{"title":"Semantic Communication Over Channels With Insertions, Deletions, and Substitutions","authors":"Tuna Ozates;Aykut Koç","doi":"10.1109/LCOMM.2025.3533928","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3533928","url":null,"abstract":"We present deep joint source-outer channel coding (DeepJSOC), an end-to-end deep learning-based semantic communication architecture designed for channels with insertions, deletions, and substitutions (IDS). We propose a three-stage training algorithm that combines, for the first time, gated recurrent unit (GRU) networks for marker detection, transformer-based semantic communication for continuous latent space, and lookup-free quantization for binarized latent space optimization, specifically tailored to IDS channels. The proposed DeepJSOC is the first to integrate deep learning-based error correction networks into joint-source channel coding schemes for binary channels with synchronization errors. We demonstrate the effectiveness of DeepJSOC by experiments, achieving significant improvements over existing methods in text transmission.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"586-590"},"PeriodicalIF":3.7,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611864","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}
Lazar S. Stojković;Velimir M. Ilić;Ivan B. Djordjevic
{"title":"Achievable Cutoff Rates of the Additive Exponential Noise Channels","authors":"Lazar S. Stojković;Velimir M. Ilić;Ivan B. Djordjevic","doi":"10.1109/LCOMM.2025.3533262","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3533262","url":null,"abstract":"We derive closed-form expressions for the Gallager error function of the additive exponential noise channels and provide theoretical upper bounds on its maximum over the input probability distribution space (the cutoff rate), thus extending the previous results derived for the additive white Gaussian noise channels. Our theoretical results allow us to design constellations using simple optimization techniques that directly maximize the Gallager error function of the additive exponential noise channels. We perform simulations and show that projected gradient ascent optimization yields constellations competitive to existing ones that are optimized for Shannon information metrics, which require numerical estimation.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"582-585"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611913","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}
{"title":"Information-Theoretic Analysis of Inverse Gamma Substitution for Lognormal Shadowing Models","authors":"Rong Yang;Shuping Dang;Jia Ye;Peng Wang","doi":"10.1109/LCOMM.2025.3533039","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3533039","url":null,"abstract":"Due to its outstanding mathematical tractability, the inverse gamma (InvG) distribution is used as a substitute for the lognormal distribution to characterize the random fluctuations of the wireless signal envelope caused by shadowing. In this letter, we carry out the information-theoretic study of this channel model substitution (CMS) technique in terms of feasibility, approximation accuracy, and optimality by adopting both moment matching and Kullback-Leibler divergence (KLD) minimization criteria for parametric mapping. Specifically, we derive the minimum achievable KLD by the lognormal-to-InvG CMS and the corresponding optimal parametric mapping relation. By comparing to the gamma substitute that has been widely used for approximating the lognormal shadowing model, we demonstrate that the InvG substitute is more mathematically tractable and rigorously prove that the InvG substitute, however, cannot yield a lower KLD than the gamma substitute when applying the same parametric mapping criterion.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"577-581"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611779","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}
{"title":"Iterative Block Decision Feedback Equalization With Near-Linear Complexity for SC-FDE Systems","authors":"Tianrun Qiao;Xiaojie Fang;Xuejun Sha","doi":"10.1109/LCOMM.2025.3532952","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3532952","url":null,"abstract":"In this letter, a low complexity iterative block decision feedback equalization (IBDFE) algorithm is designed for single carrier frequency domain equalization (SC-FDE) systems. By identifying error peaks within the output of minimum mean square error frequency domain linear equalizer (MMSE FD-LE) and substituting them with feedback signal, a performance gain of more than 3dB compared to MMSE FD-LE can be achieved at a bit error rate (BER) of <inline-formula> <tex-math>$10^{-4}$ </tex-math></inline-formula>. The proposed algorithm has a minor performance loss compared to IBDFE system based on MMSE criterion (IBDFE-MMSE), while also offering lower latency and complexity close to that of MMSE FD-LE.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"572-576"},"PeriodicalIF":3.7,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611868","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}
{"title":"Feature Contrastive Transfer Learning for Few-Shot Long-Tail Sonar Image Classification","authors":"Zhongyu Bai;Hongli Xu;Qichuan Ding;Xiangyue Zhang","doi":"10.1109/LCOMM.2025.3532258","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3532258","url":null,"abstract":"Sonar image classification is challenging due to the limited availability and long-tail distribution of labeled sonar samples. In this work, a Feature Contrastive Transfer Learning (FCTL) framework is proposed for few-shot long-tailed sonar image classification. The proposed framework combines transfer learning and contrastive learning to improve model performance under limited labeled data. First, a deep convolutional neural network (CNN) is pre-trained on a large-scale image dataset to learn general feature representations. Then, contrastive learning is employed to maximize the similarity between positive sample pairs and minimize the similarity between positive and negative sample pairs. Specifically, positive samples are generated through a Gaussian feature enhancement method, while the remaining samples in a batch are negative. In addition, a balanced sampling strategy is employed to optimize the unbalanced feature distribution of long-tailed samples. Experiments on two different sonar image datasets demonstrate that the FCTL framework outperforms existing methods in few-shot long-tailed sonar image classification tasks.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"562-566"},"PeriodicalIF":3.7,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611919","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}
{"title":"Multi-Principal Spectrum Trading Incentive for UAV-Enabled Wireless Networks","authors":"Fang Ye;Weibo Hao;Jingchao Li;Yibing Li","doi":"10.1109/LCOMM.2025.3530518","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3530518","url":null,"abstract":"This letter discusses the spectrum trading problem between UAVs acting as aerial access points and a macro base station (MBS). The study aims to address the complex game-theoretic interactions between the MBS and multiple UAVs to enhance the benefits for all parties involved. We propose a combined spectrum trading scheme for multiple UAV operators jointly requesting spectrum from the MBS. For each UAV operator, we introduce an optimal contract design problem based on cooperation and present a method utilizing greedy strategies and block coordinate descent to solve it. Compared to schemes that ignore composite contract, cooperative spectrum trading increases the transaction volume by 32.41% in the scenario we set.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"557-561"},"PeriodicalIF":3.7,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611854","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}
{"title":"ST-CSFNet: Spatial-Temporal Cross Scale FNet for Radio Environment Map Forecasting","authors":"Song Zha;Haiyang Xia;Jijun Huang;Peiguo Liu","doi":"10.1109/LCOMM.2025.3529898","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3529898","url":null,"abstract":"Radio environment maps (REMs) forecasting is critical for wireless communication, yet existing methods have notable gaps, hindering efficient, reliable, and secure spectrum utilization. This letter introduces an innovative network, ST-CSFNet, that addresses these limitations, particularly their dependence on radiation source information and their failure to capture spatiotemporal dynamics. ST-CSFNet enhances REM forecasting accuracy through multiscale temporal analysis, capturing sequence dynamics across intervals, and by assessing spatial correlations, it accurately extracts spatial characteristics at various granularities. Specifically, it reduces MAE by 37.6%, RMSE by 29.5%, and increases <inline-formula> <tex-math>$mathrm {R}^{2}$ </tex-math></inline-formula> by 6.3%, showcasing significant advancements in REM forecasting accuracy.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"547-551"},"PeriodicalIF":3.7,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611863","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}
Junliang Yang;Shaoshuai Gao;Yan Lu;Zhao Yang;Guofang Tu
{"title":"Max-Min Fairness of Cooperative RSMA for Aggregated VLC/RF Systems","authors":"Junliang Yang;Shaoshuai Gao;Yan Lu;Zhao Yang;Guofang Tu","doi":"10.1109/LCOMM.2025.3530139","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3530139","url":null,"abstract":"The aggregated visible light communication (VLC) and radio frequency (RF) system, which can be regarded as a heterogeneous multiple-input multiple-output system, has been studied to operate with novel multiple access technologies for effectively expanding spectrum resources. In this letter, we propose a novel cooperative rate splitting multiple access (RSMA)-based aggregated VLC/RF system that forwards part of common stream via device-to-device (D2D) RF sidelinks to tackle the problem of fairness among users. Meanwhile, with the objective of maximizing the minimum achievable rate, we jointly optimize the precoder, rate allocation of common stream, and power allocation of RF sidelinks under the constraint of limited total system power. Since the formulated optimization problem is non-convex, semidefinite relaxation (SDR) and successive convex approximation (SCA) methods are applied to solve it. Numerical results show that the proposed scheme significantly outperforms other baseline schemes in terms of user fairness, i.e., the minimum achievable rate in different scenarios and demonstrates robustness against blockages.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"552-556"},"PeriodicalIF":3.7,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611862","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}
Yibo Chen;Zhijin Zhao;Xueyi Ye;Shilian Zheng;Xiaoniu Yang
{"title":"Intelligent Decision-Making for Asynchronous Dynamic Orthogonal Networking Based on DO-QMIX Algorithm","authors":"Yibo Chen;Zhijin Zhao;Xueyi Ye;Shilian Zheng;Xiaoniu Yang","doi":"10.1109/LCOMM.2025.3529531","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3529531","url":null,"abstract":"In order to intelligently select the frequency points of each subnet in the asynchronous dynamic orthogonal networking (ADON), we propose the QMIX algorithm based on dataset aggregation and options architecture (DO-QMIX). Joint reward is maximized to mitigate the problem of partially observable environment. Specifically, we first pre-train the network by dataset aggregation (DAgger) to improve the sample utilization. Then, we fine-tune the policy via experiences generated by options architecture (OA) to avoid getting trapped in local optima. Numerical results show that the proposed DO-QMIX outperforms the comparison algorithms in the three complex electromagnetic environments.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"537-541"},"PeriodicalIF":3.7,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611911","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}
{"title":"An Improved Pointing Error Model for mmWave and THz Links: Antenna and Array Design Impact","authors":"Evla Safahan Ahrazoglu;Ahmet Caner Gul;Mehmet Nuri Akinci;Ibrahim Altunbas;Eylem Erdogan","doi":"10.1109/LCOMM.2025.3529519","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3529519","url":null,"abstract":"Pointing error has a significant impact on the performance of millimeter wave (mmWave) and terahertz (THz) communications due to directional transmission. Currently existing pointing error models are lacking in capturing the mmWave/THz radiation characteristics and/or the impact of antenna design and array design. Therefore, in this letter, a simple analytical pointing error model for highly directional mmWave/THz transmission is proposed. By utilizing the Gaussian beam approximation for both the array element radiation pattern and the array factor, the presented model incorporates antenna design parameters (maximum gain and 3 dB beamwidth) and array design parameters (number of array elements, element spacing, and 3 dB beamwidth). This approximation is validated via electromagnetic simulations in CST Microwave Studio. Afterwards, the statistics of the pointing error are derived according to the Gaussian beam approximation, and it is demonstrated that the pointing error follows a special case of the negative log-Gamma distribution with the shape parameter of 2 and the scale parameter depending on antenna/array design and jitter variance. It is shown that the proposed model aligns perfectly with the simulation results. Moreover, the outage performance of an aerial communication scenario is analyzed to examine the impact of pointing errors. The results have revealed that the antenna and array design parameters are as influential as the jitter variance, and they cannot be neglected.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"29 3","pages":"532-536"},"PeriodicalIF":3.7,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611870","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}