Pub Date : 2024-09-05DOI: 10.1109/LCOMM.2024.3454632
Liwei Wang;Jun Li;Wen Chen;Qingqing Wu;Ming Ding
Federated Learning (FL) facilitates collaborative machine learning by training models on local datasets, and subsequently aggregating these local models at a central server. However, the frequent exchange of model parameters between clients and the central server can result in significant communication overhead during the FL training process. To solve this problem, this letter proposes a novel FL framework, the Model Aggregation with Layer Divergence Feedback mechanism (FedLDF). Specifically, we calculate model divergence between the local model and the global model from the previous round. Then through model layer divergence feedback, the distinct layers of each client are uploaded and the amount of data transferred is reduced effectively. Moreover, the theoretical analysis reveals that the access ratio of clients has a positive correlation with model performance. Simulation results show that our algorithm uploads local models with reduced communication overhead while upholding a superior global model performance.
{"title":"Communication-Efficient Model Aggregation With Layer Divergence Feedback in Federated Learning","authors":"Liwei Wang;Jun Li;Wen Chen;Qingqing Wu;Ming Ding","doi":"10.1109/LCOMM.2024.3454632","DOIUrl":"10.1109/LCOMM.2024.3454632","url":null,"abstract":"Federated Learning (FL) facilitates collaborative machine learning by training models on local datasets, and subsequently aggregating these local models at a central server. However, the frequent exchange of model parameters between clients and the central server can result in significant communication overhead during the FL training process. To solve this problem, this letter proposes a novel FL framework, the Model Aggregation with Layer Divergence Feedback mechanism (FedLDF). Specifically, we calculate model divergence between the local model and the global model from the previous round. Then through model layer divergence feedback, the distinct layers of each client are uploaded and the amount of data transferred is reduced effectively. Moreover, the theoretical analysis reveals that the access ratio of clients has a positive correlation with model performance. Simulation results show that our algorithm uploads local models with reduced communication overhead while upholding a superior global model performance.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2293-2297"},"PeriodicalIF":3.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190009","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 : 2024-09-05DOI: 10.1109/LCOMM.2024.3454804
Diego Forlivesi;Lorenzo Valentini;Marco Chiani
We introduce surface ZZZY codes, a novel family of quantum error-correcting codes designed for asymmetric channels. Derived from standard surface codes through tailored modification of generators, ZZZY codes can be decoded by the minimum weight perfect matching (MWPM) algorithm with a suitable pre-processing phase. The resulting decoder exploits the information provided by the modified generators without introducing additional complexity. ZZZY codes demonstrate a significant performance advantage over surface codes when increasing the channel asymmetry, while maintaining the same correction capability over depolarizing channel.
{"title":"Quantum Codes for Asymmetric Channels: ZZZY Surface Codes","authors":"Diego Forlivesi;Lorenzo Valentini;Marco Chiani","doi":"10.1109/LCOMM.2024.3454804","DOIUrl":"10.1109/LCOMM.2024.3454804","url":null,"abstract":"We introduce surface ZZZY codes, a novel family of quantum error-correcting codes designed for asymmetric channels. Derived from standard surface codes through tailored modification of generators, ZZZY codes can be decoded by the minimum weight perfect matching (MWPM) algorithm with a suitable pre-processing phase. The resulting decoder exploits the information provided by the modified generators without introducing additional complexity. ZZZY codes demonstrate a significant performance advantage over surface codes when increasing the channel asymmetry, while maintaining the same correction capability over depolarizing channel.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2233-2237"},"PeriodicalIF":3.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666750","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190013","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 : 2024-09-04DOI: 10.1109/LCOMM.2024.3454420
Yan Zhang;Lu Lv;Long Yang;Yongjun Xu;Zhiguo Ding;Jian Chen
In this letter, we propose a symbiotic non-orthogonal multiple access (NOMA) mutually reinforcing paradigm for green massive access to better meet the diverse and challenging requirements of Internet-of-Things. In particular, the backscatter device (BD) utilizes the same spectrum resources of the legacy users for reflection while providing beneficial multipath to enhance the performance of legacy transmission. We aim to jointly optimize the active/receive beamforming vectors and reflection coefficients to maximize the weighted sum rate, proving that there is no need to design a dedicated beam for BD via the developed analytical results. Simulation results validate the superiority of the symbiotic NOMA scheme.
{"title":"Symbiotic NOMA: A Mutualism Communication Paradigm Toward Green Massive Access","authors":"Yan Zhang;Lu Lv;Long Yang;Yongjun Xu;Zhiguo Ding;Jian Chen","doi":"10.1109/LCOMM.2024.3454420","DOIUrl":"10.1109/LCOMM.2024.3454420","url":null,"abstract":"In this letter, we propose a symbiotic non-orthogonal multiple access (NOMA) mutually reinforcing paradigm for green massive access to better meet the diverse and challenging requirements of Internet-of-Things. In particular, the backscatter device (BD) utilizes the same spectrum resources of the legacy users for reflection while providing beneficial multipath to enhance the performance of legacy transmission. We aim to jointly optimize the active/receive beamforming vectors and reflection coefficients to maximize the weighted sum rate, proving that there is no need to design a dedicated beam for BD via the developed analytical results. Simulation results validate the superiority of the symbiotic NOMA scheme.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2437-2441"},"PeriodicalIF":3.7,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190010","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 : 2024-09-03DOI: 10.1109/LCOMM.2024.3454009
Hakim Jemaa;Simon Tarboush;Hadi Sarieddeen;Mohamed-Slim Alouini;Tareq Y. Al-Naffouri
Accurate link-level theoretical performance analysis is crucial for emerging wireless communication systems. We present a detailed study of outdoor point-to-point terahertz (THz) links, incorporating mixture gamma (MG) small-scale fading and misalignment effects. Closed-form expressions for bit-error probability, outage probability, and ergodic capacity are derived. Furthermore, we conduct an asymptotic analysis at high signal-to-noise ratios, highlighting the convergence conditions. Simulation results, using measurement-based channel parameters, validate the analytical findings across various configurations.
{"title":"Performance Analysis of Outdoor THz Links Under Mixture Gamma Fading With Misalignment","authors":"Hakim Jemaa;Simon Tarboush;Hadi Sarieddeen;Mohamed-Slim Alouini;Tareq Y. Al-Naffouri","doi":"10.1109/LCOMM.2024.3454009","DOIUrl":"10.1109/LCOMM.2024.3454009","url":null,"abstract":"Accurate link-level theoretical performance analysis is crucial for emerging wireless communication systems. We present a detailed study of outdoor point-to-point terahertz (THz) links, incorporating mixture gamma (MG) small-scale fading and misalignment effects. Closed-form expressions for bit-error probability, outage probability, and ergodic capacity are derived. Furthermore, we conduct an asymptotic analysis at high signal-to-noise ratios, highlighting the convergence conditions. Simulation results, using measurement-based channel parameters, validate the analytical findings across various configurations.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 11","pages":"2668-2672"},"PeriodicalIF":3.7,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190011","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 : 2024-09-02DOI: 10.1109/LCOMM.2024.3452754
Longlong Cao;Jiaxing Fang;Yan Wang;Pengcheng Zhu
In this letter, we propose a joint power optimization and subcarrier allocation algorithm for cell-free massive multiple-input multiple-output systems in the ultra-reliable and low-latency communication (URLLC) scenario. Considering the bursty and stochastic character of URLLC traffic, we employ a proactive packet dropping mechanism to address the queueing issue of URLLC packets within deep fading channels, where the required transmit power to guarantee queueing delay and transmission error probability becomes unbounded. Therefore, we formulate an optimization problem to minimize the required maximal transmit power and the queueing delay by optimizing the packet loss policy, power, and bandwidth allocation policies. Simulation results validate our analysis and show that the proposed algorithm can effectively reduce the required maximal transmit power to meet the requirements of URLLC, and that spatial diversity contributes to reducing the complexity of the proposed algorithm.
{"title":"Joint Power Optimization and Subcarrier Allocation for URLLC in Cell-Free Massive MIMO System","authors":"Longlong Cao;Jiaxing Fang;Yan Wang;Pengcheng Zhu","doi":"10.1109/LCOMM.2024.3452754","DOIUrl":"10.1109/LCOMM.2024.3452754","url":null,"abstract":"In this letter, we propose a joint power optimization and subcarrier allocation algorithm for cell-free massive multiple-input multiple-output systems in the ultra-reliable and low-latency communication (URLLC) scenario. Considering the bursty and stochastic character of URLLC traffic, we employ a proactive packet dropping mechanism to address the queueing issue of URLLC packets within deep fading channels, where the required transmit power to guarantee queueing delay and transmission error probability becomes unbounded. Therefore, we formulate an optimization problem to minimize the required maximal transmit power and the queueing delay by optimizing the packet loss policy, power, and bandwidth allocation policies. Simulation results validate our analysis and show that the proposed algorithm can effectively reduce the required maximal transmit power to meet the requirements of URLLC, and that spatial diversity contributes to reducing the complexity of the proposed algorithm.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2323-2327"},"PeriodicalIF":3.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190014","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 : 2024-09-02DOI: 10.1109/LCOMM.2024.3452715
Yongkang Li;Zheng Shi;Han Hu;Yaru Fu;Hong Wang;Hongjiang Lei
Semantic communications have been envisioned as a potential technique that goes beyond Shannon paradigm. Unlike modern communications that provide bit-level security, the eavesdropping of semantic communications poses a significant risk of potentially exposing intention of legitimate user. To address this challenge, a novel deep neural network (DNN) enabled secure semantic communication (DeepSSC) system is developed by capitalizing on physical layer security. To balance the tradeoff between security and reliability, a two-phase training method for DNNs is devised. Particularly, Phase I aims at semantic recovery of legitimate user, while Phase II attempts to minimize the leakage of semantic information to eavesdroppers. The loss functions of DeepSSC in Phases I and II are respectively designed according to Shannon capacity and secure channel capacity, which are approximated with variational inference. Moreover, we define the metric of secure bilingual evaluation understudy (S-BLEU) to assess the security of semantic communications. Finally, simulation results demonstrate that DeepSSC achieves a significant boost to semantic security particularly in high signal-to-noise ratio regime, despite a minor degradation of reliability.
{"title":"Secure Semantic Communications: From Perspective of Physical Layer Security","authors":"Yongkang Li;Zheng Shi;Han Hu;Yaru Fu;Hong Wang;Hongjiang Lei","doi":"10.1109/LCOMM.2024.3452715","DOIUrl":"10.1109/LCOMM.2024.3452715","url":null,"abstract":"Semantic communications have been envisioned as a potential technique that goes beyond Shannon paradigm. Unlike modern communications that provide bit-level security, the eavesdropping of semantic communications poses a significant risk of potentially exposing intention of legitimate user. To address this challenge, a novel deep neural network (DNN) enabled secure semantic communication (DeepSSC) system is developed by capitalizing on physical layer security. To balance the tradeoff between security and reliability, a two-phase training method for DNNs is devised. Particularly, Phase I aims at semantic recovery of legitimate user, while Phase II attempts to minimize the leakage of semantic information to eavesdroppers. The loss functions of DeepSSC in Phases I and II are respectively designed according to Shannon capacity and secure channel capacity, which are approximated with variational inference. Moreover, we define the metric of secure bilingual evaluation understudy (S-BLEU) to assess the security of semantic communications. Finally, simulation results demonstrate that DeepSSC achieves a significant boost to semantic security particularly in high signal-to-noise ratio regime, despite a minor degradation of reliability.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2243-2247"},"PeriodicalIF":3.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190019","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}
Movable antenna (MA) provides an innovative way to arrange antennas that can contribute to improved signal quality and more effective interference management. This technology is especially beneficial for co-frequency co-time full-duplex (CCFD) wireless communication, which struggles with self-interference (SI) that usually overpowers the desired incoming signals. By dynamically repositioning transmit/receive antennas, we can mitigate the SI and enhance the reception of incoming signals. Thus, this letter proposes a novel MA-enabled point-to-point CCFD system and formulates the minimum achievable rate of two CCFD terminals. To maximize the minimum achievable rate and determine the positions of MAs, we introduce a solution based on projected particle swarm optimization (PPSO), which can circumvent common suboptimal positioning issues. Moreover, simulation results reveal that the PPSO method leads to better performance compared to the conventional alternating position optimization (APO). The results also demonstrate that an MA-enabled CCFD system outperforms the one using fixed-position antennas (FPAs).
可移动天线（MA）提供了一种创新的天线布置方式，有助于提高信号质量和更有效地管理干扰。这种技术尤其适用于同频同时全双工（CCFD）无线通信，因为这种通信会受到自干扰（SI）的困扰，而自干扰通常会盖住所需的传入信号。通过动态调整发射/接收天线的位置，我们可以减轻自干扰，增强对传入信号的接收。因此，本文提出了一种新颖的支持 MA 的点对点 CCFD 系统，并提出了两个 CCFD 终端的最小可达速率。为了最大限度地提高最小可达速率并确定 MA 的位置，我们引入了一种基于投影粒子群优化（PPSO）的解决方案，它可以规避常见的次优定位问题。此外，仿真结果表明，与传统的交替位置优化（APO）相比，PPSO 方法具有更好的性能。结果还表明，支持 MA 的 CCFD 系统优于使用固定位置天线 (FPA) 的系统。
{"title":"Movable Antenna-Enabled Co-Frequency Co-Time Full-Duplex Wireless Communication","authors":"Jingze Ding;Zijian Zhou;Wenyao Li;Chenbo Wang;Lifeng Lin;Bingli Jiao","doi":"10.1109/LCOMM.2024.3453296","DOIUrl":"10.1109/LCOMM.2024.3453296","url":null,"abstract":"Movable antenna (MA) provides an innovative way to arrange antennas that can contribute to improved signal quality and more effective interference management. This technology is especially beneficial for co-frequency co-time full-duplex (CCFD) wireless communication, which struggles with self-interference (SI) that usually overpowers the desired incoming signals. By dynamically repositioning transmit/receive antennas, we can mitigate the SI and enhance the reception of incoming signals. Thus, this letter proposes a novel MA-enabled point-to-point CCFD system and formulates the minimum achievable rate of two CCFD terminals. To maximize the minimum achievable rate and determine the positions of MAs, we introduce a solution based on projected particle swarm optimization (PPSO), which can circumvent common suboptimal positioning issues. Moreover, simulation results reveal that the PPSO method leads to better performance compared to the conventional alternating position optimization (APO). The results also demonstrate that an MA-enabled CCFD system outperforms the one using fixed-position antennas (FPAs).","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2412-2416"},"PeriodicalIF":3.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190012","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 : 2024-08-30DOI: 10.1109/LCOMM.2024.3452127
M. Hemanta Kumar;Alok Kumar;Sanjeev Sharma;Mogadala Vinod Kumar
In this letter, a novel communication scheme termed spatial modulation aided cooperative non-orthogonal multiple access (SM-CNOMA) is proposed for multiple-input and multiple-output (MIMO) downlink scenarios. In the SM-CNOMA system, the base station (BS) transmits information to three users across two time-slots, encompassing two near users (NUs) and a single far user (FU). Notably, NUs operate in a half-duplex mode and employ joint signal detection during the cooperative phase for decoding, and forward FU information through index modulation (IM). Bit error rate (BER) and ergodic sum-rate metrics are derived, by considering inter-user interference (IUI), of the proposed SM-CNOMA system. The impact of various system parameters, such as the number of transmit and receive antennas, is thoroughly analyzed within the SM-CNOMA framework. The presented results demonstrate that SM-CNOMA outperforms conventional CNOMA with three users and the precoded CNOMA (PCNOMA) systems. This letter contributes valuable insights into the potential benefits of SM-CNOMA in MIMO downlink communications, establishing its efficiency in mitigating interference and enhancing the overall system performance.
{"title":"Performance Analysis of a Spatial Modulation Aided Cooperative NOMA System","authors":"M. Hemanta Kumar;Alok Kumar;Sanjeev Sharma;Mogadala Vinod Kumar","doi":"10.1109/LCOMM.2024.3452127","DOIUrl":"10.1109/LCOMM.2024.3452127","url":null,"abstract":"In this letter, a novel communication scheme termed spatial modulation aided cooperative non-orthogonal multiple access (SM-CNOMA) is proposed for multiple-input and multiple-output (MIMO) downlink scenarios. In the SM-CNOMA system, the base station (BS) transmits information to three users across two time-slots, encompassing two near users (NUs) and a single far user (FU). Notably, NUs operate in a half-duplex mode and employ joint signal detection during the cooperative phase for decoding, and forward FU information through index modulation (IM). Bit error rate (BER) and ergodic sum-rate metrics are derived, by considering inter-user interference (IUI), of the proposed SM-CNOMA system. The impact of various system parameters, such as the number of transmit and receive antennas, is thoroughly analyzed within the SM-CNOMA framework. The presented results demonstrate that SM-CNOMA outperforms conventional CNOMA with three users and the precoded CNOMA (PCNOMA) systems. This letter contributes valuable insights into the potential benefits of SM-CNOMA in MIMO downlink communications, establishing its efficiency in mitigating interference and enhancing the overall system performance.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2273-2277"},"PeriodicalIF":3.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190016","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 : 2024-08-29DOI: 10.1109/LCOMM.2024.3451655
M. Y. Daha;Kiran Khurshid;M. I. Ashraf;M. U. Hadi
Artificial intelligence has transformed multiple input multiple output (MIMO) technology into a promising candidate for six-generation networks. However, several interference signals impact the data transmission between various antennas; therefore, sophisticated signal detection techniques are required at the MIMO receiver to estimate the transmitted data. This letter presents an optimized AI-based signal detection technique called AIDETECT for MIMO systems. The proposed AIDETECT network model is developed based on an optimized deep neural network (DNN) architecture, whose efficiency lies in its lightweight network architecture. To train and test the AIDETECT network model, we generate and process the data in a suitable form based on the transmitted signal, channel information, and noise. Based on this data, we calculate the received signal at the receiver end, where the received signal and channel information were integrated into the AIDETECT network model to perform reliable signal detection. Simulation results show that at a 20-dB signal-to-noise ratio (SNR), the proposed AIDETECT technique achieves between 97.33% to 99.99% better performance compared to conventional MIMO detectors and is also able to accomplish between 25.34% to 99.98% better performance than other AI-based MIMO detectors for the considered performance metrics. In addition, due to lightweight network architecture, the proposed AIDETECT technique has also achieved much lower computational complexity than conventional and AI-based MIMO detectors.
人工智能已将多输入多输出（MIMO）技术转化为六代网络的理想候选技术。然而，多个干扰信号会影响不同天线之间的数据传输；因此，MIMO 接收器需要复杂的信号检测技术来估计传输的数据。本文提出了一种基于人工智能的优化信号检测技术，称为 AIDETECT，适用于 MIMO 系统。所提出的 AIDETECT 网络模型是基于优化的深度神经网络（DNN）架构开发的，其效率在于其轻量级网络架构。为了训练和测试 AIDETECT 网络模型，我们根据传输信号、信道信息和噪声，以合适的形式生成和处理数据。根据这些数据，我们计算接收端的接收信号，并将接收信号和信道信息整合到 AIDETECT 网络模型中，以进行可靠的信号检测。仿真结果表明，在 20 分贝信噪比（SNR）条件下，与传统 MIMO 检测器相比，所提出的 AIDETECT 技术的性能提高了 97.33% 到 99.99%，在所考虑的性能指标方面，也比其他基于人工智能的 MIMO 检测器提高了 25.34% 到 99.98%。此外，由于采用了轻量级网络架构，所提出的 AIDETECT 技术的计算复杂度也远远低于传统和基于人工智能的 MIMO 检测器。
{"title":"Optimizing Signal Detection in MIMO Systems: AI vs Approximate and Linear Detectors","authors":"M. Y. Daha;Kiran Khurshid;M. I. Ashraf;M. U. Hadi","doi":"10.1109/LCOMM.2024.3451655","DOIUrl":"10.1109/LCOMM.2024.3451655","url":null,"abstract":"Artificial intelligence has transformed multiple input multiple output (MIMO) technology into a promising candidate for six-generation networks. However, several interference signals impact the data transmission between various antennas; therefore, sophisticated signal detection techniques are required at the MIMO receiver to estimate the transmitted data. This letter presents an optimized AI-based signal detection technique called AIDETECT for MIMO systems. The proposed AIDETECT network model is developed based on an optimized deep neural network (DNN) architecture, whose efficiency lies in its lightweight network architecture. To train and test the AIDETECT network model, we generate and process the data in a suitable form based on the transmitted signal, channel information, and noise. Based on this data, we calculate the received signal at the receiver end, where the received signal and channel information were integrated into the AIDETECT network model to perform reliable signal detection. Simulation results show that at a 20-dB signal-to-noise ratio (SNR), the proposed AIDETECT technique achieves between 97.33% to 99.99% better performance compared to conventional MIMO detectors and is also able to accomplish between 25.34% to 99.98% better performance than other AI-based MIMO detectors for the considered performance metrics. In addition, due to lightweight network architecture, the proposed AIDETECT technique has also achieved much lower computational complexity than conventional and AI-based MIMO detectors.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2387-2391"},"PeriodicalIF":3.7,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190017","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 : 2024-08-29DOI: 10.1109/LCOMM.2024.3451510
Rong Yang;Shuping Dang;Jia Ye;Peng Wang
Channel model substitution (CMS) is an analytical technique aiming to replace a computationally complex channel model with a simpler substitute. The utility of CMS is affected by the parametric relations between the original channel model and its substitute. In this letter, we propose a moment converging criterion to enable parametric mapping for a general CMS problem. Instead of solving an equation system to yield the analytical solutions by moment matching, we formulate and minimize the moment mean squared error (MMSE) between the original channel model and its substitute to obtain parametric mapping relations. The moment converging enabled parametric mapping approach offers a surrogate way to enable parametric mapping for CMS, which is, in particular, helpful when the moment matching equation system is too cumbersome to solve and/or has no feasible solution. Taking three CMS applications as examples, the effectiveness and efficiency of the moment converging enabled parametric mapping for CMS are verified.
{"title":"Moment Converging Enabled Parametric Mapping for Channel Model Substitution","authors":"Rong Yang;Shuping Dang;Jia Ye;Peng Wang","doi":"10.1109/LCOMM.2024.3451510","DOIUrl":"10.1109/LCOMM.2024.3451510","url":null,"abstract":"Channel model substitution (CMS) is an analytical technique aiming to replace a computationally complex channel model with a simpler substitute. The utility of CMS is affected by the parametric relations between the original channel model and its substitute. In this letter, we propose a moment converging criterion to enable parametric mapping for a general CMS problem. Instead of solving an equation system to yield the analytical solutions by moment matching, we formulate and minimize the moment mean squared error (MMSE) between the original channel model and its substitute to obtain parametric mapping relations. The moment converging enabled parametric mapping approach offers a surrogate way to enable parametric mapping for CMS, which is, in particular, helpful when the moment matching equation system is too cumbersome to solve and/or has no feasible solution. Taking three CMS applications as examples, the effectiveness and efficiency of the moment converging enabled parametric mapping for CMS are verified.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"28 10","pages":"2248-2252"},"PeriodicalIF":3.7,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142190023","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：