IEEE Transactions on Cognitive Communications and Networking最新文献

{"title":"Point Cloud-Based Environmental Material Classification for Wireless Channel Ray-Tracing Simulations","authors":"Zhuoyin Li;Ruisi He;Mi Yang;Ziyi Qi;Zhong Zhang;Haoxiang Zhang;Jiahui Han;Bo Ai;Zhangdui Zhong","doi":"10.1109/TCCN.2026.3659825","DOIUrl":"10.1109/TCCN.2026.3659825","url":null,"abstract":"Ray-tracing (RT) channel simulation has been widely used for simulating and analyzing propagation of electromagnetic waves in complex environments. Accuracy of RT simulations depends on environment construction, including both scene structure and material classification. However, existing RT studies rely on manual material segmentation and presuppose idealized material parameters, which highly overlooks critical challenges of material recognition from real-world data. This prevents RT from being applied in complex scenarios and leads to inaccurate simulation results. To address this issue, we use point cloud measurements to capture real-world environment information and propose a dual-branch network based on PointNet model to automatically classify environmental materials by integrating point cloud data and LiDAR-derived feature parameters. The proposed network significantly enhances material classification accuracy within complex scenes, thereby delivering more precise and computationally efficient input data for RT simulations. Furthermore, we analyze influence of material recognition accuracy on simulation parameters, such as path loss and delay spread. The results demonstrate that the proposed network achieves high classification performance and meets accuracy requirements of RT, thereby contributing to more realistic and reliable predictions for wireless systems. This approach lays a crucial foundation for development of environment-aware models for 6G networks, enabling more effective simulation of outdoor communication environments.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5878-5890"},"PeriodicalIF":7.0,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Edge AI-Enabled Backbone Optimization for Real-Time Object Detection in Computing Power Networks","authors":"Minhyeok Jang;Jalel Ben-Othman;Hyunbum Kim","doi":"10.1109/TCCN.2026.3659849","DOIUrl":"10.1109/TCCN.2026.3659849","url":null,"abstract":"Object detection is a fundamental task in computer vision with broad applications in autonomous transportation driving, smart surveillance, and traffic monitoring. In the context of Computing Power Networks (CPNs), which interconnect cloud, edge, and terminal nodes to support distributed AI services, deploying efficient object detection models under constrained computational resources is a critical challenge, particularly at the edge and terminal layers. This study investigates backbone optimization for the YOLOv11M object detection framework to improve computational efficiency while maintaining detection performance. We propose two lightweight variants, YOLOv11M-MN and YOLOv11M-Shuffle, by replacing the original backbone with MobileNetV3-Small and ShuffleNetV2, respectively. All Edge AI-enabled models share an identical detection head and training pipeline to ensure fair and controlled comparisons. To reflect resource-limited CPN environments, all experiments are conducted under CPU-only settings with staged training budgets. Performance is evaluated using the COCO128 dataset in terms of FLOPs, parameter count, inference latency, and detection accuracy. Experimental results demonstrate that the proposed lightweight backbones significantly reduce computational overhead and inference time, while exhibiting different accuracy–efficiency trade-offs, highlighting their suitability for selective deployment across heterogeneous CPN layers.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5891-5902"},"PeriodicalIF":7.0,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Directional Differentiable Architecture Search for Waveform Recognition","authors":"Xuemin Sun;Qing Wang;Xiaofeng Liu;Zhiming Zhan;Haozhi Wang;Qi Chen;Yifang Zhang","doi":"10.1109/TCCN.2026.3658773","DOIUrl":"10.1109/TCCN.2026.3658773","url":null,"abstract":"Waveform recognition is used to identify classes of different electrical signal waveforms. It is widely used in medical diagnosis, wireless communication, signal video processing, audio processing, and other fields. However, conventional approaches to waveform recognition perform poorly under low signal-to-noise ratio conditions and with easily confusable signals of different types. To address this challenge, we introduce automatic machine learning (AutoML) into the waveform recognition task to automatically obtain a high-performance recognition network. Among AutoML, Differentiable Neural Architecture Search (DARTS) has been widely used due to its short training time, low hardware requirements, and efficient neural networks generation ability. However, DARTS cannot guide the sparsity of the architecture parameters, leading to performance loss in discretization. To this end, we propose an end-to-end trainable evolutionary method called Directional Differentiable Architecture Search (DDAS) in this paper. First, during the architecture search, the training data is augmented with more easily confusable signals samples to enhance the model’s ability to distinguish ambiguous patterns. Second, the soft-max function delays the non-zero-is-one operation selection to a weighted sum of the different operations. This makes the operation architectural parameters differentiable and greatly reduces the training cost. Third, a directional pruning-based optimization method is used to bring the highest weight of operations closer to 1 to reduce discretization loss, where the operation with the highest weight is selected as the final operation in the generated network. Experiments on two benchmark waveform recognition datasets show that the resulting network outperforms both the traditional manually designed network and the network obtained by directly applying existing architectural search methods, achieving higher accuracy. The obtained network also has a higher ability to recognize easily confusable signals. Notably, the generated network performance performs equally well under all signal-to-noise (SNR) ratios, offering new insights for waveform recognition. Code and datasets are available on <uri>https://github.com/tju-xm/DDAS</uri>.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"6309-6319"},"PeriodicalIF":7.0,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Cognitive Underwater Acoustic Networking and Target Tracking: A Comprehensive Survey","authors":"Zhong Yang;Zhengqiu Zhu;Yong Zhao;Yonglin Tian;Changjun Fan;Runkang Guo;Wenhao Lu;Jingwei Ge;Bin Chen;Yin Zhang;Guohua Wu;Rui Wang;Guangquan Cheng;Jincai Huang;Zhong Liu;Jun Zhang;Imre J. Rudas","doi":"10.1109/TCCN.2026.3658820","DOIUrl":"10.1109/TCCN.2026.3658820","url":null,"abstract":"Underwater acoustic networks are evolving from static, manually-configured systems into cognitive, learning-enabled platforms that can perceive, reason, and adapt to harsh ocean dynamics in real-time. Accurate target tracking is a core service of these networks and underpins marine resource exploration, environmental monitoring, and maritime security. Existing reviews or surveys, however, rarely examine underwater acoustic target tracking through the lens of cognitive communications and networking, and often offer a narrow perspective on addressing the paradigm shifts driven by emerging technologies like deep learning. To fill this gap, this work presents a systematic survey of this field and introduces an innovative three-dimensional taxonomy framework based on the three levels of the cognitive underwater acoustic target tracking network: the target layer, the perception layer, and the processing layer. Within this framework, we comprehensively survey the literature over the period 2016-2025, spanning from the theoretical foundations to diverse algorithmic approaches in underwater acoustic target tracking. Particularly, we emphasize the transformative potential and recent advancements of machine learning techniques, including deep learning and reinforcement learning, in enhancing the performance and adaptability of cognitive underwater tracking systems. Finally, this survey concludes by identifying key challenges in the field and proposing future avenues based on emerging technologies such as data desensitization, embodied intelligence, and large models.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5913-5936"},"PeriodicalIF":7.0,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146070223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"LAMIO-6G: Large AI Model-Empowered Cross-Layer Intent Management and Multi-Domain Policy Orchestration in 6G Terrestrial Networks","authors":"Yao Wang;Chungang Yang;Qiao Li;Pu Wang;Sai Zou;Bodong Shang;Shoufeng Wang","doi":"10.1109/TCCN.2026.3658750","DOIUrl":"10.1109/TCCN.2026.3658750","url":null,"abstract":"As differentiated services emerge, intent-driven management and orchestration in the 6G terrestrial networks will face two key challenges. On the one hand, the intent mapping gap, limited orchestration flexibility, and lack of policy abstraction constrain intent refinement across the Business Support System, Operation Support System, and Network Operation Provider layers. On the other hand, multi-domain orchestration among the radio access, transport, and core networks remains hard due to limited global awareness, resource conflicts, and inconsistent policy models. In this paper, we present LAMIO-6G, a large AI model-empowered framework for cross-layer intent management and multi-domain policy orchestration, which autonomously generates policies at different levels of abstraction from intents. The LAMIO-6G incorporates two key models: (<inline-formula> <tex-math>$i$ </tex-math></inline-formula>) a unified network policy model and (ii) a monitor-analyze-plan-execute-knowledge feedback closed-loop model. To address limited intent generality and scenario generalization in the Business Support System layer, we then introduce intent decomposition techniques via generic large AI models using low-rank adaptation-based fine-tuning, design of intent decomposition prompts, and few-shot learning-assisted intent decomposition. Within the Operation Support System layer, we design an intent reasoning and optimization scheme through collaboration between domain-specific large AI models guided by long-short chain-of-thought techniques and lightweight proximal policy optimization model. Finally, we present a proof-of-concept implementation of a wireless energy-saving intent. Simulation results demonstrate that the DeepSeek-R1-14B model achieves 17% to 30% gains over all baseline schemes in fine-tuned metrics, intent decomposition and reasoning accuracy, and intent optimization performance.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"6221-6236"},"PeriodicalIF":7.0,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146070281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Attention-Based Spatial-Temporal GCN for Sensing-Aided Beam Prediction in RIS-Assisted ISAC Systems","authors":"Jianzheng Li;Weijiang Wang;Rongkun Jiang;Xinyi Wang;Zesong Fei;Shiwei Ren","doi":"10.1109/TCCN.2026.3658751","DOIUrl":"10.1109/TCCN.2026.3658751","url":null,"abstract":"Integrated sensing and communications (ISAC), recognized as a key technology of the sixth-generation (6G) communication system, simultaneously attends to dual functionalities of communication and sensing. This paper introduces a reconfigurable intelligent surface (RIS)-assisted two-stage ISAC system. The system utilizes uplink pilots to achieve sensing-assisted communication and implements predictive optimal beamforming to maximize the multi-slot system sum-rate. Conventional beamforming algorithms predominantly rely on perfect or estimated channel state information (CSI), which is idealistic or requires a large pilot overhead, making it unaffordable in mobile user scenarios. To address this challenge, this paper proposes a fusion framework named TD3-SATGCN, which integrates deep reinforcement learning (DRL) with an attention-based spatial-temporal graph convolution network (SATGCN) for non-convex joint beamforming. The proposed framework implicitly captures the spatial features from sensed user trajectories and pilots, which are further mapped into beamforming solutions in multi-slots without explicit CSI estimation. Furthermore, the poor generalization of artificial intelligence (AI)-based algorithms has hindered their deployment in communication systems. This article converts communication systems into graph topologies, harnessing the permutation/equivariance properties of GCNs to enhance generalizability. Simulation results under various scenarios indicate that the TD3-SATGCN reduces pilot overhead by 25% and achieves up to a 13.52% improvement in the system sum-rate compared to benchmarks without CSI.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"6119-6134"},"PeriodicalIF":7.0,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146070221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"TrustPKBG: Trustworthy Protocol Knowledge Blueprints Generation via LLM for Low-Altitude AAV Networks","authors":"Fan Wu;Yuxin Zhang;Gaolei Li;Jianhua Li;Jin Ma","doi":"10.1109/TCCN.2026.3658765","DOIUrl":"10.1109/TCCN.2026.3658765","url":null,"abstract":"In low-altitude networks, reliable and lightweight flight interconnection among AAVs mainly depends on protocols like Message Queuing Telemetry Transport (MQTT). However, existing protocol analysis methods often fail to adapt to unknown program functions caused by version updates due to a lack of protocol knowledge blueprints (PKB). Moreover, due to the lack of multiple rounds of verification in terms of grammar semantics and execution logic representation, the correctness, validity and credibility of the generated PKB in practical scenarios remain questionable. To address these challenges, this paper proposes a novel trustworthy protocol knowledge blueprints generation (TrustPKBG) framework for low-altitude AAV networks by large language model (LLM). In TrustPKBG, a Hierarchical Chain-of-Thought (HCoT) strategy is designated to automatically transform technical specifications into a structured, objective, and consistent PKB draft against the bias of human construction. Moreover, to enhance the abstract semantic similarity between PKB drafts and RFC documents, a memory-aware multi-agent collaboration mechanism is also presented, which enables closed-loop error detection and knowledge updating. To demonstrate the superiority of TrustPKBG, we also implement a Fuzzing-based PKB Verifier over MQTT/CoAP. Experimental results demonstrate that fuzzing with TrustPKBG can achieve an average code coverage rate of 33.71% for MQTT and 33.5% for CoAP, which is 50.83% higher than the baseline average coverage rate of 22.35% for MQTT and 27.6% for CoAP, with a valid test ratio of 74.57% for MQTT and 62.3% for CoAP. Furthermore, we explore PKB’s application in protocol code auditing by evaluating open-source MQTT and CoAP implementations for compliance verification, which demonstrate the effectiveness of the proposed methods.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"6152-6174"},"PeriodicalIF":7.0,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146070257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Binary Waveform Design for Spectrally-Compatible Cognitive MIMO Radar DOA Estimation","authors":"Kai Zhong;Jinfeng Hu;Dongxu An;Huan Wan;Yiran Zhang;Xin Tai;Yongfeng Zuo;Ye Yuan;Cunhua Pan;Kah Chan Teh;Xianxiang Yu;Huiyong Li;Guolong Cui","doi":"10.1109/TCCN.2026.3658760","DOIUrl":"10.1109/TCCN.2026.3658760","url":null,"abstract":"Unimodular waveform design is a key technology in cognitive Multiple Input Multiple Output (MIMO) radar systems. Existing research mainly includes two categories: unimodular continuous/binary waveform design for detection, and unimodular continuous waveform design for Direction of Arrival (DOA) estimation without spectral constraints. Different from existing methods, our focus lies in investigating unimodular binary waveform design for DOA estimation within spectrally crowded environments. This problem is formulated as minimizing the mean square error (MSE) for DOA estimation, subject to the constraints of binary waveform and multiple spectral constraints. Due to the spectral constraint and nonconvex nature of the binary waveform constraint, the problem is NP-hard and challenging to solve directly. Fortunately, we observe that the problem can be decomposed into multiple more tractable subproblems by introducing auxiliary variables. Leveraging this characteristic, we propose an efficient Problem Decomposition-based Sequential Optimization (PDSO) method to tackle this problem. The method introduces two auxiliary variables to decompose the problem into two subproblems: one of which can be solved in closed-form, while the other is efficiently addressed by the Binary Alternating Directions Method of Multipliers (B-ADMM) algorithm. Compared to the existing methods, the proposed approach demonstrates superior performance in terms of computational cost, DOA resolution, and suppression of spectral interference.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5937-5952"},"PeriodicalIF":7.0,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146070256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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-Band Spectrum Prediction Algorithm Based on HGCN and Simplified ReLU-GRU","authors":"Lingzhao Zhang;Qin Wang;Haotian Chang;Haitao Zhao;Hongbo Zhu","doi":"10.1109/TCCN.2026.3657092","DOIUrl":"10.1109/TCCN.2026.3657092","url":null,"abstract":"The increasing scarcity of spectrum resources, coupled with rising demand, has made effective spectrum management crucial. However, the complexity and spatio-temporal variability of spectral data present significant challenges for accurate spectrum prediction. This paper proposes a novel multi-band spectrum prediction model that integrates a hypergraph convolutional neural network (HGCN) with a simplified rectified linear unit-gated recurrent unit (ReLU-GRU) network which eliminate the reset gate. In this framework, the HGCN employs hypergraphs to represent spectral data, where nodes correspond to individual frequency bands and hyperedges capture multivariate relationships among them. The simplified ReLU-GRU is used to model the temporal dependencies between frequency bands, effectively fusing the extracted features for enhanced prediction performance. By replacing the traditional hyperbolic tangent (tanh) activation function with a linear rectification function (ReLU) in the state update process, the model mitigates the issue of gradient vanishing and accelerates the training process. To further improve convergence, an attention mechanism is incorporated to weight the output of hidden states. Experimental evaluation on a real-world spectral dataset from sensors in St. Gallen demonstrates that the proposed model achieves a 4.43% improvement in prediction accuracy compared to the traditional LSTM model and a 0.56% improvement over the GCN-GRU model, exhibiting superior stability. The results also show that the simplified ReLU-GRU is particularly effective in predicting highly variable data, outperforming the traditional tanh-GRU, especially in scenarios with significant fluctuations.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5903-5912"},"PeriodicalIF":7.0,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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-Source Trust Evaluation Using Physical Layer Authentication and Reinforcement Learning for Distributed AUV Swarms in Underwater Data Collection","authors":"Guangjie Han;Yaxin Hu;Yu He;Tongwei Zhang;Feiyan Li","doi":"10.1109/TCCN.2026.3657053","DOIUrl":"10.1109/TCCN.2026.3657053","url":null,"abstract":"Autonomous underwater vehicle (AUV) swarms are increasingly vital for large-scale underwater data collection. However, they are vulnerable to both external and internal attacks, including identity spoofing and selfish behaviors. To address these attacks, this paper proposes a novel trust evaluation mechanism, named PRLTE, which integrates Physical Layer Authentication (PLA) with Reinforcement Learning (RL). The mechanism comprises three core components: 1) trust calculation. Sink nodes collect multi-source trust evidence, including communication trust and energy trust. Furthermore, “work trust” evaluating data quality and quantity is introduced to mitigate the issue of insufficient historical trust evidence; 2) identity assessment. PLA under the Bellhop channel model is performed to authenticate agent identities and derive “identity trust;” and 3) trust evaluation. An RL-based trust evaluation mechanism is deployed to adaptively optimize trust component weights for agents based on identity trust. Simulation results demonstrate that PRLTE outperforms existing mechanisms in detecting malicious agents, with superior performance across both dense and sparse deployment scenarios.","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"12 ","pages":"5537-5551"},"PeriodicalIF":7.0,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146042795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}