehicular networks represents a promising research direction, as it significantly reduces data transmission volume and spectrum usage, addressing the high demands of transmitting large-scale visual information between vehicles. Existing studies typically assume that communicating parties share a common database. However, this assumption poses significant privacy risks, particularly in inter-vehicle scenarios. To address these challenges, we propose a federated learning-based semantic-aware communication for vehicular networks. In this approach, each intelligent vehicle locally trains a semantic communication model and uploads its model parameters to the edge server for aggregation. To further enhance data transmission efficiency, we introduce a semantic-aware vector quantized variational autoencoder (SVQ-VAE) architecture as the local semantic communication model. This architecture optimizes transmission by selectively compressing and quantizing only the most relevant semantic information for the task. Additionally, to address data heterogeneity among vehicles, we propose a hypernetwork-based personalized federated learning (HPFL) scheme. This approach enhances the model’s scalability and generalization by training a hypernetwork at the edge server to generate specific weight parameters for each vehicle’s semantic communication model. Simulation experiments on the CIFAR-10 and BDD100K datasets demonstrate that our proposed federated learning-based semantic-aware communication achieves superior task completion rates, semantic transmission efficiency and transmission delay compared to existing federated semantic communication architectures.

In recent years, semantic communication has garnered significant attention for its potential to address challenges in traditional communication systems. However, in complex communication environments, semantic communication still faces challenges such as semantic information loss, low transmission efficiency, and poor adaptability. This paper proposes a novel Semantic Communication with Adaptive Semantic Reconstruction (SCASR) scheme to enhance transmission efficiency and adaptability in complex communication environments. First, a compression mechanism based on semantic importance is designed to achieve flexible and efficient semantic compression. Then, we develop an adaptive semantic reconstruction network to predict and reconstruct lost semantic information. Finally, we integrate an attention mechanism into the reconstruction network, dynamically adjusting parameter weights based on Signal-to-Noise Ratio (SNR), Semantic Compression Rate (SCR), and Packet Loss Rate (PLR) to improve reconstruction quality and adaptability. To evaluate the efficiency of SCASR, we conduct extensive simulation experiments on semantic segmentation tasks using the Cityscapes dataset. Results demonstrate that SCASR outperforms existing semantic communication and traditional schemes, offering higher Mean Intersection over Union (mIoU), and enhanced Semantic Transmission Benefit (STB).

Recently, the combination of Transformers and convolutional neural networks (CNNs) has witnessed significant advancements in change detection (CD) tasks. However, it remains unexplored how to interactively integrate long-range dependency and local information to enhance the model’s global-local context awareness for effectively mitigating pseudo-changes. In addition, accurate identification and distinction of building changes from complex backgrounds still pose challenges due to the insufficient semantic context modeling across time between bi-temporal images. To address these issues, we propose a hybrid model ConvFormer-CD with parallel convolution and multihead self-attention (MSA). This combination enables better interaction of global and local information, thereby enhancing the adaptability to complex scenarios. Moreover, we introduce a novel module called Temporal Attention to establish cross-temporal semantic relationships between image pairs, effectively highlighting change regions by learning shared and nonshared semantics. This enables our model to accurately detect changed targets even in scenarios characterized by intricate geo-spatial arrangements and distributions. To further refine the differences in bi-temporal images, we propose a difference integration module (DIM) that connects the encoder and the decoder to fuse high-level semantic features across channels. We conduct extensive experiments on four benchmark datasets, including LEVIR-CD, LEVIR-CD+, WHU-CD, and S2Looking-CD, which demonstrates that the proposed ConvFormer-CD outperforms other state-of-the-art (SOTA) methods. Our codes will be available athttps://github.com/taomi-lab/ConvFormer-CD.

We study a class of gossip networks where a source delivers fresh status updates through networks consisting of a set of gossiping nodes. Contrary to previous works, the source delivers updates subject to an age-dependent point process where the rates are related to the age process at each node. Moreover, our work divides the age-dependent gossip networks into two types, i.e., type-A and type-B, where the former allows only one node sampling from source and the latter allows all. We first prove the necessary Markovity and ergodicity of both age-dependent gossip networks and proceed with deriving the general form of unique stationary distributions. With these premises established, closed-form expressions of the stationary age moments for type-A networks with arbitrary topologies are derived with the help of SHSs, with three specified results given for the line, ring and fully-connected networks. Meanwhile, we prove that no closed-form expressions of stationary age moments can be obtained in type-B networks. An approximated model for arbitrary-connected type-B networks is proposed, where we formulate the stationary moment equations for the approximated SHSs under the guarantee of Lagrange stability. Then, we provide a moment closure method to solve two symmetric cases, i.e., fully-connected and ring networks, approximately and verify the effectiveness of our algorithm by comparing to the simulations.

In the evolution of the Internet of vehicles (IoV), the increasing demand for vehicular computation tasks presents significant challenges, particularly in the context of constrained local computation resources and high processing delays. To mitigate these challenges, multi-access edge computing (MEC) offers a potential solution by leveraging edge servers for lowlatency processing. However, it also encounters issues such as sub-channel competition and workload imbalance owing to the uneven distribution of vehicle densities. This paper introduces a novel IoV architecture that incorporates multi-task and multi-roadside unit (RSU) capabilities, enabling edge-toedge collaboration for efficient task offloading among RSUs. The optimization problem is formulated with the objective of minimizing the overall task delay, which is further divided into two sub-problems: communication resource allocation and load balancing. Considering the non-deterministic polynomial (NP)- hard nature of these sub-problems, we propose a two-stage deep reinforcement learning-based communication resource allocation and load balancing (DRLCL) algorithm to address them sequentially. Based on realistic vehicle trajectories, comprehensive evaluation results demonstrate the superiority of the proposed algorithm in reducing system delay compared to existing stateof-the-art baselines, offering an effective approach for optimizing the performance of vehicular edge computing (VEC) networks.

In urban environments, direct communication links between a base station (BS) and user equipment (UEs) are often obstructed by buildings. To mitigate these blockages, we integrate unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) to enhance system flexibility and improve transmission efficiency. This paper investigates an RIS-assisted multi-user multiple-input single-output (MU-MISO) downlink system, where the RIS is mounted on a UAV. To maximize the system rate while minimizing the UAV's energy consumption and flight duration, we formulate a multi-objective optimization problem. To address this problem, we propose a hybrid algorithm that integrates the soft deep deterministic policy gradient (SD3) algorithm with a graph neural network (GNN) architecture, named SD3-GNN-RIS. The original problem is decomposed into two subproblems: joint active beamforming at the BS and passive beamforming at the RIS, optimized via a GNN-based approach, and three-dimensional (3D) UAV trajectory optimization, formulated as a Markov decision process and solved using the SD3 algorithm. Simulation results demonstrate the superior performance of the proposed algorithm compared to baseline methods in terms of system rate, energy efficiency, and UAV trajectory optimization.

Analyzing student actions is an important and challenging task in educational research. Existing efforts have been hampered by the lack of accessible datasets to capture the nuanced action dynamics in classrooms. In this paper, we present a new multi-labelStudent Action Video(SAV) dataset, specifically designed for action detection in classroom settings. The SAV dataset consists of 4,324 carefully trimmed video clips from 758 different classrooms, annotated with 15 distinct student actions. Compared to existing action detection datasets, the SAV dataset stands out by providing a wide range of real classroom scenarios, high-quality video data, and unique challenges, including subtle movement differences, dense object engagement, significant scale differences, varied shooting angles, and visual occlusion. These complexities introduce new opportunities and challenges to advance action detection methods. To benchmark this, we propose a novel baseline method based on a visual transformer, designed to enhance attention to key local details within small and dense object regions. Our method demonstrates excellent performance with a mean Average Precision (mAP) of 67.9% and 27.4% on the SAV and AVA datasets, respectively. This paper not only provides the dataset but also calls for further research into AI-driven educational tools that may transform teaching methodologies and learning outcomes. The code and dataset are released athttps://github.com/Ritatanz/SAV.

This paper presents an intelligent reflecting surface (IRS)-assisted data harvesting scheme for unmanned aerial vehicle (UAV) networks. This scheme leverages the high maneuverability of the UAV and the channel gain enhancement from the IRS. By jointly optimizing the UAV trajectory and the IRS phase shift, we aim to minimize the completion time of data harvesting missions. Specifically, we devise a softmax operator applicable to deterministic policy gradients and propose a softmax deep double deterministic policy gradients (SD3) method to facilitate the design of three-dimensional trajectory for UAV. In addition, we propose a practical coherent combining (CC) strategy for IRS phase control. Simulation results demonstrate that the proposed SD3-CC algorithm surpasses other mainstream baseline methods relying on deep reinforcement learning (DRL).

The fusion of hyperspectral images (HSIs) and LiDAR data can improve land cover classification performance. However, existing fusion methods do not well consider the large discrepancies between two modalities (e.g., brightness, structure, and the possible misalignment), leading to limited improvement. In this paper, we handle this problem in frequency domain and propose a cross-modal hierarchical frequency fusion network (HFNet) for joint classification of HSI and LiDAR data. First, we extract multi-level convolutional features from both modalities. Then, we explore spatial activation maps to adaptively fuse cross-modal frequency features at each level. Since the amplitude and phase information of two modalities are separately fused, the discrepancy problem is alleviated. Finally, we concatenate the fused features at all levels to build a classification loss and an auxiliary frequency consistency loss (FCL). FCL enables the concatenated feature to predict the amplitude and phase information of the input data, which acts as a regularization term and improves the model’s discrimination ability. Experimental results on two datasets show the superiority of HFNet over the state-of-the-art methods in terms of classification performance.

We study a class of gossip networks where a single source delivers fresh status updates through networks consisting of a set of gossiping nodes. Contrary to previous works, the source delivers updates to nodes subject to an age-dependent point process where the update rates are related to the age process at each node. We derive the closed-form expressions of stationary age moments for the disconnected networks, and demonstrate the general procedure of moment analysis in the age-dependent gossip networks based on stochastic hybrid systems (SHSs). Considering the analytical difficulties in solving the infinite-dimensional stationary moment equations in more complex topologies, we provide two numerical methods to solve for the numerical values of stationary age moments approximately, and verify the effectiveness of these methods on the first three age moments in ring networks.

Unmanned aerial vehicles (UAVs) assisted mobile edge computing (MEC) systems are considered a promising solution, especially in disaster scenarios. Furthermore, recon-figurable intelligent surfaces (RISs) have emerged as a novel technology aimed at enhancing the wireless propagation environment in wireless networks. This paper proposes a multi-UAV assisted MEC system with partial task offloading, leveraging RIS to augment the communication performance between ground terminals (GTs) and UAVs. The pre-set hovering positions for the UAVs are determined by clustering the GTs using the K- means algorithm. To minimize system delay and ensure fairness among GTs, the computation offloading strategy and phase-shift of the RIS are optimized using the multi-agent deep deterministic policy gradient (MADDPG) algorithm, a form of multi-agent deep reinforcement learning. Simulation results demonstrate that the proposed cluster-aided RIS-MADDPG algorithm significantly enhances the system delay and fairness performance of the RIS-assisted multi-UAV MEC system when compared to benchmark solutions.

With the development of intelligent transportation systems (ITS), edge cooperative caching (ECC) technology has been introduced into vehicular ad hoc networks (VANETs) to reduce the transmission delay of vehicle access data and improve network performance. ECC technology achieves faster and more efficient data retrieval by storing frequently accessed data at the network edge, especially for popular or time-sensitive content in VANETs. However, due to the limited caching resources, allocating storage resources for caching and deciding which data to cache becomes a challenge. This paper first proposes a vehicle-edge network model, and then based on this network model, proposes an optimization problem that minimizes the average transmission delay. To solve this optimization problem, we propose a centralized edge cooperative caching (CECC) strategy, which converts it into a multiple-choice knapsack (M CK) problem. Finally, we propose a greedy algorithm to obtain an approximate optimal solution to the MCK problem. Simulation results show that compared with existing ECC strategies, the CECC strategy can effectively improve caching performance.

Unmanned aerial vehicles (UAVs) are regarded as a promising solution for mobile edge computing (MEC) systems due to their flexibility and capability to provide computing services to ground terminals (GTs). By leveraging UAVs, the latency in computation tasks can be reduced significantly, particularly in disaster scenarios. Additionally, Reconfigurable Intelligent Surfaces (RIS) have emerged as a novel technology for enhancing the wireless propagation environment in wireless networks. This paper proposes a multi-UAV assisted MEC system where computation tasks of GTs can be computed locally or partially offloaded to UAVs. Furthermore, practical RIS phase shift designs are considered to enhance the communication performance between GTs and UAVs. To minimize the system delay and achieve fairness among GTs, the computation offloading strategy, trajectory of the UAVs are optimized using a markov decision process. Simultaneously, the RIS phase shift is optimized through an alternating optimization algorithm. Additionally, a cooperative multi-agent deep reinforcement learning framework is developed to obtain a optimal solution by employing the multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm. Numerical results indicate that MATD3 can effectively improve the system delay and fairness performance of the RIS-assisted multi-UAV MEC system, as compared to benchmark solutions.

Deep learning has been extensively applied to hyperspectral image (HSI) classification and has achieved significant success. However, the number of labeled samples available for HSI classification tasks is typically limited in practical applications, which makes the high-accuracy of HSI small-sample classification still a challenging research task. Therefore, metric-based prototypical networks for few-shot learning (FSL) have become increasingly popular. However, the majority of existing FSL methods typically have problems with biased prototypes and domain shifts. To address these issues, this article proposed a prototype rectification network framework for cross-domain few-shot HSI classification. Specifically, to obtain more representative prototypes, we designed a query-guided prototype rectification module, which can rectify the feature distribution of the support set prototype and obtain a more representative prototype for subsequent training tasks. Then, we introduced a prototype-based interclass loss function to alleviate the interclass confusion that may result from prototype rectification. Furthermore, we construct an intermediate domain between the source domain and the target domain to alleviate domain shift, which helps mitigate the difficulties of domain transfer and achieve a more comprehensive domain alignment. The experimental results on four publicly available HSI datasets demonstrate that our proposed method outperforms the existing FSL methods.

Multilabel remote sensing (RS) image classification aims to predict multiple semantic labels from an RS image. Previous methods [e.g., graph convolution networks (GCNs)] focus on mining the relationships of multiple labels, neglecting that the scene information is closely related to labels. To remedy this deficiency, in this article we propose a novel end-to-end deep neural network for multilabel RS image classification. In the proposed network, we use the GCN as the base model and introduce several new components to improve the classification performance. First, we explore hybrid contrastive learning (CL), including supervised transformation-based CL and unsupervised mix-based CL, to explicitly learn discriminative scene representations. Then, we apply the GCN-based classifier to the learned scene representations to obtain initial label prediction scores. Meanwhile, we pass the scene representations to a softmax layer to predict the probability that each image belongs to each specific scene class and use the scene-to-label information with the law of total probability to calibrate the initial label prediction scores. Finally, we incorporate CL, scene classification, and multilabel classification into a unified learning framework using uncertainty to weigh different losses. Experimental results on two benchmark RS datasets demonstrate the superiority of our proposed network for multilabel image classification.

Hyperspectral image (HSI) and LiDAR data are complementary to each other, which can be combined to improve the classification performance. However, existing deep network models do not sufficiently consider their complementarity to design the network structure and loss functions. Moreover, there lacks a hierarchical mutual-assistance learning mechanism that leverages the modality-shared features to enhance the modality-specific ones and vice versa. In view of these, we propose a novel height information guided hierarchical fusion-and-separation network (HFSNet) for joint classification of HSI and LiDAR data. HFSNet consists of three major components, i.e., dual-structure feature encoders (DSFEs), feature fusion-and-separation blocks (F2SBs), and an edge decoder (ED). Specifically, the transformer and convolutional neural network are introduced in DSFEs to encode the spectral and spatial information of HSI and LiDAR data, respectively. In F2SBs, the deformable convolution-based height information guided fusion module and the modality separation refinement module are proposed to sequentially extract modality-shared and modality-specific features. Additionally, the ED is incorporated into our model to predict the LiDAR edge map from the HSI feature to improve the model’s generalization ability. As such, the learned features from HSI and LiDAR data are deeply fused and mutually enhanced. Experiments on three benchmark datasets show the superiority of HFSNet to the state-of-the-art methods for jointly classifying HSI and LiDAR data with limited training samples.

Change detection aims to detect changes of objects or scenes in remote sensing images, which is critical for observing the Earth’s surface. However, due to the insufficient correlation and aggregation of bitemporal features, the existing deep learning methods are still impacted by varied imaging conditions and complicated boundaries of ground objects in high-resolution remote sensing images. To tackle these challenges, we propose a change-aware cascaded dual-decoder network (CACD2Net), which integrates bitemporal features at different levels to facilitate learning change maps from coarse to fine, thus empowering the network to effectively identify changes and refine pixelwise boundaries in a progressive manner. Within the cascaded dual-decoder architecture, the change location decoder utilizes high-level features to generate a coarse change map, which approximates changes’ localization, while the mask refinement decoder further leverages low-level features to create a texture-aware map that captures more texture and structural information about the change regions. By using the coarse change map as guidance and directing the texture-aware map to focus on the details of changes, the boundaries can be gradually refined, ultimately resulting in an accurate change detection mask. We test our model on the season-varying change detection (SVCD) dataset and the Sun Yat-sen University change detection (SYSU-CD) dataset, and the experimental results show that our model surpasses other state-of-the-art change detection methods. Our codes will be available athttps://github.com/Moonquakes0/CACD2Net.

Edge caching has emerged as an effective solution to the challenges posed by massive content delivery in the vehicular network. In vehicular networks, vehicles and roadside units (RSUs) can serve as intermediate relays with caching capabilities. However, due to the mobility of vehicles, the topology of the edge network changes frequently, which leads to frequent link interruptions and increases the transmission delay. This paper proposes an adaptive cooperative caching (ACC) strategy to adapt the frequent changes in the vehicular edge network topology and describes an optimization problem to minimize the average transmission delay. Then, the optimization problem is transformed into two sub-optimization problems: multiplechoice knapsack (MCK) problem and multiple minimum-weight dominating set (MMWDS) problem. Finally, two greedy algorithms with low complexity are designed to solve the above two optimization problems and obtain approximate solutions to the optimal caching decision. Simulation results show that ACC can effectively improve the cache hit rate and reduce the average transmission delay and the communication overhead compared with other caching strategies.

The collaboration between unmanned aerial vehicles (UAVs) and intelligent reflecting surfaces (IRSs) presents an innovative approach for delay-tolerant data harvesting in distributed Internet of Things (IoT) networks. However, existing research mostly overlooks the dynamic changes in communication links caused by the real-time UAV movement and the realistic geographical features. In this paper, we address these challenges by considering a practical three-dimensional (3D) urban scenario with a centralized IRS. Our aim is to minimize the completion time of data harvesting missions by jointly optimizing the 3D trajectory of the UAV and the phase shift of the IRS. Specifically, the formulated problem is decoupled into two subproblems. First, for the 3D continuous trajectory design, we propose a robust memory-based softmax deep double deterministic policy gradients (MSD3) approach, which enables the UAV to adaptively collect delay-tolerant data from randomly distributed ground devices starting from any arbitrary point. Second, we present a comprehensive theoretical analysis for the continuous IRS phase control, which provides a practical and intuitive numerical solution. Simulation results demonstrate that the proposed MSD3-IRS algorithm outperforms other mainstream baselines based on deep reinforcement learning.

Federated learning (FL) is an emerging machine learning setting designed to preserve privacy. However, constantly updating model parameters on uplink channels results in huge communication overload, which is a major challenge for FL. In this paper, we consider an adaptive gradient quantization approach based on rate-distortion optimization in FL, which consists of a non-stationary random walk model on the true global optimal model parameters. Unlike traditional quantization methods, our goal is to minimize the total communication costs when the global server reconstructs model parameters under distortion constraints. Furthermore, when considering the iterative process, we utilize the Kalman filter to reduce computational complexity. And in each iteration, a generalized water-filling algorithm is used to calculate the optimal quantization levels for each local client. Numerical results show that the proposed method outperforms conventional quantization methods in terms of reducing communication costs.

Remote sensing (RS) object detectors based on convolutional neural networks (CNNs) are hard to model global context dependencies. Transformer-based detectors can overcome this problem via global pairwise interactions, but more comprehensive information interactions are not systemically investigated to boost the detection performance. In view of this issue, we propose a transformer-guided multi-interaction network (TransMIN), which uses ResNet50-feature pyramid network (FPN) as the backbone for remote sensing object detection (RSOD). Specifically, we implement local–global feature interactions (LGFIs) by combining convolution and transformer in the residual blocks of ResNet50 to learn complementary features. We implement cross-view feature interactions (CVFIs) via transformers in the pyramid layers of FPN to capture the correlation between reference features (spatial edge priors and channel statistics) and pyramid features. This enhances edge information and suppresses background interference. In the detection head, we adopt a task-interactive sample assigner (TISA) by considering the interactions of classification and localization losses to obtain high-quality predictions. Experiments on two benchmark datasets demonstrate the superior detection performance of TransMIN over state-of-the-art methods.

This paper considers a new extremal inequality and proves that a Gaussian distribution is one of the solutions to hold this extremal inequality. The method of factorization is applied in the proof. We also exploit the chain rule in two separate ways to establish the subadditivity of factorization. As an application, the converse part of the rate-distortion problem of the quadratic Gaussian Gray-Wyner system with single-letter characterization is solved using this new extremal entropy inequality.

With the development of Internet of Things (IoT), wireless communication networks and Artificial Intelligence (AI), more and more real-time applications such as online games and autonomous driving have emerged. However, due to limited computing power and battery capacity, it has become increasingly difficult for local user devices to take on the full range of computing tasks under tight timing constraints. The emerging Mobile Edge Computing (MEC) technology is widely considered to be an important technology for achieving ultra-low latency. However, most of the existing work is focused on non-splittable computation tasks. In fact, data partitioning-oriented applications can be split into multiple subtasks for parallel processing. In this paper, we study the partial computation offloading of multiple detachable tasks in MEC networks, focusing on minimizing the total user device latency in the multi-MEC multi-user scenarios. Considering the dynamic partitioning of tasks, we adopt the barrel theory to construct a linear system of equations to find the optimal solutions and propose an approach for distributed computation offloading based on numerical methods. The simulation results show that the proposed algorithm can reduce the average user device latency by 31 % compared with the binary offloading method.

Deep convolutional neural networks (CNNs) have made great progress in remote sensing (RS) image scene classification. However, by visualizing the learned feature maps, we find that the popular CNN of ResNet can capture incomplete and inaccurate semantic information for classifying scene images with complex spatial distributions and varying object scales. In this letter, we propose a multilayer and multiattention fusion network (M2FN) to alleviate this issue. Specifically, we first introduce a multilayer adaptive feature fusion (MLAFF) module to model the information interaction between different layers and enhance the network’s multiscale representation ability. Then, we design a multidimensional attention (MA) module to weight the multilayer fused features by comprehensively considering their interdependencies between all possible dimensions. The proposed MA module extends the traditional spatial and channel attentions to a more comprehensive one. Experiments on two benchmark data sets demonstrate the superiority of M2FN for RS scene classification over many state-of-the-art methods.

Recurrent neural networks (RNNs) have been widely used for hyperspectral image (HSI) classification via sequence modeling. However, most of the RNN methods focus on modeling long-range dependencies along the spectral direction, without fully exploring multi-directional dependencies in the joint spectral-spatial domain. To tackle this issue, we propose MSLAN, a two-branch multi-directional spectral-spatial long short-term memory (LSTM) attention network, for HSI classification. In particular, we employ LSTMs to extract six-directional spatial-spectral features which simultaneously capture the spectral-spatial dependencies along different directions. We then design an attention-based feature fuse module to integrate these directional features, followed by a fully connected layer with cross-entropy loss for classification. Additionally, we incorporate an auxiliary branch into our model to enhance the generalization capability. In this branch, random spatial shuffle and a cosine loss are explored for feature consistency learning by taking into account the varying spatial distributions. The resulting two branch networks, sharing the same network structure and weights, are incorporated into a unified deep learning architecture for training. Experiments show the superiority of MSLAN to the state-of-the-art methods for HSI classification with limited training samples.

Spectrum map is an essential tool for a range of emerging applications of 5G and 6G networks. Despite the great efforts that have been put on the construction of spectrum maps, access to accurate and valid spectrum data in dynamically changing environments emphasizes the need for more advanced solutions tailored to such rapidly varying scenarios. To this end, the idea of spectrum map prediction is introduced. In this paper, we address the problem of spectrum map prediction from historical spectrum observations in the dynamically changing environments. The problem is particularly challenging when the available historical spectrum observations are incomplete and corrupted by anomalies. We propose three techniques to solve the problem. First, we combine the spectrum map with prediction functionalities so as to offer a huge potential for efficient resource management and flexible sharing of resources in dynamically changing environments. Second, by fully exploiting the hidden spatial-temporal-spectral structures of the spectrum data and the sparsity of anomalies and missing data, we model the spectrum map as a 3rd-order spectrum tensor and formulate the spectrum map prediction problem as a low-rank tensor completion problem. Third, we design a robust online spectrum map prediction (ROSMP) algorithm based on the alternating direction minimization method, which derives the tensor decomposition factors for a new timeslot based on the update of existing ones rather than re-computing from the scratch. By gradually learning the hidden spatial-temporal-spectral structures of the spectrum data, ROSMP is able to predict and obtain the complete spectrum map with high accuracy. Finally, extensive numerical evaluations using a real spectrum measurement dataset confirm the efficacy and efficiency of ROSMP and show the superiority of ROSMP over the baselines.

Abstract In an interweave cognitive radio system, cooperative spectrum sensing has been recognised as a key technology to enable secondary users to opportunistically access licensed spectrum band without harmful interference to primary users. At the same time, the unmanned aerial vehicle equipped with spectrum sensing and data transmission facilities is gaining more popularity in different applications. An unmanned aerial vehicle‐based interweave cognitive radio is investigated in which the unmanned aerial vehicle is used as a secondary user, but unlike the participation of multiple secondary users in traditional cooperative spectrum sensing, a virtual cooperative spectrum sensing model is introduced into the periodic spectrum sensing frame structure. Afterwards, the authors further propose an energy‐efficient virtual cooperative spectrum sensing with the sequential 0/1 fusion rule to reduce the average number of decisions without any loss in the detection performance. Sequentially, the authors formulate the optimisation of virtual cooperative spectrum sensing for unmanned aerial vehicle‐based interweave cognitive ratio system as the optimal sequential 0/1 fusion problem on the basis of the K ‐out‐of‐ N fusion rule and prove the formulated problem indeed has one optimal K , which yields the highest throughput. Finally, numerical simulations are presented to demonstrate the correctness of theoretical analyses and the effectiveness of the virtual cooperative spectrum sensing with the sequential 0/1 fusion rule.

Due to the existence of noise and spectral redundancies in hyperspectral images (HSIs), the band selection (BS) is highly required and can be achieved through the attention mechanism. However, existing BS methods fail to consider global interaction between the spectral information and spatial information in a nonlinear fashion. In this letter, we propose an end-to-end unsupervised dual-attention reconstruction network for BS (DARecNet-BS). The proposed network employs a dual-attention mechanism, i.e., position attention module (PAM) and channel attention module (CAM), to recalibrate the feature maps and subsequently uses a 3-D reconstruction network to restore the original HSI. This way, the long-range nonlinear contextual information in spectral and spatial directions is captured, and the informative band subset can be selected. Experiments are conducted on three well-known hyperspectral data sets, i.e., Indian Pines (IP), University of Pavia (UP), and Salinas (SA), to compare existing BS approaches, and the proposedDARecNet-BScan effectively select less redundant bands with comparable or better classification accuracy. The source code will be made publicly available athttps://github.com/ucalyptus/DARecNet-BS.

Local binary pattern (LBP) and its many variants have shown effectiveness for texture classification. However, most of these LBP methods focus on encoding local intensity differences between a central pixel and its neighboring sampling points and consequently have two major problems: 1) they are unable to describe the intensity order relationships among neighboring sampling points, and 2) they fail to capture long-range pixel interactions that take place outside a compact neighborhood. In view of these problems, in this paper we propose two novel operators, called local grouped order pattern (LGOP) and non-local binary pattern (NLBP), for texture description. For the first problem, LGOP groups the neighboring sampling points by referring to a dominant direction and encodes the groupwise intensity order relationships. For the second problem, NLBP computes several anchors based on global image statistics and progressively encodes non-local intensity differences between the neighboring sampling points and anchors. Finally, we combine LGOP and NLBP via central pixel encoding to construct discriminative histogram features as texture descriptor LGONBP. Experiments on four texture benchmark databases (i.e., Outex, CUReT, UMD and KTH-TIPS) demonstrate the superiority of LGONBP over state-of-the-art LBP variants for texture classification under both noise-free and noisy conditions. The code is available athttps://github.com/stc-cqupt/LGONBP.

Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands. Due to the existence of noise and band correlation, the selection of informative spectral-spatial kernel features poses a challenge. This is often addressed by using convolutional neural networks (CNNs) with receptive field (RF) having fixed sizes. However, these solutions cannot enable neurons to effectively adjust RF sizes and cross-channel dependencies when forward and backward propagations are used to optimize the network. In this article, we present an attention-based adaptive spectral-spatial kernel improved residual network (A2S2K-ResNet) with spectral attention to capture discriminative spectral-spatial features for HSI classification in an end-to-end training fashion. In particular, the proposed network learns selective 3-D convolutional kernels to jointly extract spectral-spatial features using improved 3-D ResBlocks and adopts an efficient feature recalibration (EFR) mechanism to boost the classification performance. Extensive experiments are performed on three well-known hyperspectral data sets, i.e., IP, KSC, and UP, and the proposed A2S2K-ResNet can provide better classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa compared with the existing methods investigated. The source code will be made available at https://github.com/suvojit- 0×55aa/A2S2K-ResNet.

Electric Vehicle (EV) public charging is important to meet the exploding charging demand and to address the range anxiety issue. In this paper, we focus on the EV public charging market with heterogeneous charging stations (CSs) under the time-based billing model. We jointly consider the charging time optimization for EVs, the EV-CS pairing, and the pricing mechanism for CSs. A hierarchical game, which mathematically corresponds to an equilibrium problem with equilibrium constraints (EPEC), is then developed to formulate the three coupled problems. In the proposed hierarchical game, each CS sets the charging price to maximize its own revenue first, then the EVs choose their desired CSs and determine the charging time. We analyze the optimal charging time strategies for EVs, and a many-to-one matching algorithm is applied to solve the EV-CS pairing problem. Besides, a block coordinate descent (BCD) based algorithm is applied for each CS to solve the pricing problem. Simulation results show that our proposed schemes can achieve the performance improvement of the charging system.

Vehicular communication is an important application of the fifth generation of mobile communication systems (5G). Due to its low cost and energy efficiency, intelligent reflecting surface (IRS) has been envisioned as a promising technique that can enhance the coverage performance significantly by passive beamforming. In this paper, we analyze the outage probability performance in IRS-assisted vehicular communication networks. We derive the expression of outage probability by utilizing series expansion and central limit theorem. Numerical results show that the IRS can significantly reduce the outage probability for vehicles in its vicinity. The outage probability is closely related to the vehicle density and the number of IRS elements, and better performance is achieved with more reflecting elements.

Local binary pattern (LBP) based descriptors have shown effectiveness for texture classification. However, most of them encode the intensity relationships between neighboring pixels and a central pixel into binary forms, thereby failing to capture the complete ordering information among neighbors. Several methods have explored intensity order information for feature description, but they do not address the grayscale-inversion problem. In this paper, we propose an image descriptor called local grouped invariant order pattern (LGIOP) for grayscale-inversion and rotation invariant texture classification. Our LGIOP is a histogram representation which jointly encodes neighboring order information and central pixels. In particular, two new order encoding methods, i.e., intensity order encoding and distance order encoding, are proposed to describe the neighboring relationships. These two order encoding methods are not only complementary but also invariant to grayscale-inversion and rotation changes. Experiments for texture classification demonstrate that the proposed LGIOP descriptor is robust to (linear or nonlinear) grayscale inversion and image rotation.

Local binary pattern (LBP), as one of the most representative texture operators, has attracted much attention in computer vision and pattern recognition. Many LBP variants were developed in the literature. However, most of them were designed for gray images and their performance remains to be improved for color images. In this paper, we propose a novel color image descriptor named Holistic and Hierarchical Order-Encoding Patterns (H2OEP) for texture classification. In H2OEP, the holistic order-encoding pattern compactly encodes color order variation tendencies for each pixel in color space. The hierarchical order-encoding pattern leverages min ordering, median ordering and max ordering to encode local neighboring relationships across different color channels. Finally, the generated order-encoding patterns are aggregated via central pixel encoding to build 3D joint histograms for image representation. Experiments on four benchmark texture databases demonstrate the effectiveness of the proposed descriptor for color texture classification.

Local binary pattern (LBP) is sensitive to inverse grayscale changes. Several methods address this problem by mapping each LBP code and its complement to the minimum one. However, without distinguishing LBP codes and their complements, these methods show limited discriminative power. In this paper, we introduce a histogram sorting method to preserve the distribution information of LBP codes and their complements. Based on this method, we propose first- and second-order sorted LBP (SLBP) features which are robust to inverse grayscale changes and image rotation. The proposed method focuses on encoding difference-sign information and it can be generalized to embed other difference-magnitude features to obtain complementary representations. Experiments demonstrate the effectiveness of our method for texture classification under (linear or nonlinear) grayscale-inversion and rotation changes.

Mobile edge caching (MEC), content delivery network (CDN) and data center (DC) serve Internet content providers (ICPs) with different advantages and disadvantages. In this paper, we propose an equilibrium problem with equilibrium constraints (EPEC) to investigate the delivery strategies for files and pricing mechanisms for MEC, CDN, and DC. At the upper level, MEC and CDN predict the files' rational delivery strategies and set the delivery price for each byte to provide the content delivery service. DC serves as origin servers to provide free content delivery service. At the lower level, the files observe the price strategy and determine their delivery strategies. In the proposed EPEC problem, there exist Nash equilibriums, which are coupled with each other, at both the upper level and lower level. We adopt a block coordinate descent (BCD) method to find the equilibrium solutions at both the upper level and lower level. Simulation results show that our proposed approach yields high utilities at the equilibrium.

Cooperative spectrum sensing (CSS) by exploiting diversity via the observations of spatially located secondary users improves the accuracy of the primary user (PU) detection, but cooperative paradigms are threatened by Byzantine attack. In this study, the authors propose a flexible Byzantine attack model, which goes beyond the existing models for its generalisation. Under this generalised Byzantine attack model, they give insights into the blind scenario where Byzantines make the fusion centre (FC) incapable of deciding the presence of the PU. To solve the blind problem, they formulate data transmission revelation (DTR) as trust reputation management to check consistency of the local decision. Moreover, they evaluate the usability of Byzantine data based on DTR and propose a sequential detection (SD) approach to reuse Byzantine data, which is a remarkable issue involved in CSS, however, ignored by most previous studies. Simulation results clearly reveal that in contrast to other approaches associated with sequential probability ratio test, the proposed SD benefits from Byzantine data to greatly improve the correct sensing ratio and the sample size, and still functions well in the blind scenario.

Cooperative spectrum sensing is a key technology of cognitive radio networks (CRNs) to the reliability of spectrum sensing but is prone to be affected by a series of user characteristics, which results in a serious decline in the throughput of CRNs and the harmful interference to the primary user network. The performance analysis and optimisation of existing cooperative spectrum‐sensing schemes do not completely cover key user characteristics. In this study, the joint effects of key user characteristics are studied with the objective to determine the parameters that affect the cooperative spectrum‐sensing functionality. To this aim, the mobile CRN model and spatial–temporal spectrum‐sensing model are formulated. Furthermore, the authors propose a dynamic double threshold energy detection (DDTED) scheme to derive the miss‐detection probability and false alarm probability involving user characteristics. Moreover, the performance optimisation is carried out by a dynamic threshold factor. Finally, simulation results show that a variety of user characteristics have different effects on the performance of cooperative spectrum sensing, and the proposed DDTED scheme can achieve better performance than the existing approach.

Most of the local binary pattern (LBP) variants improve LBP by simply concatenating multi-scale LBP histograms or by encoding complementary components in one single image domain, thereby ignoring the correlation information between different scales and image domains. In this paper, we propose a novel LBP-based texture representation by exploring local binary encoding across scales, frequency bands and image domains. Specifically, given a texture image, the multi-scale low- and high-frequency images are obtained by Gaussian filtering and image subtraction. Meanwhile, the multi-scale gradient images are computed based on Gaussian derivative filtering. Then, the LBP code maps are extracted from the low-frequency, high-frequency and gradient images. Finally, the joint LBP encoding across scales, frequency bands and image domains is explored to construct histogram features for texture representation. Experimental results for texture classification demonstrate the superiority of our method over the state-of-the-art LBP variants under both noise-free and noisy conditions.

Cognitive radio enabled vehicular ad‐hoc networks (CR‐VANETs) are one of the promising architectures in the future vehicular ad‐hoc networks. In this study, the joint spatial–temporal correlation is exploited to improve decision accuracy of cooperative spectrum sensing (CSS) while reducing overhead introduced by cooperation in the CR‐VANETs. Firstly, a theoretical method is presented to analyse the impact of spatial–temporal correlation on cooperative sensing performance when using soft combining in the CR‐VANET. Then, the expression of the optimal probability of detection with respect to spatial–temporal correlation is given for a target probability of false alarm by employing likelihood ratio test. Additionally, the user selection problem is formulated as an efficient double‐threshold optimisation problem by considering both sensing accuracy and stability to achieve the optimal probability of detection. Finally, a hybrid CSS scheme based on spatial–temporal correlation is designed for the CR‐VANET. Simulation results reveal that the proposed scheme could achieve significant sensing performance gain by selecting a subset of secondary users for combination, and could reduce user selection frequency by employing spatial–temporal diversity.

The Internet of Things (IoT) has attracted significant attentions in the fifth generation mobile networks and the smart cities. However, considering the large numbers of connectivity demands, it is vital to improve the spectrum efficiency (SE) of the IoT with an affordable power consumption. To improve the SE, the nonorthogonal multiple access (NOMA) technology is newly proposed through accommodating multiple users in the same spectrums. As a result, in this paper, an energy efficient resource allocation (RA) problem is introduced for the NOMA-based heterogeneous IoT. At first, we assume the successive interference cancellation (SIC) is imperfect for practical implementations. Then, based on the analyzing method for cognitive radio networks, we present a stepwise RA scheme for the mobile users and the IoT users with the mutual interference management. Third, we propose a deep recurrent neural network-based algorithm to solve the problem optimally and rapidly. Moreover, a priorities and rate demands-based user scheduling method is supplemented, to coordinate the access of the heterogeneous users with the limited radio resource. At last, the simulation results verify that the deep learning-based scheme is able to provide optimal RA results for the NOMA heterogeneous IoT with fast convergence and low computational complexity. Compared with the conventional orthogonal frequency division multiple access system, the NOMA system with imperfect SIC yields better performance on the SE and the scale of connectivity, at the cost of high power consumption and low energy efficiency.

Device-to-device (D2D) communication is one of the key technologies for the collaborative heterogeneous networks towards the fifth generation (5G) ecosystem. Among D2D techniques, D2D-relay, which combines the advantages of both D2D and relay technology, is a promising tool to enhance performance of communication systems. In this paper, we propose a stable and proportional fair user pairing algorithm for D2D-relay systems. The proposed algorithm adopts the concept in symmetric pairing theory, which is verified to be absolutely stable. Moreover, we also proved that the proposed algorithm is Pareto optimal in system performance. Numerical results demonstrate that the proposed algorithm distinctly outperforms the traditional user pairing methods in both energy efficiency (EE) and proportional fairness (PF) aspects, while maintaining a comparable throughput performance with traditional pairing methods, which is attractive for practical applications.

In this paper we address the task of infrared and visible image registration in complex scenes. Due to the difference of infrared and visible images, it is neither easy to reliably find features nor suitable for directly training in deep learning architecture. Thus, we propose a two-stage adversarial network, which first conducts a multi-spectral image transfer to obtain a mapped image. And then the proposed network incorporate a transformer module into the conditional adversarial network architecture to get the refined warped image. Our method can back propagate the multi-spectral registration loss and achieve end-to-end training. Experiments on our multi -spectral dataset demonstrate that this approach is effective and robust, which outperforms other state-of-the-art methods.

The original Local Binary Pattern (LBP) has limited discriminative power and is sensitive to noise. In view of this., this paper proposes a novel image descriptor called Multi-Scale Cross-Band Encoding of Sectored Local Binary Pattern (MCE-SLBP) for robust texture classification. First., the pyramid decomposition is explored to obtain multi-scale low-frequency and high-frequency (difference) images. To encode more discriminative features., these high-frequency images are further decomposed into positive and negative high-frequency images via the polarity splitting. Then., a robust Sectored Local Binary Pattern (SLBP) is proposed to compute texture feature codes on the decomposed images via cross-band joint coding. Finally., a multi-scale histogram representation is obtained by concatenating histograms of texture codes computed at all decomposition levels. Experiments on three benchmark texture databases (i.e.., Outex., Brodatz and CUReT) demonstrate that the proposed method achieves the state-of-the-art classification accuracies both under noise-free conditions and in the presence of different levels of Gaussian noise.

Local binary pattern (LBP) and its variants (e.g., LTP and CLBP) are powerful descriptors for texture analysis. However, most of these LBP-based methods are sensitive to inverse grayscale changes. To overcome this problem, we present a novel texture descriptor named Completed Grayscale-Inversion and Rotation Invariant Local Binary Pattern (CGRI-LBP). CGRI-LBP is based on the framework of CLBP which jointly encodes three components (i.e., the signs and magnitudes of local differences as well as central pixels) but with two significant improvements: 1) the sign information of local differences is encoded by a rotation-invariant complementary coding scheme, and 2) the intensity information of central pixels is encoded via a dominant intensity order measure. Extensive experiments on three texture databases (Outex, CUReT and KTH-TIPS) demonstrate that the proposed descriptor achieves the state-of-the-art classification performance in the presence of linear and even nonlinear grayscale-inversion changes.

In this paper, an energy efficient resource allocation (RA) problem is introduced for a NOMA based heterogeneous IoT. Particularly, the successive interference cancelation (SIC) is assumed imperfect for implementations. Accordingly, a stepwise scheme is presented with the mutual interference management. Specifically, a deep learning based algorithm is proposed to solve the problem optimally and rapidly. The simulation results verify that the proposed RA scheme provides the optimal results for the NOMA based heterogeneous IoT with fast convergence and low computational complexity. Compared with the OFDMA scheme, the NOMA based scheme yields better performance on the spectrum efficiency (SE) and the scale of connectivity, at the cost of high power consumption and low energy efficiency (EE).

Cognitive radio enabled vehicular ad hoc networks (CR- VANETs) is one of the promising architecture in the future VANETs. In this paper, the joint spatial- temporal correlation is exploited to improve decision accuracy of cooperative spectrum sensing while reducing overhead introduced by cooperation in the CR-VANET. Firstly, a theoretical method is presented to analyze the impact of spatial-temporal correlation on cooperative sensing performance when using soft combining in the CR-VANET. Then, the expression of the optimal probability of detection with respect to spatial-temporal correlation is given for a target probability of false alarm by employing likelihood ratio test. Additionally, the user selection problem is formulated as an efficient double threshold optimization problem by considering both sensing accuracy and stability to achieve the optimal probability of detection. Finally, a hybrid cooperative spectrum sensing scheme based on spatial-temporal correlation is designed for the CR-VANET. Simulation results reveal that the proposed scheme could achieve significant sensing performance gain by selecting a subset of secondary users for combination, and could reduce user selection frequency by employing spatial- temporal diversity.

Radio frequency identification (RFID) is a kind of automatic identification technology which can be used for indoor positioning system. In this paper, an indoor RFID location algorithm is proposed based on nonlinear support vector regression (SVR) and particle swarm optimization (PSO). The algorithm uses SVR to construct the nonlinear mapping relation between received signal strength indication (RSSI) and distance between the tags and the readers. Based on nonlinear mapping relation, the nonlinear equation set is constructed. In addition, through applying PSO to optimize the objective function converted by nonlinear equation set, the coordinate position of target tag can be estimated. Finally, the simulation of this algorithm and some other algorithms is conducted. The experimental results show that SVR-PSO algorithm is more efficient than the previous algorithms in terms of positioning accuracy and positioning stability.

Recently, many technological issues concerning co-operative spectrum sensing (CSS) of cognitive radio networks (CRNs) have been studied, but most of them focus on maximizing spectral efficiency (SE) under the opportunistic spectrum access (OSA) scheme. In this paper, we investigate the mean energy efficiency (EE) maximization problem under the hybrid spectrum sharing (HSS) scheme. Due to channel fading, the effects of reporting channel errors on the EE should be considered. Specifically, the minimum transmit data rate constraint is imposed to ensure the quality of service (QoS) requirements of secondary users (SUs). Our goal is to maximize the mean EE while maintaining the sensing accuracy by jointly optimizing the sensing slot length and the number of cooperative SUs, subject to the rate constraint and the transmit and interference power constraints. To address the non-convexity of the optimization problem, we propose an energy-efficient CSS iterative power adaptation algorithm. Simulation results demonstrate that the proposed algorithm can achieve higher average EE than the conventional OSA scheme.

This letter introduces a novel grayscale-inversion and rotation invariant descriptor, called sorted local gradient pattern, for texture classification. First, we propose two complementary local gradient patterns (LGP), the center-to-ring LGP (LGP_CR) and the ring-to-ring LGP (LGP_RR), to encode rich gradient information present in a local neighborhood. Then, we propose to enhance LGP by encoding pixels’ intensity information. This is achieved by sorting image pixels into two categories via a dominant intensity order measure, followed by extracting LGP features over the categorized pixels. As a result, local gradient information and global intensity order information are both encoded into our descriptor in a way that is robust to grayscale-inversion and rotation changes. Experiments on three texture databases demonstrate that the proposed descriptor achieves state-of-the-art classification results in the presence of linear and even nonlinear grayscale-inversion changes.

Classifying texture images, especially those with significant rotation, illumination, scale, and viewpoint changes, is a fundamental and challenging problem in computer vision. This paper proposes a simple yet effective image descriptor, called Locally Encoded TRansform feature hISTogram (LETRIST), for texture classification. LETRIST is a histogram representation that explicitly encodes the joint information within an image across feature and scale spaces. The proposed representation is training-free, low-dimensional, yet discriminative and robust for texture description. It consists of the following major steps. First, a set of transform features is constructed to characterize local texture structures and their correlation by applying linear and non-linear operators on the extremum responses of directional Gaussian derivative filters in scale space. Established on the basis of steerable filters, the constructed transform features are exactly rotationally invariant as well as computationally efficient. Second, the scalar quantization via binary or multi-level thresholding is adopted to quantize these transform features into texture codes. Two quantization schemes are designed, both of which are robust to image rotation and illumination changes. Third, the cross-scale joint coding is explored to aggregate the discrete texture codes into a compact histogram representation, i.e., LETRIST. Experimental results on the Outex, CUReT, KTH-TIPS, and UIUC texture data sets show that LETRIST consistently produces better or comparable classification results than the state-of-the-art approaches. Impressively, recognition rates of 100.00% and 99.00% have been achieved on the Outex and KTH-TIPS data sets, respectively. In addition, the noise robustness is evaluated on the Outex and CUReT data sets. The source code is publicly available athttps://github.com/stc-cqupt/letrist.

How to improve system capacity and spectral efficiency is a key issue for next generation wireless communication. Heterogeneous network (HetNet) has been considered as a new promising technique for enhancing the quality of service and spectrum efficiency due to different radio access technology and network structures. However, conventional resource allocation algorithms in HetNets are achieved under the assumption of perfect parameter information which may be invalid in practical systems. In this paper, a robust rate maximization resource allocation problem for multiuser cognitive HetNets is formulated to flexibly use network resource and improve overall capacity where robust cross-tier interference constraint and maximum transmit power constraint of base station are simultaneously considered. The semi-infinite programming problem is converted into a geometric programming problem by using relaxation approaches. Simulation results show that the proposed algorithm can guarantee transmission performance of macrocell users and microcell users under channel uncertainties.

In cognitive radio networks (CRNs), spectrum sensing data falsification (SSDF) is one of the most typical attack which hugely degrades the detection performance of cooperative spectrum sensing (CSS). SSDF and defense strategies have been an active field of research, but countermeasures of existing researches are sensitive to the number of malicious users (MUs). In this paper, we propose a two-stage credit threshold (TSCT) scheme based CSS to counter arbitrary number of MUs who exist in CRNs. We divide the network region into cells according to channel condition, and CSS procedure is conducted into two stages, which are the secondary user (SU) stage and cell stage. Our proposed scheme can effectively remove MUs in the SU stage and weaken the bad effects of remnant MUs in the cell stage. In comparison to existing schemes, simulation results show that the proposed scheme can provide with better detection performance regardless of detection rounds, and can work well when MUs outnumber SUs while previous schemes fail.

Cooperative spectrum sensing is one of the key technologies to accurately detect the primary user (PU) activity in cognitive radio networks (CRNs). However, collaboration among multiusers provides malicious users (MUs) with an opportunity to launch spectrum sensing data falsification (SSDF) attack. Various approaches have been proposed regarding how to mitigate the negative effect of SSDF attack, while extensive references have strong assumptions such as MUs are in minority and need more decision samples. In this paper, we develop a general SSDF attack model. We further propose a robust data fusion scheme, named robust weighted sequential probability ratio test (RWSPRT), which can deal with various attack probabilities. In the proposed RWSPRT, according to the correct decision ability, the reputation value (RV) of each SU is integrated into weight coefficient of weighted sequential probability ratio test (WSPRT) to improve the performance of cooperative spectrum sensing. Simulation results show that RWSPRT performs more robust than traditional data fusion techniques whereas requires less number of samples, even when a large number of MUs exists in CRNs.

In this paper, we investigate the physical-layer security for a wireless two-hop relay network in the presence of channel estimation errors when estimating the channel state information (CSI) of the main links (from the source via relays to the destination) and wiretap links (from the source and relays to the eavesdropper). The eavesdropper can not only overhear the confidential signals transmitted by the relays, but also tap the secret messages transmitted by the source. We present an channel estimation error oriented relay selection (CEEoRS) scheme to improve the security-reliability tradeoff (SRT). We also analyze the intercept probability and outage probability of the CEEoRS scheme, where the intercept probability and outage probability can quantify the security and reliability, respectively. For comparison purposes, the traditional direct transmission with channel estimation errors (TDTwCEE) is also analyzed. It is shown that the proposed CEEoRS scheme outperforms the TDTwCEE scheme in terms of its SRT. More specifically, the proposed CEEoRS scheme is capable of significantly improving the SRT performance of wireless communications through increasing the number of relays.

In this paper, we propose a novel resource allocation (RA) scheme based on interference minimization (IM) for cognitive radio networks (CRN). In the approach, we focus on an efficient scheme of subchannels assignment, power allocation and access control for the orthogonal frequency division multiple access (OFDMA)-based secondary users (SUs), accessing licensed spectrums of primary users (PUs) with underlay approach. Different from traditional schemes, we consider more for PUs' capacity protection, by taking the interference introduced to PUs as minimization objective. Compared with other schemes, the simulation results show that our proposed scheme can reserve more PUs' capacity, while guaranteeing the rate and the Quality of Service (QoS) of SUs.

Schemes combining Ultra-wide bandwidth (UWB) ranging technology and Inertial Measurement Unit (IMU) have been proposed for high precision positioning and tracking. However, positioning accuracy can be significantly affected by the non-line-of-sight (NLOS) UWB ranging measurements and cumulative inertial sensing error. In this paper, we model the ranging measurement error and the step length as Gaussian Mixture Model (GMM), respectively. Then, we derived a Suboptimal Importance Density (SID) for particle filters, which could resolve the degeneracy of particles and sample impoverishment. Finally, experimental results illustrate the performance gain of the particle filters with the proposed SID.

Cooperative localization has become a promising solution for location-enabled technologies in Wireless Sensor Networks (WSNs). However, it suffers from great energy consumption problem due to the energy-constrained characteristic of the networks. To alleviate this problem, we propose a cluster nodes selection strategy based on the Cramer-Rao lower bound (CRLB) for the cooperative localization algorithm in WSN. We first define clusters for every agent node by setting the received signal strength (RSS) threshold to screen out some less useful nodes, which greatly saves the energy at a cost of only a slight degradation in accuracy. Then, to improve the localization accuracy, the cluster nodes selection strategy catches the nodes that make the biggest contribution to localization results while discarding the least ones based on the derived analogous-CRLB values. Simulations show that the number of nodes participating in the localization is greatly decreased, which means a substantial reduction in energy consumption. In addition, the localization mean absolute error performance is significantly improved by using the proposed nodes selection algorithm.

In this paper, we consider a cooperative relay network consisting of a source, a destination, and multiple decode-and-forward (DF) relays in the presence of multiple eavesdroppers, which intend to tap confidential messages transmitted by both the source and the relays. We propose a so-called secrecy maximization oriented relay selection (SMORS) scheme to improve the physical-layer security of wireless communications. In the SMORS scheme, a relay with the maximal secrecy rate is selected among all the DF relays to forward the source signal. We analyze the intercept probability of the proposed SMORS scheme as well as the traditional max-min relay selection scheme. Numerical results show that the proposed SMORS scheme outperforms the conventional max-min relay selection scheme in terms of the intercept probability. Additionally, it is shown that with an increasing number of eavesdroppers, the intercept performance of wireless communications degrades, which can be well addressed using the proposed SMORS scheme through increasing the number of relays. By contrast, increasing the number of relays has little impact on the intercept probability for the conventional max-min relay selection scheme, especially when the number of relays is sufficiently high (e.g., exceeding 20 relays).

In this study, the authors investigate the physical‐layer security in a cognitive amplify‐and‐forward relay network consisting of a secondary transmitter (ST) and a secondary destination (SD) with the aid of multiple secondary relays (SRs) in the face of multiple eavesdroppers. In cognitive radio networks, increasing transmit power may not always be beneficial in terms of improving the channel capacity of cognitive transmissions, which would not only cause an extra interference to primary user, but also enhance the possibility of successfully intercepting the cognitive transmissions at an eavesdropper because an improved signal strength is received in this case. The authors propose two relay selection schemes to improve the physical‐layer security of cognitive transmissions against eavesdropping attacks, which are referred to as the global and partial channel state information based relay selection, denoted by GCSIbRS and PCSIbRS, respectively. The authors analyse the intercept probability of the proposed GCSIbRS and PCSIbRS, as well as the traditional round‐robin and all‐relay transmission schemes. It is shown that the proposed GCSIbRS and PCSIbRS schemes both outperform the conventional round‐robin and all‐relay schemes in terms of their intercept probability performance.

Most existing video segmentation methods are focused on extracting the primary objects in test video sequences. They assumed that only one object appeared through the whole video sequences, which is impractical in many applications. In this paper, we focus on the object segmentation from the long video sequences which consist of many different scenes, shot cuts and various motion patterns, etc. In order to solve this problem, we propose a framework to segment the objects in relative video shots, while discarding the irrelative video shots. A graph is constructed to model the video object detection and final segmentation is obtained by getting the superpixels in the detection boxes. We also introduce a new long video segmentation dataset which corresponds to the pixel-wise ground truth. The experiments demonstrate that our proposed method can deal with the object segmentation in long video sequence.

The opportunistic spectrum access in cognitive radio networks has always played a key role in improving the performance of secondary users. In this paper, we propose an optimal spectrum access strategy for multi-channel access of secondary users under multiple physical considerations. Firstly we integrate path loss and Nakagami-m fading of primary and secondary links with imperfect spectrum sensing into our model to obtain the probability that data packet is successfully transmitted. Then we introduce the M/M/1/K queueing to deduce the average packet delay under the assumption of finite-size buffer. In order to minimize the total average packet delay, the optimal probability vector for spectrum access is confirmed by genetic algorithm. Result proves that our proposed spectrum access strategy outperforms the strategies of equal probability and inverse ratio. Furthermore, according to the optimal probability vector, the total average packet loss rate is derived with one more consideration that the number of transmission attempts for automatic repeat request is fixed. Finally, numerical results illustrate the effects of referred lower-layer parameters on total average packet delay and loss rate.

Despite its success in texture analysis, Local Binary Pattern (LBP) is operated in the original image space, and it fails to capture deeper pixel interactions to provide a more discriminative description. In this paper, we propose to explore the joint statistical representation in the space-frequency domain with local quantized patterns for texture classification. The proposed method consists of two channels. In each channel, the multi-resolution spatial filters are employed to generate multi-scale spatial maps and the local Fourier transform is subsequently applied to extract local frequency features (spectral maps). The global thresholding is adopted to quantize the spatial and spectral maps into different levels, which are then jointly encoded to built a space-frequency co-occurrence histogram. Finally, the two-channel feature histograms are combined to represent the texture. Experiments on the Outex texture database demonstrate the robustness of our method to image rotation and illumination changes, and our method outperforms the state of the art in terms of the classification accuracy.

This letter presents a noise-robust descriptor by exploring a set of local contrast patterns (LCPs) via global measures for texture classification. To handle image noise, the directed and undirected difference masks are designed to calculate three types of local intensity contrasts: directed, undirected, and maximum difference responses. To describe pixel-wise features, these responses are separately quantized and encoded into specific patterns based on different global measures. These resulting patterns (i.e., LCPs) are jointly encoded to form our final texture representation. Experiments are conducted on the well-known Outex and CUReT databases in the presence of high levels of noise. Compared to many state-of-the-art methods, the proposed descriptor achieves superior texture classification performance while enjoying a compact feature representation.

In this paper, we present a robust texture representation by exploring an ensemble of binary codes. The proposed method, called Locally Enhanced Binary Coding (LEBC), is training-free and needs no costly data-to-cluster assignments. Given an input image, a set of features that describe different pixel-wise properties, is first extracted so as to be robust to rotation and illumination changes. Then, these features are binarized and jointly encoded into specific pixel labels. Meanwhile, the Local Binary Pattern (LBP) operator is utilized to encode the neighboring relationship. Finally, based on the statistics of these pixel labels and LBP labels, a joint histogram is built and used for texture representation. Extensive experiments have been conducted on the Outex, CUReT and UIUC texture databases. Impressive classification results have been achieved compared with state-of-the-art LBP-based and even learning-based algorithms.

In this paper, we exploit an algorithm for detecting the individual objects from multiple images in a weakly supervised manner. Specifically, we treat the object co-detection as a jointly dictionary learning and objects localization problem. Thus a novel low-rank and sparse representation dictionary learning algorithm is proposed. It aims to learn a compact and discriminative dictionary associated with the specific object category. Different from previous dictionary learning methods, the sparsity imposed on representation coefficients, the rank minimization of learned dictionary, data reconstruction error and the low-rank constraint of sample data are all incorporated in a unitized objective function. Then we optimize all the constraint terms via an extended version of augmented lagrange multipliers (ALM) method simultaneously. The experimental results demonstrate that the low-rank and sparse representation dictionary learning algorithm can compare favorably to other single object detection method.

Spectrum sensing is a key feasible technology for cognitive radio (CR). Sensing time is an important sensing parameter which brings about a sensing-throughput tradeoff. In this paper, based on soft decision schemes, we investigate the sensing-throughput tradeoff problem and analyze the impact of different system parameters on the optimal sensing time for cooperative spectrum sensing. Simulation results show that maximal ratio combination g (MRC) and modified deflection coefficient (MDC) schemes have almost the same performance which outperform equal gain combination (EGC) scheme. Further, optimal sensing time decreases with the increase of number of CR users and increases when average signal-noise-ratio (SNR) decreases.

We present a novel feature descriptor, Local Polar DCT Features (LPDF), which is robust to a variety of image transformations. Specifically, the local patch is quantized in the designed polar geometric structure and the 2-D DCT features are then extracted and rearranged. A subset of the resulting DCT coefficients is selected as our compact LPDF descriptor. We perform a comprehensive performance evaluation with state-of-the-art methods, i.e., SIFT, DAISY, LIOP, and GLOH on the standard Oxford dataset and two additional test image pairs. Experimental results demonstrate the superiority of proposed descriptor under various image transformations, even with very low dimensions.

The cognitive cooperative system with coexisting scenario of multiple primary users and one secondary capable of relaying is considered in this study. The primary users transmit packets in orthogonal subchannels. According to the cognitive principle, the secondary activity cannot interfere with the primary performance. Therefore in this study, the secondary user makes use of the spectrum when sensed idle. Based on the proposed media access control (MAC) protocol, the authors derive the stable throughput and delay slots expressions of each primary user with secondary relaying. They also achieve the stable network constraints of relaying probability ɛ, the feasible range of primary arrival rates and the maximum allowed secondary transmitting power which is to make a tradeoff between the stable throughput of the primary and secondary user. Simulation results show that secondary relaying can increase the primary and secondary throughput and also reduce the delay slots when designing an appropriate ɛ.

The concept of cognitive radio is to exploit efficiently the spectrum resources by allowing the coexistence of the primary and secondary users in the same bandwidth without interfering the performance of primary users. Three coexisting models (overlay, underlay and interleave) were presented in recent literature. In this study, the authors propose a hybrid cognitive network model with overlay and underlay models, whereby a primary link leases its fractions of transmission time to the secondary users for their cooperation (i.e. these nodes form as a virtual multiple input multiple output (VMIMO) group) under the outage constraints of the primary and secondary systems. A new cooperative protocol between primary and secondary users is presented. The authors attempt to achieve the maximum transmission capacity of the secondary users under the primary and secondary outage constraints, which depend on the secondary density in the cognitive network. This study gives the upper bound density of the secondary transmitters that are modelled as a homogeneous marked Poisson point process. The maximum density is achieved by computing an optimal set of system parameters such as power control factor of the secondary user and the dirty paper coding (DPC) parameter. Simulation results illustrate that the maximum secondary density obtained using VMIMO is superior to that obtained by direct primary transmission.

The cognitive cooperative system with coexisting scenario of multiple primary users and one secondary capable of relaying is considered. The primary users transmit packets in orthogonal sub-channels. According to the cognitive principle, the secondary activity cannot interfere with the primary performance. Therefore, in this paper, the secondary user makes use of the spectrum when sensed idle. Based on the proposed MAC protocol, we derive the stable throughput expressions of each primary user with secondary relaying. We also achieve the stable network constraints of relaying probability ε, the feasible range of primary arrival rates and the maximum allowed secondary transmitting power which is to make a tradeoff between the stable throughput of the primary and secondary user. Numerical simulations show that secondary relaying can increase the primary and secondary throughput when designing an appropriate ε.

A novel selection cooperation scheme for cognitive nodes (Cog-Sel scheme) in multiple sources cooperative networks is presented and the outage probability is derived. In the proposed scheme, the source chooses a single optimal relay or transmits directly to the destination in terms of the SNR between the source-destination pair with some feedback. Each node can smartly utilize the idle frequency band to transmit signal using cognitive radio technology. Therefore, no extra channel resources are allocated for cooperation and the system encounters no bandwidth losses. The outage probability of the proposed scheme is analyzed and the result reveals that it outperforms the conventional relaying strategies such as simple selection and opportunistic relaying schemes. These benefits contribute to the efficient use of power and channel resources. Theoretic analysis and numerical simulation results are presented to verify our analysis.

Performance analysis for keyhole channel of a new kind of quaternion quasi-orthogonal space time block code is introduced in this paper. First the transmission model is formulated. Then the new code of four transmit antennas is designed, the new code can provide full transmission rate. And zero-forcing linear decoding method is adopted. Lastly the new code is compared with the quaternion quasi-orthogonal space-time block code of four transmit antennas for Rayleigh channel and with the traditional quasi-orthogonal space-time block code of four transmit antennas for keyhole channel. Simulation results show that the new code can increase bit error rate compared with the quaternion quasi-orthogonal space-time block code for Rayleigh channel, and can reduce bit error rate compared with the traditional quasi-orthogonal space-time block code for keyhole channel.