Journal of Communications and Information Networks最新文献

{"title":"Graph-Based Communication Optimization for Multi-Agent Reinforcement Learning in Unmanned Warehousing","authors":"Ziming He;Zijia Wang;Yinhong Huang;Haobin Shi","doi":"10.23919/JCIN.2025.11357504","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357504","url":null,"abstract":"With the advancement of the industrial Internet and the ongoing intelligent transformation of manufacturing, multi-robot cooperative operations in unmanned warehouse systems face critical challenges in communication efficiency and real-time decision-making. Conventional path-planning algorithms are insufficient for cooperative scheduling in dynamic and complex environments, while existing multi-agent reinforcement learning (MARL)-based communication approaches often fail to determine appropriate communication targets or when to broadcast messages, resulting in excessive overhead and low efficiency. To address these limitations, this paper proposes a MARL-based communication optimization algorithm with graph representations. A graph-structured encoder is designed to intelligently select communication partners and optimize the communication topology. In addition, a graph information bottleneck mechanism is introduced to guide the graph neural network in learning minimally sufficient representations of communication messages. This mechanism maximizes the relevance of the representations to the cooperative task while minimizing dependence on the original communication graph, thereby enabling effective compression of redundant information. Experimental validation on a cooperative transportation task with warehouse robots in the robot operating system (ROS) and Gazebo simulation environment demonstrates that the proposed method reduces communication overhead by 79.0% and improves efficiency by a factor of 3.5, while maintaining a task success rate comparable to that of full-communication schemes. These results provide an efficient communication solution for large-scale multi-robot cooperative systems in industrial Internet scenarios.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"388-398"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Meta-Backscatter: Long-Distance Battery-Free Metamaterial-Backscatter Sensing and Communication","authors":"Taorui Liu;Xu Liu;Zhiquan Xu;Houfeng Chen;Hongliang Zhang;Lingyang Song","doi":"10.23919/JCIN.2025.11357493","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357493","url":null,"abstract":"Battery-free Internet of things (BF-IoT) enabled by backscatter communication is a rapidly evolving technology offering advantages of low cost, ultra-low power consumption, and robustness. However, the practical deployment of BF-IoT is significantly constrained by the limited communication range of common backscatter tags, which typically operate with a range of merely a few meters due to inherent round-trip path loss. Meta-backscatter systems that utilize metamaterial tags present a promising solution, retaining the inherent advantages of BF-IoT while breaking the critical communication range barrier. By leveraging densely paved sub-wavelength units to concentrate the reflected signal power, metamaterial tags enable a significant communication range extension over existing BF-IoT tags that employ omni-directional antennas. In this paper, we synthesize the principles and paradigms of metamaterial sensing to establish a unified design framework and a forward-looking research roadmap. Specifically, we first provide an overview of backscatter communication, encompassing its development history, working principles, and tag classification. We then introduce the design methodology for both metamaterial tags and their compatible transceivers. Moreover, we present the implementation of a meta-backscatter system prototype and report the experimental results based on it. Finally, we conclude by highlighting key challenges and outlining potential avenues for future research.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"311-325"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11357493","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM4AMC: Adapting Large Language Models for Adaptive Modulation and Coding","authors":"Xinyu Pan;Boxun Liu;Xiang Cheng;Chen Chen","doi":"10.23919/JCIN.2025.11357496","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357496","url":null,"abstract":"Adaptive modulation and coding (AMC) is a key technology in 5G new radio (NR), enabling dynamic link adaptation by balancing transmission efficiency and reliability based on channel conditions. However, traditional methods often suffer from performance degradation due to the aging issues of channel quality indicator (CQI). Recently, the emerging capabilities of large language models (LLMs) in contextual understanding and temporal modeling naturally align with the dynamic channel adaptation requirements of AMC technology. Leveraging pretrained LLMs, we propose a channel quality prediction method empowered by LLMs to optimize AMC, termed LLM4AMC. We freeze most parameters of the LLM and fine-tune it to fully utilize the knowledge acquired during pretraining while better adapting it to the AMC task. We design a network architecture composed of four modules, a preprocessing layer, an embedding layer, a backbone network, and an output layer, effectively capturing the time-varying characteristics of channel quality to achieve accurate predictions of future channel conditions. Simulation experiments demonstrate that our proposed method significantly improves link performance and exhibits potential for practical deployment.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"352-363"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling and Optimization of Three-Dimensional Polarforming for Multiuser Communications","authors":"Zijian Zhou;Jingze Ding;Jie Xu;Rui Zhang","doi":"10.23919/JCIN.2025.11357497","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357497","url":null,"abstract":"Polarforming has emerged as a promising technique to dynamically reconfigure antenna polarization, thereby mitigating depolarization effects encountered during electromagnetic (EM) wave propagation. In this paper, we propose and investigate three-dimensional polarforming (3DPF) for an uplink multiuser communication system, where the base station (BS) employs polarization-reconfigurable antennas (PRAs) with three orthogonally polarized antenna elements to serve users with fixed-polarization antennas (FPAs). By modifying the phase differences among these elements via low-cost phase shifters (PSs), 3DPF enables the full exploitation of polarization degrees of freedom (DoF) in three dimensions, thereby achieving polarization matching with incoming waves, particularly in multipath environments. We then present a polarized multipath channel model for the considered system and formulate a joint optimization problem for receive combining, power control, and polarforming phase shifts to maximize the minimum achievable rate among users. To solve this highly non-convex max-min fairness problem, we develop an efficient algorithm based on the block coordinate descent (BCD) framework, which iteratively optimizes the optimization variables by particle swarm optimization (PSO). Furthermore, simulation results demonstrate that the proposed system not only effectively combats polarization loss but also yields substantial performance gains over conventional polarization-reconfigurable systems in terms of the max-min achievable rate.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"364-375"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Neural Polar Codes for Integrated Data and Energy Communication Networks Enabled by Sensing-Aided UAVs","authors":"Yankai Wang;Luping Xiang;Jun Liu;Jingwen Cui;Kun Yang;Kang Zheng;Danhuai Zhao","doi":"10.23919/JCIN.2025.11357507","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357507","url":null,"abstract":"In unmanned aerial vehicle (UAV)-based scenarios, sensing-aided integrated data and energy networking (IDEN) systems can significantly mitigate non-line-of-sight (NLoS) propagation, thereby enhancing sensing accuracy. However, the rapid channel variations induced by UAV mobility pose a challenge for traditional polar code construction methods, making it difficult to satisfy the stringent requirements of IDEN systems. To address this challenge, we propose a neural network (NN)-based sensing-aided IDEN framework. This system leverages sensing information to assist polar code construction while satisfying energy constraints. Furthermore, it incorporates neural networks to optimize the performance of polar codes in dynamic environments. Specifically, a sensing-aided binarized neural network (BNN)-based polar encoder is proposed for both low-latency and high-reliability requirements, and a deep neural network (DNN)-based polar decoder is applied to match the encoder. Moreover, the corresponding training method is proposed, which focuses on the initialization design of the NNs. The simulation results show that the NN-based sensing-aided polar encoding scheme outperforms the conventional counterparts in terms of IDEN for both low-latency and high-reliability requirements.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"399-413"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems","authors":"Xuran Liu;Nan Xue;Rui Bao;Yaping Sun;Zhiyong Chen;Meixia Tao;Xiaodong Xu;Shuguang Cui","doi":"10.23919/JCIN.2025.11357495","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357495","url":null,"abstract":"While deploying large language models on edge devices promises low-latency and privacy-preserving artificial intelligence (AI) services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches often ignore the cold-start latency caused by on-demand model loading. In this paper, we propose a latency-aware scheduling framework that overlaps model loading with computation and communication to minimize total inference latency. Based on device and model parameters, the framework dynamically adjusts layer partitioning and allocation to effectively hide loading time, thereby eliminating as many idle periods as possible. We formulate the problem as a mixed-integer non-linear program (MINLP) and design an efficient dynamic programming algorithm to optimize model partitioning and device assignment. Experimental results show that the proposed method significantly reduces cold-start latency compared to baseline strategies.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"340-351"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Task-Oriented Space-Air-Ground Uniformly Integrated Networks: Architecture and Design Challenges","authors":"Jiachen Wang;Ran Li;Guowei Shi;Chao Deng;Chuan Huang","doi":"10.23919/JCIN.2025.11357494","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357494","url":null,"abstract":"In space-air-ground uniformly integrated network (SAGUIN), a centralized data control center (DCC) is deployed to manage the shared spectrum resources across the space, aerial, and ground layers under a unified communication architecture, which makes it a promising candidate for the next-generation wireless systems. However, due to the extremely large physical scale of SAGUIN, signals transmitted across different layers experience substantially different propagation delays and channel conditions, a disparity further amplified by the network's layered structure and spatially clustered topology. On the other hand, task-oriented communications typically employ short-packet transmissions, whose durations are only a small fraction of the large propagation delays between satellites, aerial platforms, and ground users. The above phenomena, including asynchronous and out-of-order signal arrivals induced by delay asymmetry among satellites, aerial platforms, and ground users; non-coherent transmissions over heterogeneous links with substantial timing offsets; and spatiotemporally coupled interferences arising from overlapping coverage areas and disparities in propagation delay, present major challenges for throughput modeling, access protocol design, and network resource management. In this article, we analyze the network throughput, design the multi-user access signal detection scheme, and optimize the task scheduling under ripple effect, thereby offering new insights into the deployment of future SAGUINs.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"376-387"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Malware Classification Algorithm Based on Multiple Data Augmentation and Transfer Learning using Pretrained Image Classification Models","authors":"Jun Yan;Jian Liu;Wei Wang","doi":"10.23919/JCIN.2025.11357503","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357503","url":null,"abstract":"In order to solve the problem of limited number of training data and insufficient feature representation for malware classification, in this paper, the data augmentation and pretrained image classification models based algorithm is proposed. First, two malware image construction and augmentation approaches are proposed. The malware data is preprocessed and converted into RGB image by mapping. Then, the deep convolutional generative adversarial network is utilized for image augmentation of each channel. And the structural similarity index is proposed for generated malware image filtering. For another, the denoising diffusion implicit model is utilized for malware data augmentation of each class. After the cosine similarity and Jensen-Shannon divergence based data filtering, the Gramian angular summation field method is used for malware image construction. Second, the pretrained VGG16 and ResNet50 models are proposed for feature extraction by transfer learning. Moreover, three feature fusion strategies are designed. At last, by the off-line training, the malware classification model is obtained. Experiment results demonstrate that the proposed algorithm has better malware classification performance than some existing methods.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"414-424"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Sensitive Information Mimetic Classification Algorithm Based on Intelligent Algorithms","authors":"Lingling Li","doi":"10.23919/JCIN.2025.11357502","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11357502","url":null,"abstract":"In the era of exponential Internet growth, social media platforms have become indispensable channels for daily communication. However, this digital ecosystem harbors a dual challenge: 1) users transmit information of varying sensitivity, demanding differentiated security measures for critical data (e.g., encrypted transmission) versus general content; 2) the Internet’s anonymity enables malicious actors to spread harmful content—often embedding sensitive information. Such dissemination not only degrades the online experience for legitimate users but also threatens social stability, underscoring the urgency of robust sensitive information classification. Sensitive texts exacerbate these challenges: they typically manifest as short messages with sparse semantic features, fragmented syntax, and deliberate lexical obfuscations (e.g., phonetic substitutions or deformed word forms) to evade rule-based detection. Traditional methods relying on manually curated dictionaries or fixed rules struggle with this dynamism, while collected datasets often suffer from severe class imbalance—a critical limitation for supervised learning. This paper introduces a heterogeneous mimetic classification framework that transcends conventional ensemble approaches (e.g., XGBoost). Unlike homogeneous ensembles, its innovation lies in integrating diverse model paradigms: prior-probability models [e.g., support vector machine (SVM)], posterior-probability networks, attention-based architectures, and large pre-trained language models. This design enables adaptive knowledge fusion, enhancing both cross-domain adaptability and interpretability by leveraging complementary strengths of different models. Experimental validation on newly created Chinese datasets (covering 7 macro-categories and 59 sub-categories) compares the framework against state-of-the-art pre-trained models and SVM with mimetic strategies. While SVM-based methods perform adequately for low-dimensional vectors but falter in high-dimensional spaces, our framework demonstrates consistent superiority across all vector dimensions—highlighting its efficacy in handling real-world sensitive information classification tasks.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 4","pages":"425-434"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Beamforming Design for Reconfigurable Intelligent Surface-Assisted LEO Satellite Constellation Communication","authors":"Wenfei Yao;Xiaoming Chen;Qi Wang","doi":"10.23919/JCIN.2025.11207210","DOIUrl":"https://doi.org/10.23919/JCIN.2025.11207210","url":null,"abstract":"Low earth orbit (LEO) satellite constellation, as a typical non-terrestrial network (NTN), can provide ubiquitous connectivity for 6G wireless networks with low transmission delay. However, satellite communications (SATCOM) are still hampered by challenges such as scarcity of spectrum resources and significant path losses. In this paper, reconfigurable intelligent surfaces (RIS) are deployed to enhance the performance of long-distance satellite-terrestrial communication. Further, by exploring inter-satellite links, a joint active beamforming at satellites and passive beamforming at RIS design algorithm is proposed to improve the weighted sum rate (WSR) of satellite-terrestrial communication in the presence of inter-satellite interference due to spectrum sharing. Specifically, we adopt alternating optimization (AO) method to split the original problem into two sub-problems and then solve them step by step. Firstly, given passive beamforming at RIS, we solve the active beamforming design problem with a closed-form solution. Secondly, given the active beamforming, we design passive beamforming for RIS through the alternating direction method of the multipliers. Theoretical analysis and extensive numerical simulations demonstrate the effectiveness of our proposed algorithm in RIS-assisted LEO satellite constellation communications.","PeriodicalId":100766,"journal":{"name":"Journal of Communications and Information Networks","volume":"10 3","pages":"254-267"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}