While machine learning (ML) has been explored for beam prediction, many methods remain constrained by single-modality inputs, shallow temporal modeling, and limited robustness to interference and domain shift. We introduce Multimodal Semantic-Enhanced Real-World Beam Prediction via Temporal Modeling with Visual Foundation Models (MSET), a multimodal framework that couples visual semantics with positional priors in a causal, lightweight design. A visual foundation model (VFM), instantiated as a Swin-Transformer, learns rich spatial and semantic cues from RGB images and Segment Anything Model (SAM)-derived region masks, and a lightweight ResNet-18 student distills this knowledge for efficient inference. Short-horizon dynamics are captured by a causal Temporal Convolutional Network (TCN) with an adaptive receptive field, whose volatility-driven depth gate expands context under motion spikes and contracts it in calm periods. On top of semantic-aware frame embeddings, a Temporally Aware Cross-Attention (TACA) aligns original and semantic-enhanced tokens, while a Mambaconditioned GPS prior, implemented via a selective state-space model (SSM), issues a location-conditioned single query with positional bias to attend the fused tokens. We further extend inference to dense deployments with multiple proximate candidates and address target selection under ambiguity. Experiments on DeepSense 6G dataset show consistent Top-k improvements across single/multi-target and day/night scenarios, indicating reduced sweep reliance and strong generalization under realistic V2I dynamics.

With the emergence of distributed machine learning, federated learning has become a prevalent paradigm for multi-party collaborative training scenarios. To address security vulnerabilities such as imperfect encryption and incapability to with-stand attacks within existing federated learning architectures, a blockchain-based trustworthy federated learning architecture is proposed. The architecture utilizes a threshold variant of the Paillier encryption scheme to protect the local and global model updates. A flexible Multi-Krum selection scheme is also proposed for balancing the utility of the overall architecture while ensuring safe federated learning training processes. Based on theoretical analysis and experimental results, the proposed architecture demonstrates a high level of security and the feasibility of the scheme is supported.

Abstract Millimeter‐wave (mmWave) multi‐input multi‐output systems, affected by atmospheric conditions and hardware failure, are vulnerable to antenna element blockages and failures. The authors consider the hybrid beamforming (HBF) optimization problem for systems with impaired elements to approximate the performance of a fault‐free system. Especially, the impaired coefficient of elements is estimated rather than simply assuming it is completely invalid. Firstly, to ensure that radiation power is within the desired angle, the impaired coefficients are estimated and the beamforming vector basis is designed. Then, by using the derived basis and semidefinite relaxation (SDR) technique, a minimax optimization problem is solved to smooth the passband response. Finally, a hybrid decomposition is conducted to be compatible with HBF structures. Numerical results indicate that the proposed algorithm improves the average data rate of the mmWave system with three impaired elements by about 40%, which is almost 93% of the performance of a fault‐free system.

Abstract Line‐of‐sight (LOS)/non‐line‐of‐sight (NLOS) identification is crucial for millimetre‐wave (mmW) since it is vulnerable to blocking in the NLOS environment. In this paper, an LOS/NLOS environment identification method is proposed based on angle information learning. Specifically, a neural network named ALNN (angle information learning neural network) is employed, which can learn the difference between the various angle paraments to identify the LOS and NLOS environments for mmW wireless communication systems. First, the 3D mmW channel model is applied to extract the desired angle information. Moreover, an mmW wireless transmission system is constructed to introduce actual measurement data to test the proposed method. Furthermore, various hyperparameters of the ALNN are adjusted to improve identification accuracy. Simulation results show that the proposed method has outstanding identification performance, and the identification accuracy is up to 99.41%.

Abstract Here, the beamforming design for multiuser multiple‐input and multiple‐output (MIMO) downlink transmission aided by an intelligent reflecting surface (IRS) with discrete phase shifts is studied. The authors deduce a minimum signal‐to‐interference‐plus‐noise‐ratio (SINR) maximization fairness problem with the transmit beamformer, the receive beamformer and IRS phase shifts as optimization variables, which is generally NP‐hard. Hence, an alternating optimization algorithm based on the gradient extrapolated majorization‐minimization (GEMM) approach is employed to solve the above problem. Specifically, when the transmit beamformer and reflective phase shift are fixed, the authors give an optimal closed expression for the receive beamformer. Then, the receive beamformer is fixed, and the minimum SINR maximization problem at the transmitter is transformed into a power minimization problem. Finally, under the zero‐forcing (ZF) transmitter beamformer, the GEMM algorithm is used to optimize the reflective phase shift. Simulation results show that by comparing to existing methods, the proposed GEMM algorithm can almost achieve the same performance with lower complexity.

Due to the ultra-dense deployment of small cells in 5G millimeter wave (mmWave) backhaul networks, the consumed energy of transmitting data flows will increase significantly. In this paper, we propose an energy-saving scheme for the mmWave backhaul networks to minimize the energy consumption with the throughput requirements and data flows transmitting order satisfied. In the scheme, based on the concurrent transmission, the Space/Time- Division Multiple Access (STDMA) groups are established and the Joint Time Allocation and Power Control (JTAPC) algorithm is proposed to achieve low energy consumption. Besides, the transmission order for the multi-hop backhaul networks is considered by designing a status indicator. Simulations in the 60 GHz band are conducted to demonstrate the superior performance of our algorithm in energy consumption and system throughput.

Millimeter wave backhaul (mmW BH) network has attracted the great interest of both academia and industry for providing high capacity, low cost and easy installation. In this regard, we formulate a dynamic spectrum allocation optimization problem for mmW BH network, which maximizes the spectrum efficiency of the network and characterizes the associated traffic demand of each small cell base station (SBS). To solve the problem, a spectrum allocation algorithm based on matching game (SAMG) is proposed, which yields a two-sided stable and Pareto optimal matching between the sub-channels and SBSs. Simulations show that our SAMG algorithm can effectively improve the spectrum efficiency of the mmW BH network, with the dynamic traffic demand of each SBS satisfied.

With hybrid access model in heterogeneous networks (HetNets), a capacity efficient resource allocation strategy is proposed in this paper. Combining with millimeter wave (mmWave) and Sub-6GHz, we divide the optimization of system capacity into two Sub- optimization problems. Firstly, this paper proposes a resource allocation algorithm based on the maximum interference free group (MIFG) for the users in mmWave Pico BS (PBS). The capacity of each PBS is maximized by grouping users and maximizing the utilization of resource block (RB). Secondly, to ensure the service quality of users in Macro BS (MBS), a twostage QoS guaranteed greedy pair (TQGP) algorithm is proposed in this paper. Simulation results indicate that the proposed capacity efficient resource allocation strategy can improve the system capacity with user QoS guaranteed.

Hybrid beamforming (HBF) has been widely accepted to offer a compromise between cost and system performance in millimeter wave (mmWave) systems, while its performance is highly dependent on the corresponding computation complexity. Using an assumption of orthogonal constraint and phase extraction, an effective HBF algorithm is presented in this paper, which consists of a digital beamformer (DBF) stage and an analog beamformer (ABF) stage. Firstly, the optimal DBF with orthogonal constraint is derived for a given RF beamformer. Secondly, when the orthogonal property of the digital beamformer is enabled, the analog beamformer can be developed by extracting the phases of the unconstraint solution of the optimization in RF domain. Specifically, we consider the case of that the number of RF chains is equal to the number of data streams, which can further improve the energy efficiency of mmWave systems. Simulation results show that our proposed algorithm can effectively approach the full digital beamformer performance limit.

The rapid development of wireless communication comes at the cost of dramatically increasing energy consumption, which makes the optimisation of energy efficiency (EE) extremely important. In this study, the authors focus on maximising EE of large‐scale multiple‐input–multiple‐output system by optimising the transmit power and the number of selected base station antennas. First, the EE optimisation problem, i.e. finding the optimal EE‐based values of each parameter, when the other one is fixed, is investigated. Then, the optimisation problem jointly considering these two parameters to maximise EE is studied. Moreover, the EE optimisation problem is extended to multi‐user (MU) system. Owing to the formulation of EE, the EE optimisation problem is reformulated as the fractional programming problem, and the Dinkelbach method is proposed to deal with this problem instead of the binary search algorithm (BSA) by switching the objective function to a weighted sum of rate and power. Simulation results show that the EE can be improved with the proposed Dinkelbach method, and it has a faster convergence speed than the BSA without any performance loss for both single‐user system and MU system.

Indoor localisation could benefit greatly from non‐line‐of‐sight (NLOS) identification and mitigation, since the major challenge for WiFi indoor ranging‐based localisation technologies is multipath and NLOS. NLOS identification and mitigation on commodity WiFi devices, however, are challenges due to limited bandwidth and coarse multipath resolution with mere MAC layer received signal strength index. In this study, the authors explore and exploit the finer‐grained PHY layer channel state information (CSI) to identify and mitigate NLOS. Key to the authors’ approach is exploiting several statistical features of CSI, which are proved to be particularly effective. The approaches, NLOS identification support vector machine (NISVM) and related channel information regression model (RCIRM), based on machine learning are proposed to identify NLOS and mitigate NLOS error, respectively. Experiment results in various indoor scenarios with severe interferences demonstrated an overall NLOS identification rate of 94.12% with a false alarm rate of 5.88% and a better mitigation performance.

Due to the high cost and power consumption, it is impractical to perform full‐digital beamforming at baseband in millimetre‐wave systems. Thus, as a cost‐effective alternative, a hybrid beamforming (HBF) is introduced in this study. Since the HBF can be designed as a matrix factorisation problem, an effective greedy algorithm with low complexity for multiuser scenes is proposed to approach the full‐digital matrix. Firstly, initialisation for partial columns of the analogue matrix is enabled by extracting the phases of the full‐digital scheme. Then the singular value decomposition in low‐dimension matrix can be used to obtain the rest columns of the analogue matrix. Finally, based on effective channel, the digital matrix can be easily designed. Therefore, the authors' proposed algorithm has low complexity and only needs fewer iterations. Furthermore, by handling the inter‐user interference, the full‐digital matrix needed for the initialisation in analogue domain can be approximated to an orthogonal matrix, which can further reduce computational complexity. Simulation results demonstrate that the proposed greedy algorithm performs very close to the optimal unconstrained solution and enjoys low complexity.

The cooperative spectrum sensing techniques in cognitive radio networks increase the energy consumption while improving the throughput of the system. The energy efficient techniques with sensing time optimization are considered in this paper. The optimization model is established, in which the sensing time is to be optimized to maximize the energy efficiency. Then, the golden section search algorithm is used to get the optimal solution based on the proof that energy efficiency is a unimodal function in terms of sensing time. The initial value of the golden section search algorithm is given, and the optimal value is obtained by iteration. Simulation results show that the energy efficiency can be improved obviously by optimizing sensing time.

In this paper, a linear Channel Orthogonalization (CO) algorithm with low complexity is presented, which is applicable to systems with an arbitrary number of antennas and users. Unlike other conventional linear methods, CO obtains the orthonormal basis to achieve the precoding matrix by means of using Schmidt Orthogonalization method. Then, the algorithm (CO-THP) combining CO with Tomlinson-Harashima Precoding (THP) is proposed to eliminate the residual interference from any former user in CO. Different from the conventional THP algorithms, CO-THP eliminates all the Multi-User Interference (MUI) without amplifying the noise, which brings it better BER performance. And the combination with THP brings CO a higher capacity than linear scheme BD. Simulation results show the performance advantage obtained by the CO and CO-THP.

This paper presents a novel reduced-complexity channel estimator for Coordinated Multi-point (CoMP) multi-user systems. The proposed scheme is based on Space Alternating Generalized-EM (SAGE) algorithm combining with the Least Square (LS) criterion. Aiming at the problem that the conventional joint multi-user LS estimator introduces the complex inversion of large size matrix when using non-orthogonal pilots, the proposed estimator avoids the inverse operation by transforming the joint multi-user estimation into a series of single-user estimating process in an iterative way. Simulation results verify that the proposed algorithm obtain huge complexity reduction, while achieving the optimal performance of joint LS channel estimation for the CoMP systems.

In order to provide an increased capacity, throughput and QoS guarantee for terrestrial users in emergency scenarios, a low-medium-altitude aerial platform based time-division-duplex long term evolution (TD-LTE) system referred to as Aerial LTE, is presented in this paper. Additionally a power-efficient radio resource allocation mechanism is proposed for both the Aerial LTE downlink and uplink, which is modeled as a cooperative game. Our simulation results demonstrate that the proposed algorithm imposes an attractive tradeoff between the achievable throughput and the power consumption while ensuring fairness among users.

A novel decomposed transceiver design scheme is developed for multiuser non-regenerative MIMO relay downlink systems. With a decomposed relay structure, the whole system can be decomposed into a point-to-point and a point-to-multipoint systems, thus the transceiver design can be individually proceeded for the first and second hop. In the first hop, the transceiver is derived to minimize the mean square error (MSE) of symbol estimations with equal MSEs of all data streams. While for the second hop, a modified block diagonalization (BD) and geometric mean decomposition (GMD) based scheme is proposed to design the transceiver. Simulation results demonstrate the proposed method can effectively improve the BER performance.

The rapid growth of wireless networks makes cognitive coexistence an important technology to use the spectrum efficiently. In this paper, a novel sensing based delay optimal method is considered to meet the requirement of the delay-sensitive traffics as well as to minimize the collision between the primary user and the secondary user. After establishing the Markov Decision Process (MDP) model, we proposed a spectrum access policy using EXP-LOG rule, in which the transmission probability is determined by the sensing result and queue state information. The simulation results verify the validity and feasibility of the proposed policy.

In this paper, we focus on the performance analysis of the cognitive coexistence between Bluetooth and WLAN systems with sensing errors. The packet transmission rate and packet error probability are derived corresponding to the sensor operating points (consisting of the false alarm probability and the miss detection probability). Then, the optimization problem is established as maximizing the throughput of cognitive user with the constraint of the colliding probability with primary user. Simulation results illustrate that the proposed error analysis approach can obtain the optimal performance when considering the sensing errors. Moreover, the influence on the throughput of cognitive user caused by different sensor operating points is investigated by simulation.

In this paper, a low complexity Modified QRD-M (MQRD-M) algorithm based on limited tree search is proposed for MIMO systems. The sphere radius and candidate set of each branch are considered to reduce the computational complexity. The sphere radius is efficiently acquired through the QRD detection based on pruning off unnecessary survival branches at each layer. Moreover, the candidate set of each branch is used to cut down the metric computation for it is much smaller than modulation set. Simulation results show that the proposed MQRD-M algorithm can achieve near-MLD performance and its average metric computation is lower than conventional QRD-M algorithms.

This article proposes a new space time cooperative diversity scheme called full feedback-based cooperative diversity scheme (FFBCD). In contrast to the conventional adaptive space time cooperative diversity schemes which utilize the feedback from only the destination node, the new scheme utilizes the feedback from both the destination node and the cooperation node. With the feedback from the destination node, the occasional successful reception of the destination node in the information distribution stage can be detected, and so to avoid unnecessary retransmissions in the information delivery stage. The feedback from the cooperation node indicates the receive state of the cooperation node in the information distribution stage, and the source node and the cooperation node won’t perform cooperative retransmission during the information delivery stage unless the cooperation node received successfully in the information distribution stage. In this way the new scheme can reduce the number of transmission attempt and improve the channel utilization. The expressions of the average number of transmission attempt are given. Numerical approximations and simulation results both show that the new scheme performs better than the non-cooperative scheme and the conventional adaptive space time cooperative diversity scheme.

A new grouping strategy based on particle swarm optimization (PSO) is proposed for the multiuser MIMO broadcast systems in this paper. Aiming at maximizing the system capacity, the PSO algorithm is introduced to seek the best users group. Besides, two objective functions in PSO applicable for the cases of different requirements on capacity and complexity are also presented, which can be denoted as PSO_I algorithm and PSO_II algorithm respectively. Simulation results reveal that the PSO_I strategy achieves nearly the same capacity performance to the optimal exhaustive search (ES) algorithm, and the PSO_II algorithm is slightly worse than PSO_I algorithm in terms of capacity performance, but with lower complexity.

In this paper, a novel scheduling strategy based on particle swarm optimization (PSO) algorithm is proposed for the downlink of multiuser MIMO systems. By means of PSO searching mechanism, this scheduling algorithm mainly seeks the optimal "particle", i.e. the best scheduled user group, to maximize the system capacity. Besides, a new approach to associate the possible scheduled candidates by "particles" in PSO is also presented. Simulation results reveal that the proposed PSO strategy achieves nearly the same performance to the exhaustive search (ES) algorithm in terms of capacity performance, but with lower complexity. The convergence analysis is also presented to give a guideline in determining the parameters to keep the PSO convergent.

Based on the cross-layer design, a novel resource allocation algorithm for multi-user Orthogonal Frequency Division Multiplexing (OFDM) system is presented in this paper. The algorithm allocates the resource by considering not only the Channel State Information (CSI), but also the Quality of Service (QoS) requirement of the users, including the delay and the throughput. The performance of the algorithm has been verified by theoretical analysis and simulations. The results demonstrate that, using the algorithm, the spectral efficiency can approach to the achievable capacity obtained by the water-filling algorithm under the fairness constrain among the users.

This paper begins with the investigation of the adaptive technologies for high speed WLAN (Wireless local Area Network) systems. A system model of MIMO (Multi-Input Multi-Output) OFDM (Orthogonal Frequency Division Multiplexing) WLAN is built, on the basis of which, a novel modulation scheme with adaptive margin is proposed. With the simulation results, we can see that the proposed algorithm can improve the BER (Bit Error Rate) character over different channel environments, such as the quasistatic channel, the multi-path channel and the MIMO correlation channel.

In this paper, we propose a novel scheduling architecture for IEEE 802.16 broadband wireless access network. Based on the WFQ and WF2Q which play an important role in wired network, we do more deeply research in how integrate these algorithm into IEEE 802.16. Then, a QoS architecture with WFQ algorithm is proposed. A model for our new scheduling structure is built, and the simulations are given. The results show that the delay character is improved using the proposed architecture with the new WFQ algorithm.

The focus of this paper is on a secure mobile commerce model based on wireless local area network (WLAN). The model is investigated through the accessing procedure, the roaming management procedure, and the electronic trade procedure. To solve the security problem in the WLAN, a novel authentication method is proposed, in which the mobile node (MN) is validated twice by an access point (AP) and a mobile agent (MA), and all the devices are authenticated in a register procedure with the PKI/CA mechanism. Finally, the advantages of the model are analyzed.