In this paper, we investigate an unmanned aerial vehicle (UAV)-assisted satellite-terrestrial system with simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) and rate splitting multiple access (RSMA). More specially, the satellite employs RSMA to send messages over a STAR-RIS-assisted UAV to a pair of legitimate users located on the earth in order to enable better use of spectrum resources. Serving as a mobile aerial base station, the UAV transmits information to the users through a fixed-gain amplify-and-forward (AF) or decode-and-forward (DF) relay. Also, we use the STAR-RIS to enhance the link from satellite to terrestrial. In order to evaluate the covert performance of the considered system, we derive closed-form expressions of covert performance metrics including the outage probability (OP), the covert transmission rate, and the detection error probability (DEP). Then, we analyze the impact of changes in the system parameters on the system performance, and provide some useful insights. Additionally, we present numeric simulations to validate the correctness of the theoretical results and show the considered system performs better in terms of the covert performance than the system using the non-orthogonal multiple access (NOMA) protocol.

This paper studies an intelligent omni-surface (IOS)-aided integrated sensing and communication (ISAC) system, where a base station (BS) provides simultaneous target sensing and communication services with an IOS under outdated and imperfect channel state information (CSI). Both the communication sum-rate and sensing signal-to-noise ratio are maximized through joint optimization of BS beamforming and IOS configuration. To address this problem, we propose an intelligent joint optimization scheme called meta multi-objective hybrid deep reinforcement learning (meta-MHDRL). Specifically, the meta-MHDRL framework first introduces a hybrid deep reinforcement learning (DRL) approach that integrates double-critic-based deep deterministic policy gradient with deep double Q-network algorithms, enabling parallel optimization of both continuous-domain variables (i.e., BS beamforming, IOS reflecting phase shift, and IOS reflecting/refracting amplitudes) and the discrete-domain variable (i.e., IOS refracting phase shift). Thereafter, an objective-preference weight is incorporated into the hybrid DRL framework, such that meta-MHDRL can capture the trade-off between communication and sensing performance. To address the complex coupling relationships among different optimization variables, we further put forth a synchronized experience replay mechanism for meta-MHDRL, which maintains training synchronization among different neural networks. In addition, a meta-learning approach is developed to enhance the generalization ability of meta-MHDRL across different objective-preference weights. Simulation results show that meta-MHDRL attains more Pareto-efficient solutions than other schemes under outdated and imperfect CSI while maintaining stronger robustness across various simulation setups. Besides, we demonstrate the generalization ability of meta-MHDRL for unseen tasks

This paper investigates a new integrated sensing and communication (ISAC) scheme for underwater acoustic (UWA) networks based on deep reinforcement learning, referred to as Deep UWA-ISAC (DeepUSC). Specifically, we consider a UWA-ISAC system, where an autonomous underwater vehicle (AUV) transmits the collected environmental data to the buoy, while sensing the sea area to monitor the unauthorized mobile target. The expected communication rate over a given navigation period is maximized by jointly optimizing the AUV's beamforming and trajectory, subject to the constraints on the average signal-to-noise ratio requirement for target sensing as well as the navigation mission, collision avoidance, and maximum transmit power limit of the AUV. Three key challenges for DeepUSC are: (i) long propagation delays in the UWA-ISAC system may cause interference from the previous echo to the current ISAC signal; (ii) the mobility pattern of the target is unknown in advance; and (iii) the AUV navigation-oriented ISAC problem is a long-term optimization problem as the navigation mission typically lasts for a long period. To circumvent the above challenges, DeepUSC is developed based on a specific partially observable Markov decision process model termed episode task, where each navigation period is considered as an episode and the navigation mission corresponds to the episode task. Through judicious design of a reward function and action selection policy, DeepUSC can satisfy various preset constraints without requiring prior knowledge of the target's mobility. Besides, to enable efficient learning in episode tasks, we propose an episodic experience replay mechanism that dynamically prioritizes high-value recent experiences and utilizes all experiences generated within each episode to jointly train the neural network. Simulation results demonstrate that compared with benchmarks, DeepUSC yields a higher communication rate while satisfying all constraints, converges faster, and is more robust against different simulation setups.

In this paper, we propose a federated learning (FL) system enhanced by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS), which is designed to protect client-side data privacy and reinforce the security of data exchange over wireless channels. Assuming an honest-but-curious central server that may infer private information from user gradients, we adopt differential privacy (DP) by injecting noise into local updates to safeguard user data. Theoretical results are derived to characterize the systematic privacy guarantees provided by the DP noise power and the gradient information in the proposed STAR-RIS-enabled DP-FL systems. Building on these results, the secrecy sum rate of local information is formulated by jointly optimizing the STAR-RIS coefficient matrices, users’ transmission power, artificial jamming power, and the power of DP noise introduced by the FL users. To tackle the non-convex optimization challenge, we develop a block coordinate descent algorithm that partitions the original problem into four manageable subproblems. The closed-form expressions are obtained for users’ transmit power, artificial jamming power, and the power of DP noise. For the STAR-RIS phase shift design, approximate solutions are derived through semidefinite relaxation combined with a surrogate lower bound method. Finally, simulation results demonstrate that the proposed STAR-RIS-enabled DP-FL systems achieve significantly improved secrecy performance compared to conventional FL systems with randomly configured STAR-RIS amplitude, phase shifts, and transmit power. Furthermore, the proposed FL algorithm achieves model training and testing performance that closely approximates that of FL without DP, highlighting its effectiveness in preserving both data privacy and model utility.

Face super-resolution (FSR) aims to reconstruct high-resolution (HR) face images from the low-resolution (LR) inputs. The advancement of FSR has been significantly accelerated by the application of convolutional neural networks in recent years. However, most existing FSR methods are still unsatisfactory in recovering facial texture details. Particularly in the high-magnification face image reconstruction tasks, it is difficult to accurately restore the facial detail features. To address this problem, we propose a Hierarchical Texture Reconstruction Network for FSR with Facial Prior (HTR-FSRNet), which performs hierarchical processing of textures in different regions of face images by proposing new local texture reconstruction modules, thereby better restoring the texture details. The HTR-FSRNet consists of two stages. In the first stage, we introduce a Local-Global Feature Enhancement Module (LGEM) to establish contextual dependencies. Then, based on the traditional convolutional feature extraction method, we develop a new Local Variance Adaptive Convolution (LVAC) module, specifically designed to handle texture-rich regions in face images. In the second stage, we develop a Local Pixel Adjustment Module (LPAM), which not only alleviates artifacts generated during the image restoration process but also reconstructs face regions with relatively lower texture complexity from a new perspective. With this design, we can reconstruct the facial structure and more specifically restore different texture regions. Meanwhile, our method is applicable to the tasks of high-magnification face image reconstruction. Experimental results confirm the superior performance of the proposed HTR-FSRNet.

This work addresses the challenge of simultaneous position and orientation (SPAO) estimation in visible light systems, a task complicated by interference from wall reflection components. To overcome this issue, a novel visible light SPAO system is proposed that integrates a single light-emitting diode (LED) and a single photodiode (PD) with an optical intelligent reflecting surface (IRS). Unlike traditional visible light SPAO methods, the proposed system determines the number of independent measurement links based on the number of positioning time slots rather than the number of LEDs, PDs, or IRSs. The system effectively mitigates the adverse effects of wall reflection components by relying solely on the channel gain between the IRS and the user device. The Cramer–Rao Lower Bound (CRLB) is derived as a performance benchmark for the SPAO system. Building on this benchmark, an enhanced differential evolution (DE) algorithm is introduced, balancing global exploration and local exploitation. The algorithm incorporates mechanisms to escape local optima, ensuring improved convergence to the global optimal solution. Simulation results demonstrate that the proposed visible light SPAO system’s performance closely approaches the CRLB and surpasses state-of-the-art baseline methods.

Due to the harsh channel conditions and operational difficulties in battery recharging, energy-efficient transmission is critical in underwater acoustic communications (UACs). This paper investigates a new link adaptation technique for UACs that jointly optimizes transmission frequency, power, and rate to maximize energy efficiency. Conventional optimization-based approaches typically require real-time and perfect channel state information and have high computational complexity, making them difficult to implement in realistic systems. To circumvent this problem, we put forth MetaDT, a model-free link adaptation technique combining deep reinforcement learning with meta-learning. To enable powerful reasoning and fast decision-making, we further propose a dueling echo state network (ESN) with separate output architecture for incorporation into MetaDT. Besides, to enable MetaDT to quickly adapt to diverse new/unseen environments, a low-complexity meta-learning is developed to find the optimal meta-parameters of the dueling ESN architecture. Numerical results show that compared to various benchmarks, MetaDT attains significant energy efficiency gains and is more robust against different transmission distances and numbers of multi-paths. In comparison to conventional neural networks, dueling ESN shortens the run-time of MetaDT by more than 89.58% and is more efficient for temporal inference. In addition, we demonstrate the generalization capability of MetaDT with meta-learning to new/unseen environment configurations.

Tumor-stroma ratio (TSR), which is the area ratio between two components within tumor beds, namely tumor cells and tumor stroma, has been suggested as a promising prognostic feature in breast cancers. However, due to imperfect datasets, and the similarity between tumor stroma and non-tumor stroma, previous algorithms struggle to delineate tumor beds, especially those of histomorphologies with a fibrotic focus. To overcome these limitations, we propose a novel ray-aided quadruple affiliation network (RQA-Net) for calculating TSRs in breast cancers. RQA-Net uses quadruple branches to segment tumor cells and tumor beds simultaneously, where a crisscross task subtraction module (CTS-Module) is designed to locate tumor stroma, grounded on its affiliation relationships with tumor beds. Moreover, we propose an affiliation loss (Aff-Loss) to force identified tumor beds to incorporate tumor cells to enhance their affiliation relationships. Furthermore, we propose a ray-based hypothesis testing (RH-Testing) to obtain line segments from ray equations in tumor beds that can decorate identified tumor beds by overlapping. In summary, RQA-Net precisely predicts tumor cells and tumor beds, and thus supports the calculation of TSRs. We also create a cancerous dataset (CrD-Set) containing 100 slides with an average resolution of $50,000\times 50,000$ pixels from real breast cancer cases, which is the first dataset with pixel-wise tumor bed annotations. Experimental results on existing datasets and CrD-Set demonstrate that compared with previous methods, RQA-Net better calculates breast cancer TSRs by precisely identifying tumor cells and tumor beds. The created CrD-Set and codes in this work will be available online at https://github.com/Kunpingyang1992/Breast-Cancer-TSR-Calculation.

Fatigue driving is a common issue that often leads to traffic accidents, which has motivated numerous automatic driving fatigue detection methods based on various sources, especially reliable physiological signals. However, it still faces the challenges of accuracy, robustness and practicality, especially for the cross-subject detection. The fusion of multi-modality data can improve the effective estimation of driving fatigue. In this work, we take the advantages of user-friendly and multi-modality signals to build a Multi-Modality Attention Network (MMA-Net) for driver fatigue detection with frontal electroencephalography (EEG), electrodermal activity (EDA) and photoplethysmography (PPG) signals for a hybrid. Specifically, a signal adaptive coding module (SAC-M) has been constructed to fully excavate spatial-temporal information of signals, combining with an attention-based feature dissimilation module (AFD-M) to further obtain key comprehensive features. In addition, the performances of baseline models and state-of-the-art methods on signal sources with different window lengths are also compared. The cross-subject experiment is performed on two groups of 14 participants in the driving simulation experiment. The experimental results prove the superiority of our proposed method. It is possible to use the MMA-Net for driver fatigue detection with user-friendly multi-modality signals, such as our selected frontal EEG, EDA and PPG in real-world applications.

Autonomous aerial vehicles (AAVs) with cache are considered as an efficient technique to enhance serving capabilities of traditional wireless networks in terms of network coverage and capacity. However, with the introduction of AAVs, new challenges such as trajectory design and AAV-user association occur. In this paper, we consider a caching AAV-assisted wireless network and formulate a user fairness problem by jointly optimizing AAV-user association, trajectory design, and bandwidth allocation of the AAVs, which is mixed-integer and non-convex. In order to find solutions, we decompose the original problem into three subproblems and propose an iterative algorithm based on block alternating descent and successive convex approximation methods. In addition, computational complexity is analyzed. Finally, simulation results validate the efficiency of the proposed algorithm, compared to benchmark algorithms.

While single-image super-resolution (SISR) methods based on convolutional neural networks (CNNs) have made remarkable progress, the increasing number and width of convolutional layers pose challenges due to heightened demands on computing resources and memory. In response to this issue, researchers have introduced several lightweight CNN models, among which the feature distillation network has emerged as a prominent solution. Motivated by the success of feature distillation networks and convolutional modulation (Conv2Former), we propose a straightforward convolutional modulation feature distillation network (CFDN). Dilated convolution is employed to expand the receptive field, thereby enhancing the performance of Conv2Former. Simultaneously, we integrate channel attention with a modified convolutional modulation block. Additionally, to optimize network performance, we introduce a spatial attention block. In comparison to other lightweight CNN SR models, our CFDN demonstrates commendable performance across various SR benchmarks.

To fulfill the requirements of human lunar exploration programs and establish bases on the moon in the distant future, lunar sensors (LSs) will inevitably produce a significant amount of data. It is necessary to construct the Earth-Moon metaverse in order to obtain and utilize lunar information more effectively. Due to the long communication distance between Earth and Moon as well as the lack of communication resources, a hybrid Earth-Moon metaverse network with channel model and transmission model is designed. To ensure the efficiency and stability of transmission in the network, LSs transmit lunar data to Earth clients (ECs) through the active and passive intelligent reflecting surface (IRS) deployed at relay satellites. Then, we propose a Stackelberg game model to describe the adversarial relationship between the satellites, LSs and ECs, and optimal strategies are obtained by solving the Nash equilibrium to maximize their utility. Simulations demonstrate that the network can effectively shorten the transmission delay and improve the utility of ECs and satellites.

To solve the sudden inter-satellite link failures of low earth orbit satellite networks (LEO-SNs), a robust routing algorithm against link failures is proposed in this paper. Firstly, we introduce a 2-D Markov model for LEO-SNs to study the problem about how to minimize the probability of encountering link failures in minimum-hop path set. Theoretical results indicate that forwarding in the more-hop direction has a lower probability to encounter link failures. Based on the results, we propose a More-Hop Direction Priority routing algorithm with routing Recovery strategy by Extending Path Area (MHDPREPA). The algorithm consists of three components which are routing preparation, routing calculation and routing recovery. In the routing process, each node aims to avoid encountering link failures when selecting the next hop node. If the node encounters link failures, a routing recovery strategy is adopted to bypass the failed links. Simulation results show that our proposed algorithm can effectively improve delivery ratio and average throughput compared with baseline algorithms.

In this work, we study the performance of an unmanned aerial vehicle (UAV)-aided mixed radio frequency (RF)/underwater acoustic communication (MRFUAC) transmission system, where the UAV transmits signals to an underwater node through the amplify-and-forward (AF) relay, such as a buoy located on the sea surface. In particular, the UAV-relay RF channel follows a Rician distribution, while κ-μ shadowed fading distribution is applied to model the UAC link. For this considered system with the fixed-gain AF relay, we obtain the statistical distributions of the end-to-end signal-to-noise ratio. To demonstrate the performance of the MRFUAC system, formulae for the outage probability and average bit-error rate are further obtained in closed form. Moreover, to obtain some interesting insights, we present the asymptotic analyses of these performance metrics. To show the validity of our analysis, the truncation error analysis is also provided and the results show that our proposed method has a smaller error than that in the previous literature. In addition, we present the analysis of the optimal height of the UAV at different horizontal distances. In addition to the fixed-gain analysis, we also provide few results for the variable-gain AF relaying MRFUAC system. Finally, the validity of the theoretical analysis is confirmed by Monte Carlo simulations.

The intelligent transportation system (ITS) was supported by the sixth generation (6G) wireless networks, since it has great potential to realize intelligent transportation with the benefit for the society and economy. In order to overcome the practical problem of spectrum scarcity, ultra-low latency, large-scale connectivity in ITS, we propose a cooperative multiple-input single output non-orthogonal multiple access (MISO-NOMA) for ITS with intelligent reflecting surface (IRS) and simultaneous wireless information and power transfer (SWIPT). An user fairness optimization problem is formulated to maximize the fairness rate of the vehicles, subject to the quality of service requirements of the vehicles and the successive interference cancellation. The optimization problem involves the transmit beamformers design, the IRS reflection matrix design, and the power splitting ratio of the SWIPT, which lead to the problem is difficult to solve. For solving the challenging problem, an iterative successive convex approximation and semi-definite relaxation based algorithm is proposed. Explicitly, we firstly adopt the method of reconstructing epigraph for simplification due to the objective function is non-convex, and then the original problem is decomposed into two sub-problems that are easy to solve. Finally, Experimental results illustrate that the user fairness of the proposed cooperative MISO-NOMA for ITS with IRS and SWIPT is better than that of both the IRS-NOMA for ITS without SWIPT and the IRS-OMA for ITS.

The majority of prior coded computation works treat stragglers as erasures over an erasure channel and ignore their partial computations. The whole speed of a computation network will still be limited due to different processing speeds of worker nodes. This paper presents a novel coded scheme for this problem to effectively leverage partial stragglers. It simultaneously embeds the maximum distance separable (MDS) codes and codes in the universally decodable matrices (UDMs) into the system. By imposing constraints on coding parameters, the coefficient matrix corresponding to any first kAkBproducts of encoded submatrices from worker nodes is full rank, when two input matrices are partitioned into kAand kBblock-columns, respectively. Thus, it only requires the minimum kAkBproducts performed by worker nodes (including stragglers). Analysis results show that our scheme can achieve not only the optimal utilization of partial computations of worker nodes, but also the optimal straggler resilience capability.

Collaborative inference in mobile edge computing (MEC) enables mobile devices to offload the computation tasks for the computation-intensive perception services, and the inference policy determines the inference latency and energy consumption. The optimal inference policy depends on the inference performance model of deep learning, the data generation model and the network model that are rarely known by mobile devices in time. In this paper, we propose a multi-agent reinforcement learning (RL) based energy-efficient MEC collaborative inference scheme, which enables each mobile device to choose both the partition point of deep learning and the collaborative edge of each mobile device based on the image quantity, the channel conditions and the previous inference performance. A learning experience exchange mechanism exploits the Q-values of the neighboring mobile devices to accelerate the inference policy optimization with less energy consumption. We also provide a deep multi-agent RL based inference scheme to accelerate learning for large-scale MEC networks, in which an actor network yields the collaborative inference policy probability distribution and a critic network guides the weight update of the actor network to enhance sample efficiency. We provide the inference performance bound and analyze the computational complexity. Both simulation and experimental results show that our proposed schemes reduce the inference latency and save the MEC energy consumption.

This paper investigates the secrecy performance for simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted downlink multi-carrier non-orthogonal multiple access (NOMA) networks, consisting of multiple legitimate users and eavesdroppers. We propose two STAR-RIS-NOMA schemes for maximizing the secrecy performance by jointly optimizing the transmission and reflection beamforming of the STAR-RIS, the transmit beamforming of the base station (BS), the power allocation coefficients and the user pairing vector under the full channel state information (CSI) and the statistical CSI of the eavesdropping channel, respectively. For the full CSI available to the BS, an alternating beamforming algorithm is proposed for maximizing the secrecy sum rate. Specifically, we first propose a user pairing scheme based on the differences of user’s channel gains. Then the beamforming vectors and the power allocation coefficients are optimized based on the techniques of semidefinite programming and surrogate lower bound approximation, respectively. For the statistical CSI available to the BS, the problem of minimizing the maximum secrecy outage probability (SOP) is investigated. By invoking the subroutines of alternating beamforming algorithm, we first derive an exact SOP given the user pairing. Then, we conceive the beamforming vectors and the power allocation coefficients by linear matrix inequality and linear programming, respectively. Simulation results show that: 1) the secrecy performance of the proposed STAR-RIS-NOMA scheme outperforms the existing conventional RIS-NOMA scheme and RIS assisted orthogonal multiple access (RIS-OMA) scheme; 2) the proposed alternating beamforming algorithm is capable of achieving a near-optimal performance with low complexity compared to the exhaustive search.

Since deep convolutional neural network (CNN) has achieved excellent results in single image super-resolution (SISR), an increasing number of methods based on CNN have been proposed. Most CNN-based methods are devoted to finding mapping based on pixel intensity while ignoring the importance of frequency information, which can reflect semantic information of images on different bands. This leads to less effectiveness in the reconstruction of high-frequency details. To address this problem, we propose a novel CNN-based super-resolution method named joint wavelet sub-bands guided network (JWSGN). We separate the different frequency information of the image by the WT and then recover this information by a multi-branch network. To recover finer edge details, we propose an edge extraction module, which estimates an edge feature map by using the similarity of all high-frequency sub-bands and then corrects the high-frequency features recovered from each branch by exploiting the edge feature map. Furthermore, we use the complementary relationship between different frequencies to calibrate the high-frequency sub-bands. Finally, the high-resolution image is obtained by inverse wavelet transform. Both qualitative and quantitative experiments show that our method performs excellent performance with the guidance of the edge extraction module.

In this paper, we study an uplink reconfigurable intelligent surfaces-non-orthogonal multiple access (RIS-NOMA) assisted mobile edge computing (MEC) network with simultaneous wireless information and power transfer (SWIPT), where the users want to offload their computing tasks to the BS via a RIS and a relay based on the SWIPT technique. The goal of the paper is to minimize the delay concerning the computing tasks of the users by jointly optimizing the power allocation ratio, the phase shift matrix of the RIS, the offloading task ratio, and the offloading transmit power. For solving the challenging optimization problem, we conceive a low-complexity algorithm by optimizing two subproblems separately, based on the penalty method as well as the successive convex approximation. Simulation results demonstrate that the proposed RIS-NOMA assisted MEC network with SWIPT outperforms both the conventional RIS-NOMA assisted MEC network without SWIPT and the RIS-orthogonal multiple access assisted MEC network.

In this paper, we consider a downlink multiple-input single-output non-orthogonal multiple access (MISO-NOMA) network with several legitimate users and a eavesdropper using successive interference cancellation (SIC). The purpose of this paper is to maximize the secrecy performance of the MISO-NOMA network by designing the transmit power between the legitimate users and the artificial jamming. Explicitly, the secrecy sum rate of the MISO-NOMA network is to be maximized by optimizing the transmit beamforming vectors and the artificial jamming vector, subject to the required quality of service of each legitimate user, the artificial jamming beamforming design constraint and the SIC decoding condition. Due to the non-convexity of the optimization problem, we reformulate the original problem into an equivalent optimization problem and then provide a successive convex approximation based iterative algorithm for solving it. Simulation results demonstrate that the proposed optimization scheme outperforms the existing schemes.

With significantly dynamic characteristics of the new aerial users, the emerging cellular-enabled unmanned aerial vehicle (UAV) communication paradigm raises great challenges to current research of UAV applications. As far as the robust channel allocation is concerned, the high mobility of UAV nodes and the unexpected disturbance of external environment would render most existing methods which rely on definite information and are vulnerable to dynamic environment, become less attractive or even invalid. In this paper, we particularly investigate a cellular-enabled mesh UAV network exploiting partially overlapping channels (POCs), and propose a distributed fuzzy space based learning scheme for POCs allocation to combat the dynamic environment. Rather than the perfect channel state information (CSI) assumption, the dynamic and uncertain CSI of UAVs is characterized by fuzzy number. On this basis, the allocation process can be implemented in a mapped fuzzy space. Integrating fuzzy-logic and game based learning, we formulate the problem of POCs assignment as a fuzzy payoffs game (FPG), and demonstrate the existence of fuzzy Nash equilibrium for our designed FPG. Then, with the derived priority vector in the fuzzy space, the equilibrium solution can be achieved by the proposed algorithm. Numerical simulations demonstrate the advantages of our new scheme.

Visible light positioning has become a new research hotspot in recent years. In this study, a new Gaussian model of hybrid noise and multipath reflection is established for noise interference in line‐of‐sight (LOS) communication and multipath reflection in non‐LOS (NLOS) communication. First, the likelihood function of the ranging error is established according to the Gaussian hybrid model, and the analytical expression of Cramer–Rao lower bound is derived. Second, the novel adaptive parameter particle swarm optimisation (AP‐PSO) algorithm is proposed to calculate the three‐dimensional (3D) coordinates of the target. In order to avoid falling into the local optimal solution, a novel particle adaptive mutation algorithm, namely AP‐PSO‐M algorithm is also proposed. Simulation results show that if the NLOS propagation probability is 0.3 and the swarm size is 20, compared with Newton–Raphson (NR), particle swarm optimisation (PSO), dissipative PSO (DPSO) and simulated annealing PSO (SA‐PSO) algorithms, the average positioning error based on AP‐PSO‐M algorithm can be reduced by 45.43, 38.98, 25.37 and 26.42%, respectively. If similar positioning accuracy is obtained, compared with PSO, DPSO and SA‐PSO algorithms, the average calculation time required by the AP‐PSO‐M algorithm can be reduced by 48.16, 30.24 and 26.14%, respectively.

This study considers a downlink power consumption problem for unmanned aerial vehicles (UAVs)‐assisted wireless communications, in which UAVs are used as aerial base stations to provide service for the ground users and equipped with a directional antenna of fixed beamwidth. Moreover, the on‐board circuit power of UAV is taking into consideration. The authors derive a closed‐form expression for the optimal flying altitude and number of UAVs by minimising the total power consumption under the users' rate requirements in the given coverage area. The numerical simulation and theoretical results show that the optimal flying altitude of UAVs depends on the beamwidth of the directional antenna at UAVs, the on‐board circuit power of UAVs, and the rate constraint of each user.

In this paper, we propose a face super-resolution (FSR) method to handle the decreasing face recognition rate caused by low-quality images. To better model the input images, we build a nearest neighbor network (NNN) which consists of nodes and paths by introducing the second-layer nearest neighbors (SLNNs), where the paths of the network represent the distance between nodes. As the SLNN is trained in the high-resolution (HR) space and is exponentially supplementary to the traditional first-layer nearest neighbors (FLNNs), the neighbor inadequacy problem can be effectively solved by enriching the neighbor candidate set via NNN. Furthermore, we solve the NNN for the optimal weights of neighbors. Finally, we fuse the refined weights and neighbors for better reconstruction results. The effectiveness of this fusion strategy is validated by both quantitative and qualitative experimental results. The extensive experimental results on the public face datasets and real-world challenging low-resolution (LR) images demonstrate that the proposed method performs favorably against the state-of-the-art methods.

Because Face Super-Resolution (FSR) tends to infer High-Resolution (HR) face image by breaking the given Low- Resolution (LR) image into individual patches and inferring the HR correspondence one patch by one separately, Super- Resolution (SR) of face images with serious degradation, especially with occlusion, is still a challenging problem of the computer vision field. To address this problem, we propose a patch-level face model for FSR, which we called the position relation model. This model consists of the mapping relationships in every face position to the rest of the face positions based on similarity. In other words, we build a constraint for each patch position via the relationship in this model from the global range of face. Once an individual input LR image patch is seriously deteriorated, the substitute patch in whole face range can be sought according to the relationship of the model at this position as the provider of the LR information. In this way, the lost facial structures can be compensated by knowledge located in remote pixels or structure information which leads to better high-resolution face images. The LR images with degradations, not only the serious low-quality degradation, e.g. noise, blur, but also the occlusions, can be effectively hallucinated into HR ones. Quantitative and qualitative evaluations on the public datasets demonstrate that the proposed algorithm performs favorably against state-of-theart methods.

Software-defined networking (SDN) has been considered as a breakthrough progress for the next-generation LAN/WAN technologies. It enables fine-grained flow control that can make networks more customizable and flexible. However, the transition of traditional networking model to SDN architectures poses scalability issues due to the possible flow entry explosion in SDN switches. Typically, flow entries are removed from flow tables in three ways, either at the request of the controller, via the switch flow expiry mechanism, or via the optional switch eviction mechanism. No matter which one the network administrator choose, the invalid flow entries still keep on flow table for a while, thus unsalable due to available space of flow table are exhausted for future requests of continuous flow. In this paper, we propose to address this issue by detecting the disconnect signaling of connection-oriented protocols such as Transmission Control Protocol (TCP) for SDN framework. In particular, we propose to add a specific SDN ruleset with a transparent layer in between the controller and switch, referred to as a TCP FIN detector. TCP FIN detector inspects the FIN bit field from incoming and outgoings traffic; therefore once the transport-layer disconnection can be immediate recognized and no longer rely on timeout. Results of a series of simulations show that our proposed scheme outperforms timeout solutions for significant reduction of both the flow table occupancy and control signal costs.

In this paper, we propose enhanced Reed-Muller (RM) and Polar decoder for SDN-based C-RAN fronthaul. The simulation results show that our proposed algorithm outperforms traditional decoding algorithm in terms of average number of connected user equipment to RRHs, and the feasibility of decoding the RM codes by the Successive Cancellation (SC) decoding algorithm is verified by comparing the performance and decoding time of the RM and Polar codes under the SC and Belief Propagation (BP) iterative algorithm. The simulation results show that the decoding time of SC decoding algorithm is reduced about 98.98% compared with the BP decoding algorithm. For the BP decoding algorithm with excellent decoding performance but long decoding time, this paper proposes an improved BP decoding algorithm based on early terminating iteration criterion of the absolute values difference for the likelihood, which reduces the computational complexity of criterion. The simulation results illustrate that the early-terminating iteration criterion proposed in this paper reduces the computational complexity, thereby reducing the decoding delay and energy consumption effectively, and satisfying the low complexity and energy consumption decoding requirements.

Efficient data delivery in vehicular named data networks (VNDNs) can immensely enhance the safety and entertainment for drivers. For this purpose, in-network caching is used to expedite data delivery. In this work, a distributed probability-based caching with content-location-awareness (DPC-CLA) is proposed for efficient data delivery in VNDNs, where the roadside-units (RSUs) with caching capabilities can accurately access the relatively popular contents of the received packets by normalizing the reciprocal sum of the request hops in an indefinite period. In addition, the RSUs can also perceive the surrounding cache locations using the weighted recursive sum of the neighbouring cache intervals. Simulation results show that the proposed DPC-CLA performs better than four existing caching mechanisms in terms of the average number of hops and the cache hit ratio.

Millimeter wave is a promising technology for the next generation of wireless systems. As it is well-known for its high path loss, the systems working in this spectrum tend to exploit the shorter wavelength to equip the transceivers with a large number of antennas to overcome the path loss issue. The large number of antennas leads to large channel matrices and consequently a challenging channel estimation problem. The channel estimation algorithms that have been proposed so far either neglect the probability of estimation error or require a high feedback overload from receivers to ensure the target probability of estimation error. In this paper, we propose a multi-stage adaptive channel estimation algorithm called robust adaptive multi-feedback (RAF). The algorithm is based on using the estimated channel coefficient to predict a lower bound for the required number of measurements. Our simulations demonstrate that compared with existing algorithms, RAF can achieve the desired probability of estimation error while on average reducing the feedback overhead by 75.5% and the total channel estimation time by 14%.

In this paper, we conduct performance analysis for uplink (UL) massive multiple input and multiple output (mMI-MO) networks using stochastic geometry. With the consideration of practical system assumptions, such as sophisticated path loss model incorporating both line-of-sight (LoS) and non-line-of-sight (NLoS) transmissions and a finite user equipment (UE) density, we derive the coverage probability and the area spectral efficiency (ASE) performance. In particular, we adopt a practical user association strategy (UAS) based on the smallest pathloss since we differentiate LoS and NLoS transmissions, and we consider the correlation among the positions of UEs and base stations (BSs) in realistic networks. From our simulation and analytical results, we find that the performance impacts of the probabilistic LoS/NLoS transmissions and a finite UE density on UL mMIMO networks are significant. More specifically, the coverage probability performance suffers from a moderate decrease or even a severe degradation when the UE density becomes large in sparse mMIMO networks. Moreover, our results indicate that there exists an optimal BS density to maximize the sum spectral efficiency per BS. However, the ASE performance keeps growing with network densification.

In this study, the design of an adaptive medium access control (MAC) protocol based on the space‐division–time‐division multiple access (SD‐TDMA) mechanism is presented to improve the utilisation and fairness of the time‐slot allocation scheme in the vehicular ad hoc network. The SD‐TDMA mechanism dynamically allocates time‐slots owing to a dynamic topology. This protocol reduces transmission collisions through user detection procedures. Most users can thus access the service channel (SCH) without conflict and acquire time slots according to the mapping between geographic locations and time slots. Users failing to access the channel in user detection procedures can send request access packets in security channels to again participate in SCH time‐slot allocation during the SCH interval. Simulations are conducted to evaluate the performance of the proposed method in urban scenarios. The SD‐TDMA mechanism is compared with an SDMA‐based MAC protocol, the IEEE 802.11p distributed coordination function and an MAC protocol based on transmission sequences. Owing to the decreased rate of transmission collisions and the dynamic time‐slot allocation scheme, it is shown that the SD‐TDMA mechanism provides a significantly higher utilisation of time slots and better fairness of data transmission than existing approaches.

Unmanned aerial vehicle (UAV)-satellite communication has drawn dramatic attention for its potential to build the integrated space-air-ground network and the seamless wide-area coverage. A key challenge to UAV-satellite communication is its unstable beam pointing due to the UAV navigation, which is a typical SatCom on-the-move scenario. In this paper, we propose a blind beam tracking approach for Ka-band UAV-satellite communication system, where UAV is equipped with a hybrid large-scale antenna array. The effects of UAV navigation are firstly released through the mechanical adjustment, which could approximately point the beam towards the target satellite through beam stabilization and dynamic isolation. Specially, the attitude information for mechanical adjustment can be realtimely derived from data fusion of low-cost sensors. Then, the precision of beam pointing is blindly refined through electrically adjusting the weight of the massive antennas, where an array structure based simultaneous perturbation algorithm is designed. Simulation results are provided to demonstrate the superiority of the proposed method over the existing ones.

This paper considers a downlink single-cell non-orthogonal multiple access (NOMA) network, where the base station, which has multiple antennas, broadcasts the mixed multicast and unicast messages to multiple users with a single antenna. We propose two types of power allocation schemes for NOMA networks with multicast-unicast transmission to investigate the impact of performance, namely, cognitive radio inspired NOMA with dynamic quality of service (QoS) at multicast users (CR-NOMA-D-M), and CR-NOMA constrains the dynamic QoS at the unicast user (CR-NOMA-D-U). Based on the proposed schemes, we drive the exact/closed-form expressions for the secrecy outage probability, outage probability, as well as the approximate outage probability at high signal-to-noise ratio to study the diversity gain. Compared with existing works, the derived analytical results show that both proposed schemes cannot only significantly improve the outage performance for multicast users, but also remarkably enhance the diversity gain and the secrecy outage probability for the unicast user. Finally, the theoretical results are validated by the numerical results.

This paper presents an optimal roadside unit (RSU) placement method for vehicle localization in Vehicle Ad-hoc Networks (VANETs). Since the RSU layout can significantly affect the performance of localization algorithms, the proposed method needs to find an optimal K-coverage RSU placement, to ensure the best localization accuracy while using minimum number of RSUs. We adopt the Geometric Dilution of Precision (GDOP) metric to evaluate the accuracy provided by RSU placements, and derive the expression of GDOP towards received signal strength (RSS) and hybrid parameter estimators, respectively. There are two steps contained in the proposed method. Firstly, the optimal elementary pattern is obtained and applied to form the 1-coverage placement. Secondly, the optimal K-coverage placement based on K-layer elementary patterns is found by minimizing the average GDOP of the road area, using asynchronous particle swarm optimization (APSO) algorithm. In simulations the convergence and stability of APSO solutions are verified, then our method is compared with existing uniform placement method, the results show that the proposed method can achieve better positioning performance.

In this paper, we propose a weighted cooperative localization algorithm with the ability to mitigate non-line-of-sight (NLOS) propagations in wireless networks. The link condition indicator (LCI) for each connection is calculated based on the amplitude and delay statistics of channel responses. We partition the ambiguity of link condition into N levels according to the LCI values. With the distance-dependent LOS/NLOS probability suggested by the 3rd Generation Partnership Project (3GPP), the relationship between LOS/NLOS probability and the time-of-arrival (TOA) of inter-node signal transmission is derived. We incorporate this probability into N-level LCI range regions and propose the N probabilistic hard weight (N-PHW) strategy for the cooperative localization, which penalizes the NLOS-induced positive biases by weighting the belief terms introduced by the conventional cooperative localization algorithm, the sum-product algorithm over a wireless network (SPAWN). Simulation results show that the proposed weighted algorithm significantly improves the localization performance in terms of localization accuracy, especially in serious NLOS environments.

This paper presents a vehicle positioning method based on joint estimation of time of arrival (TOA) and direction of arrival (DOA) with Vehicle-to-Roadside (V2R) communications. By analyzing the measured channel frequency response (CFR) between vehicles and the roadside unit (RU), the enhanced two-dimensional matrix pencil (2-D MP) algorithm is implemented to design the parameter estimator, which has lower complexity without forming a covariance matrix. The position coordinates of vehicles can then be calculated from the estimates. To improve the positioning accuracy, the extended Kalman filtering (EKF) is further introduced for mitigating the noise influence and estimating error. Simulation results show that the proposed method can achieve better positioning estimation compared with the Global Positioning System (GPS) and inertial navigation systems (INS) fusion method.

Protocol sequences offer a promising alternative for media access control of mobile ad hoc networks, because they do not require any coordination among the users nor any centralized synchronization. We show that by using suitably designed deterministic scheduling, the delay performance can indeed be much better than using random and pseudo-random sequences. The reported results indicate that protocol sequences can offer practical solutions to complicated multiple-access problems in ad hoc networks, such as vehicular ad hoc networks (VANET). The cumulative distribution function of delay and an upper bound of the individual delay in the cases of protocol sequences are derived.