Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3657504
Fabian Jaensch;Giuseppe Caire;Begüm Demir
In 5G, beam training consists of the efficient association of users to beams for a given beamforming codebook used at the base station and the given propagation environment in the cell. We propose a convolutional neural network approach that leverages the position of the base station and geospatial data to predict beam distributions for all user locations simultaneously. Our method generalizes to unseen environments without site-specific training or specialized sensors. The results show that it significantly reduces the number of candidate beams considered, thereby improving the efficiency of beam training.
{"title":"Beam Index Map Prediction in Unseen Environments From Geospatial Data","authors":"Fabian Jaensch;Giuseppe Caire;Begüm Demir","doi":"10.1109/LWC.2026.3657504","DOIUrl":"10.1109/LWC.2026.3657504","url":null,"abstract":"In 5G, beam training consists of the efficient association of users to beams for a given beamforming codebook used at the base station and the given propagation environment in the cell. We propose a convolutional neural network approach that leverages the position of the base station and geospatial data to predict beam distributions for all user locations simultaneously. Our method generalizes to unseen environments without site-specific training or specialized sensors. The results show that it significantly reduces the number of candidate beams considered, thereby improving the efficiency of beam training.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1519-1523"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11363011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3657385
Zhen Wen;Haiyang Ding;Shilian Wang;Guoxi Song;Chenglin Feng;Jules M. Moualeu;Maged Elkashlan;Chau Yuen
This letter proposes several constellation integration schemes for a simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) enabled symbiotic backscatter system to achieve a 360° merging transmission, which include the bistatic scheme, the uniquely factorable constellation pair (UFCP) scheme, and the non-orthogonal multiple access (NOMA)-UFCP scheme. To begin with, we design the detectors of the proposed schemes and derive the closed-form expressions of the symbol error rate (SER) and throughput of the underlying system. Then, an algorithm for solving the optimal reflection and transmission coefficients is subsequently designed to maximize the system achievable performance. Finally, numerical results show that the throughput performance of the proposed Bistatic, UFCP, and NOMA-UFCP schemes outperform the corresponding benchmarks over the entire signal-to-noise ratio region.
{"title":"360° Merging Coverage: A STAR-RIS-Enabled Symbiotic Backscatter System With Constellation Integration Schemes","authors":"Zhen Wen;Haiyang Ding;Shilian Wang;Guoxi Song;Chenglin Feng;Jules M. Moualeu;Maged Elkashlan;Chau Yuen","doi":"10.1109/LWC.2026.3657385","DOIUrl":"10.1109/LWC.2026.3657385","url":null,"abstract":"This letter proposes several constellation integration schemes for a simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) enabled symbiotic backscatter system to achieve a 360° merging transmission, which include the bistatic scheme, the uniquely factorable constellation pair (UFCP) scheme, and the non-orthogonal multiple access (NOMA)-UFCP scheme. To begin with, we design the detectors of the proposed schemes and derive the closed-form expressions of the symbol error rate (SER) and throughput of the underlying system. Then, an algorithm for solving the optimal reflection and transmission coefficients is subsequently designed to maximize the system achievable performance. Finally, numerical results show that the throughput performance of the proposed Bistatic, UFCP, and NOMA-UFCP schemes outperform the corresponding benchmarks over the entire signal-to-noise ratio region.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1538-1542"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3657319
Shiguo Wang;Bin Li;Xiukai Ruan;Qingyong Deng
Pilot spoofing attacks pose a severe threat to the security and reliability of massive multiple-input multiple-output (MIMO) communication systems by compromising the accuracy of channel estimation. To address this issue, two complementary physical-layer features, namely the pilot power ratio (PPR) and the eigenvalues of the covariance matrix of the received signals, are fused effectively, and then support vector machine (SVM) and deep neural network (DNN) are constructed to distinguish the legitimate from the spoofing pilot signals, respectively. Comprehensive simulations demonstrate that the proposed scheme with dual-feature fusion technique can significantly enhance detection accuracy compared to single-feature approaches under both the scenarios of synchronous and asynchronous attack. Meanwhile, its high performance in robustness is also validated by varying attack power and the size of dataset.
{"title":"Pilot Spoofing Detection for Massive MIMO Systems Based on Dual-feature Fusion","authors":"Shiguo Wang;Bin Li;Xiukai Ruan;Qingyong Deng","doi":"10.1109/LWC.2026.3657319","DOIUrl":"10.1109/LWC.2026.3657319","url":null,"abstract":"Pilot spoofing attacks pose a severe threat to the security and reliability of massive multiple-input multiple-output (MIMO) communication systems by compromising the accuracy of channel estimation. To address this issue, two complementary physical-layer features, namely the pilot power ratio (PPR) and the eigenvalues of the covariance matrix of the received signals, are fused effectively, and then support vector machine (SVM) and deep neural network (DNN) are constructed to distinguish the legitimate from the spoofing pilot signals, respectively. Comprehensive simulations demonstrate that the proposed scheme with dual-feature fusion technique can significantly enhance detection accuracy compared to single-feature approaches under both the scenarios of synchronous and asynchronous attack. Meanwhile, its high performance in robustness is also validated by varying attack power and the size of dataset.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1548-1552"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3656528
Kang Wei;Guangji Chen;Yan Hong;Long Shi;Feng Shu
Graph neural networks (GNNs) over the air (AirGNNs) has shown significant potential for efficiently training distributed GNN models by aggregating the feature representations based on the over the air computation (AirComp) technique. However, devices in existing wireless systems operate in half-duplex mode, the collision issue that devices cannot transmit and receive simultaneously may limit the potential of AirGNNs. To tackle this challenge, we proposed two scheduling methods, i.e., collision-aware graph division (CAGD) and interference-aware graph division (IAGD), which can achieve collision avoidance and interference control, respectively. Furthermore, we derive the convergence bound of AirGNNs that reveals the following three key properties: 1) the convergence bound is a function of the accumulated transmission errors of all devices; 2) there is an optimal transmit power for each device in terms of training performance; and 3) there is a fundamental tradeoff between training performance and transmission efficiency. Extensive experimental results on real-world datasets validate the effectiveness of our proposed methods and insights in the theoretical results.
{"title":"Graph Neural Networks via AirComp: Algorithms and Performance Analysis","authors":"Kang Wei;Guangji Chen;Yan Hong;Long Shi;Feng Shu","doi":"10.1109/LWC.2026.3656528","DOIUrl":"10.1109/LWC.2026.3656528","url":null,"abstract":"Graph neural networks (GNNs) over the air (AirGNNs) has shown significant potential for efficiently training distributed GNN models by aggregating the feature representations based on the over the air computation (AirComp) technique. However, devices in existing wireless systems operate in half-duplex mode, the collision issue that devices cannot transmit and receive simultaneously may limit the potential of AirGNNs. To tackle this challenge, we proposed two scheduling methods, i.e., collision-aware graph division (CAGD) and interference-aware graph division (IAGD), which can achieve collision avoidance and interference control, respectively. Furthermore, we derive the convergence bound of AirGNNs that reveals the following three key properties: 1) the convergence bound is a function of the accumulated transmission errors of all devices; 2) there is an optimal transmit power for each device in terms of training performance; and 3) there is a fundamental tradeoff between training performance and transmission efficiency. Extensive experimental results on real-world datasets validate the effectiveness of our proposed methods and insights in the theoretical results.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1499-1503"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3656966
Jiujia Yin;Xilong Liu;Nirwan Ansari;Kun Yue
With the rapid development of sixth-generation (6G) mobile communications, high-mobility scenarios are drawing attention, as Doppler shifts significantly impair reliable transmission. Orthogonal time frequency space (OTFS) modulation has emerged, owing to its robustness against Doppler effects. However, even with OTFS, rapidly varying channel state information continues to pose a major challenge for accurate channel estimation, as Doppler spread introduces severe time and frequency selectivity. Thus, we propose an attention-enhanced bidirectional long short-term memory (BiLSTM) network that leverages pilot features to perform accurate channel estimation, thereby ensuring reliable transmission in high-mobility environments. Extensive simulations validate the effectiveness of the proposed network.
{"title":"Attention-Enhanced BiLSTM Network for Accurate Channel Estimation in High-Mobility OTFS Communications","authors":"Jiujia Yin;Xilong Liu;Nirwan Ansari;Kun Yue","doi":"10.1109/LWC.2026.3656966","DOIUrl":"10.1109/LWC.2026.3656966","url":null,"abstract":"With the rapid development of sixth-generation (6G) mobile communications, high-mobility scenarios are drawing attention, as Doppler shifts significantly impair reliable transmission. Orthogonal time frequency space (OTFS) modulation has emerged, owing to its robustness against Doppler effects. However, even with OTFS, rapidly varying channel state information continues to pose a major challenge for accurate channel estimation, as Doppler spread introduces severe time and frequency selectivity. Thus, we propose an attention-enhanced bidirectional long short-term memory (BiLSTM) network that leverages pilot features to perform accurate channel estimation, thereby ensuring reliable transmission in high-mobility environments. Extensive simulations validate the effectiveness of the proposed network.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1529-1533"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/lwc.2026.3656740
Aleksey S. Gvozdarev
{"title":"IRS Compensation of Hyper-Rayleigh Fading: How Many Elements Are Needed?","authors":"Aleksey S. Gvozdarev","doi":"10.1109/lwc.2026.3656740","DOIUrl":"https://doi.org/10.1109/lwc.2026.3656740","url":null,"abstract":"","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"287 1","pages":""},"PeriodicalIF":6.3,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3657598
Ping Cao;Wei Wang;Yiliang Liu;Zou Su
Distributed spectrum allocation for large-scale UAV swarm remains a challenging issue, due to spectrum allocation collisions and the high communication overhead required to reach consensus. To address these challenges, we propose a lightweight consensus protocol for distributed collision-free spectrum allocation (LCCFSA), where UAV nodes in the swarm form a blockchain and spectrum allocation consensus is reached on the chain. Specifically, a fast low-complexity allocation scheme is developed for each UAV based on an interference graph, where each UAV adaptively adjusts its occupancy area to avoid mutual interference. To further reduce the consensus overhead, we design a lightweight consensus protocol with a transaction-based blockchain ledger and provide a formal security analysis of the proposed protocol. A prototype is built to validate the feasibility of the proposed scheme. Simulation results show that the average consensus latency can be reduced by more than 20% in scenarios with 100 consensus nodes.
{"title":"A Lightweight Consensus Protocol for Distributed Collision-Free Spectrum Allocation","authors":"Ping Cao;Wei Wang;Yiliang Liu;Zou Su","doi":"10.1109/LWC.2026.3657598","DOIUrl":"10.1109/LWC.2026.3657598","url":null,"abstract":"Distributed spectrum allocation for large-scale UAV swarm remains a challenging issue, due to spectrum allocation collisions and the high communication overhead required to reach consensus. To address these challenges, we propose a lightweight consensus protocol for distributed collision-free spectrum allocation (LCCFSA), where UAV nodes in the swarm form a blockchain and spectrum allocation consensus is reached on the chain. Specifically, a fast low-complexity allocation scheme is developed for each UAV based on an interference graph, where each UAV adaptively adjusts its occupancy area to avoid mutual interference. To further reduce the consensus overhead, we design a lightweight consensus protocol with a transaction-based blockchain ledger and provide a formal security analysis of the proposed protocol. A prototype is built to validate the feasibility of the proposed scheme. Simulation results show that the average consensus latency can be reduced by more than 20% in scenarios with 100 consensus nodes.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1553-1557"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/LWC.2026.3656548
Peng Wu;Xiaopeng Yuan;Yulin Hu;Anke Schmeink
In this letter, we investigate the timeliness of an unmanned aerial vehicle (UAV)-enabled covert and secure communication network, where a novel metric, i.e., covert and secure age of information (C&S AoI), is proposed to capture the relationship between the information freshness and communication security. We first analyze the covert and secure communication performance on account of location uncertainty of warden, which leads to characterization on the expression of C&S AoI. Then, we formulate a joint UAV position, transmit power and blocklength design problem to minimize the C&S AoI. To solve the complicated problem, an efficient iterative algorithm based on optimal solution analysis and a novel convex approximation is developed for obtaining a high-quality solution. Simulations demonstrate the superior performance of proposed algorithm in improving C&S AoI performance of delay sensitive networks compared with benchmark.
{"title":"Age of Information for UAV-Enabled Covert and Secure Communication","authors":"Peng Wu;Xiaopeng Yuan;Yulin Hu;Anke Schmeink","doi":"10.1109/LWC.2026.3656548","DOIUrl":"10.1109/LWC.2026.3656548","url":null,"abstract":"In this letter, we investigate the timeliness of an unmanned aerial vehicle (UAV)-enabled covert and secure communication network, where a novel metric, i.e., covert and secure age of information (C&S AoI), is proposed to capture the relationship between the information freshness and communication security. We first analyze the covert and secure communication performance on account of location uncertainty of warden, which leads to characterization on the expression of C&S AoI. Then, we formulate a joint UAV position, transmit power and blocklength design problem to minimize the C&S AoI. To solve the complicated problem, an efficient iterative algorithm based on optimal solution analysis and a novel convex approximation is developed for obtaining a high-quality solution. Simulations demonstrate the superior performance of proposed algorithm in improving C&S AoI performance of delay sensitive networks compared with benchmark.","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"15 ","pages":"1524-1528"},"PeriodicalIF":5.5,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：