IEEE Transactions on Consumer Electronics最新文献

{"title":"SQLLM: A Secure and Quantized Framework for Large Language Models in 5G Private Network Operations","authors":"Jian Ma;Tong Liu;Yimeng Shang;Nan Hu;Lei Xia;Peizhen Liao;Yitong Shang","doi":"10.1109/TCE.2026.3657983","DOIUrl":"https://doi.org/10.1109/TCE.2026.3657983","url":null,"abstract":"With the development of 5G technology, the demand for large language models (LLMs) in private network operation and maintenance is growing. These models enhance the intelligence and efficiency of network management through deep learning techniques. However, the application of LLMs for 5G private network operation and maintenance faces the dual challenges of data security and resource limitations. To address these challenges, we propose SQLLM, which is an integrated framework dedicated to detecting abnormal user query-based network attacks and performing high-quality compression on large language detection models for network attacks. Specifically, leveraging the powerful representational capacity of large language models, we utilize the LoRA fine-tuning technique to identify normal questions and three types of attack questions, thus avoiding behaviors that attempt to disrupt or obtain sensitive information. Moreover, this research innovatively adopts the static quantization technique to compress LLMs for private network operation and maintenance. Unlike traditional static quantization that uses fixed parameters and uniform granularity for activations, our optimized strategy introduces a dynamic smoothing factor <inline-formula> <tex-math>$alpha $ </tex-math></inline-formula> to transfer outlier variance from activations to weights and adopts a hybrid per-tensor/per-token granularity tailored to 5G O&M data, thus avoiding the challenge of the sharp decline in the inference ability of the quantized LLM caused by outliers, enabling it to adapt to resource-constrained and multi-user concurrent usage environments. Finally, we validate four types of questions and evaluate the performance of the quantized model on key performance indicators such as accuracy, VRAM consumption, and inference time. The experimental results demonstrate that the SQLLM model achieves excellent performance on all test indicators. This achievement proves the security and feasibility of the efficient deployment of LLMs for private network operation and maintenance in the 5G private network environment with network attacks and resource limitations.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7552-7564"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Secure and Interference-Resilient mmWave Consumer Links Using a Compact SIW Leaky-Wave MIMO Antenna With Common-Radiator Design","authors":"Sultan Shoaib;Iftikhar Ahmed;Riqza Y. Khattak;Raza Ali Shah;Nosherwan Shoaib","doi":"10.1109/TCE.2026.3665762","DOIUrl":"https://doi.org/10.1109/TCE.2026.3665762","url":null,"abstract":"A compact and reliable multiband leaky-wave antenna (LWA) based on substrate integrated waveguide (SIW) is proposed for millimeter-wave (mmWave) consumer devices. The antenna employs slant rectangular slots oriented at ±45° to enable frequency-dependent beam scanning while maintaining high radiation efficiency. A common-radiator <inline-formula> <tex-math>$4times 4$ </tex-math></inline-formula> MIMO architecture is introduced in which radiating slots are shared between the opposite excitation ports to achieve independent backward and forward beam scanning while reducing size and structural complexity. This configuration provides a total angular scanning range of approximately 120° without the need for additional beamforming networks. The proposed antenna operates over multiple millimeter-wave frequency bands ranging from 37 to 54 GHz thereby covering 5G NR n259, n260 and n262. Measurements demonstrate peak realized gain between 9.5 and 13.5 dBi, radiation efficiency of up to 75% and port isolation better than 22 dB for adjacent ports and 30 dB for the opposite ports. Excellent MIMO performance is achieved with an envelope correlation coefficient below 0.01 and a diversity gain closer to 10 dB. These results confirm the suitability of the proposed antenna for compact mmWave platforms requiring high-capacity, interference-resilient and reliable wireless links.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7565-7578"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Self-Supervised Topology-Aware Skeleton Masking for Robust Human Action Recognition","authors":"Yanxin Cui;Jinlong Wang;Jiahui Yu;Gaoxiang Ouyang;Zhaojie Ju","doi":"10.1109/TCE.2025.3643489","DOIUrl":"https://doi.org/10.1109/TCE.2025.3643489","url":null,"abstract":"Self-supervised representation learning has become critical for addressing the annotation bottleneck in skeleton-based human action recognition on consumer electronics devices. However, most existing methods adopt a spatio-temporal decoupled training paradigm, which neglects the inherent synergy between a skeleton’s spatial topology and its temporal dynamics. Even recent hierarchical approaches fail to capture cross-level associations fully, limiting overall performance. To address these challenges, we propose a Topology-aware Spatio-Temporal Interaction Contrastive Network (TSI-CNet) within a self-supervised framework. Topology-driven spatial masks quantify joint centrality in the skeleton graph to prioritize highly connected nodes. Motion-driven temporal masks dynamically select high-change frames based on inter-frame motion magnitude. A dual-branch decoupling–interaction architecture further disentangles spatial and temporal features and achieves semantic fusion through a cross-domain alignment loss. Extensive experiments on five public datasets show that TSI-CNet achieves competitive performance with a lightweight design. The results confirm the effectiveness of the proposed topology- and motion-driven masking strategies, and ablation studies further validate the contributions of individual components. Robustness evaluations under seven simulated real-world perturbations also highlight the method’s resilience to spatial and temporal disturbances, underscoring its suitability for consumer applications such as smart cameras, AR/VR devices, and service robots.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5282-5293"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Reliability-Guided Consistency Learning for Robust Semi-Supervised Semantic Segmentation","authors":"Qiaoling Xiong;Guozhi Yan;Xiaolu Li;Ke Wang;Chunhui Liu;Kai Liu","doi":"10.1109/TCE.2026.3664484","DOIUrl":"https://doi.org/10.1109/TCE.2026.3664484","url":null,"abstract":"Semi-Supervised Semantic Segmentation (SSS) has emerged as an effective paradigm to reduce the reliance on dense pixel-wise annotations. However, existing pseudo-labeling approaches often suffer from instability and semantic inconsistency, particularly in complex consumer electronic environments where visual inputs are noisy and heterogeneous. To overcome these limitations, we propose a unified framework termed Reliability-Guided Consistency Learning (RGCL), which systematically enhances probabilistic stability and semantic reliability through temporally and spatially consistent supervision. At the core of RGCL lies the Variance-Guided Prior Augmentation (VGPA), which quantifies temporal prediction variance across training checkpoints to identify and weight reliable unlabeled samples, thereby constructing a stability-aware prior. Building upon this, the Dual-Stream Pseudo-Label Refinement (DSPL) module distills high-confidence pseudo-labels from the variance-filtered subset and jointly optimizes them with labeled data in a dual-stream manner, promoting boundary accuracy and structural coherence. To further regularize the predictive manifold, the Interpolation Consistency Regularization (ICR) enforces geometric smoothness by coupling interpolation in the input domain with consistency in the predictive space, ensuring local continuity and mitigating spurious confidence transitions. By jointly addressing temporal uncertainty, semantic reliability, and manifold smoothness, RGCL establishes a reliability-driven learning paradigm for semi-supervised segmentation. Extensive experiments on Cityscapes, Pascal VOC, and ADE20K benchmarks demonstrate that RGCL consistently achieves state-of-the-art performance under various label ratios, confirming its robustness and effectiveness for deployment in consumer electronic applications.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6097-6108"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Reinforcement-Learning-Based Edge Caching for IoT in Compute-First Networks","authors":"Hamid Asmat;Ikram Ud Din;Ahmad Almogren;Joel J. P. C. Rodrigues","doi":"10.1109/TCE.2025.3574153","DOIUrl":"https://doi.org/10.1109/TCE.2025.3574153","url":null,"abstract":"6G networks require ultra-low latency and intelligent resource management in IoT environments. Compute-First Networking (CFN), integrating distributed computing and edge caching, addresses backhaul congestion. This paper proposes CaRL, a DRL-based caching framework using TD3 algorithm. CaRL optimizes cache placement at edge nodes by incorporating real-time network state, content popularity, and resource utilization. Simulations show CaRL improves cache hit ratio, reduces latency, and enhances bandwidth efficiency, and ensures secure caching decisions under dynamic network conditions. Unlike existing methods, CaRL adapts to dynamic network conditions by integrating latency, CPU, and memory metrics, demonstrating scalability and adaptability in CFN-driven 6G environments.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6526-6533"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"One Modality is Enough: Multi-Modal Backdoor Attacks via Prototype-Based Modality Rebalancing and Data Selection","authors":"Bo Liu;Yingnan Guo;Shun Wang;Shaofeng Zhao;Haokun Zheng;Haojie Huang;Jing Yang;Yuan Gao;Xiaokang Wang;Zhigao Zheng","doi":"10.1109/TCE.2026.3675597","DOIUrl":"https://doi.org/10.1109/TCE.2026.3675597","url":null,"abstract":"Multi-modal deep learning has become the backbone of modern consumer electronics (CE), enabling seamless interaction in devices like smart security systems and health monitors. However, this also introduces new attack surface. While existing backdoor research focuses on uni-modal scenarios, successfully planting triggers on every modality is often blocked by the physical or protocol-driven constraint in practical CE environments. In response, we focus on a more challenging yet realistic threat model where the attacker has limited control and can only manipulate a single input modality to activate the backdoor. To address this, we introduce “prototype”, which represents each class in the embedding space, and propose a prototype-based modality rebalancing backdoor training method that stimulates specific modalities with poor backdoor learning performance. However, modality rebalancing inevitably introduces extra computation costs. Therefore, we reuse the computational elements of the prototype and propose a poisoning training data selection strategy based on the distance between the boundary samples group and poisoning samples, which can greatly save computational costs. Experimental results show that our attack success rate with a single weak modality’s trigger exceeds the latest multi-modal attack competitor by over 20% on average at the same poisoning rate.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6109-6119"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Det2Pose: Lightweight Visual Sensing and Computation Framework for 3D Perception in Consumer Autonomous Intelligent Systems","authors":"Shi Feng;Jintong Cai;Huimin Lu;Zijiang Zhang;Yujie Li","doi":"10.1109/TCE.2026.3689218","DOIUrl":"https://doi.org/10.1109/TCE.2026.3689218","url":null,"abstract":"With the growing use of embedded intelligent systems in smart homes, service robots, and AR/VR devices, there is an increasing need for accurate 3D visual perception under low-power constraints. In consumer autonomous intelligent systems (AIS), 3D perception is typically realized through object detection followed by 6D pose estimation, yet achieving both efficiently on resource-constrained platforms remains challenging. This work presents Det2Pose, a lightweight, multi-stage visual sensing and computation framework designed for embedded deployment. It integrates a compact 2D detector (LiteDet) for real-time object localization with an efficient 6D pose estimation network (CurvePose) for robust spatial prediction, forming a unified pipeline for consumer 3D perception. Experiments on the ICD-4 industrial component dataset show that Det2Pose outperforms existing methods in both detection and pose accuracy, while maintaining real-time performance on low-power devices such as the Jetson Xavier NX. We additionally evaluate generalization in consumer-like settings, observing consistent accuracy and on-device real-time throughput. These results highlight its suitability for consumer applications, offering a practical approach to lightweight visual sensing and computation for 3D perception.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6288-6298"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Distributed Data-Driven Economic MPC for Frequency Regulation and Power Sharing of Microgrids","authors":"Panxiao Yong;Yubin Jia;Changyin Sun","doi":"10.1109/TCE.2026.3669368","DOIUrl":"https://doi.org/10.1109/TCE.2026.3669368","url":null,"abstract":"This paper proposes a data-driven distributed economic model predictive control (EMPC) strategy for load dispatch and frequency regulation in microgrids. To address the nonlinearity introduced by inverter-interfaced distributed generators (DGs), a distributed Koopman approach is employed to achieve global linearization of the complex system dynamics. Based on this linear model, a distributed EMPC controller is designed to simultaneously optimize frequency stability and economic load dispatch. The controller is solved in real time via a synchronized iterative Alternating Direction Method of Multipliers (ADMM), ensuring both computational efficiency and subsystem autonomy. Simulation results demonstrate the effectiveness and superiority of the proposed method in terms of dynamic performance and operational economy.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6407-6416"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Distributed Consensus of Lipschitz Nonlinear Multiagent Networks Under DoS Attacks: A Strict Zeno-Free Event-Triggered Approach","authors":"Weizhao Song;Dawei Zhao;Lijuan Xu;Xin Li;Fenghua Tong","doi":"10.1109/TCE.2026.3669225","DOIUrl":"https://doi.org/10.1109/TCE.2026.3669225","url":null,"abstract":"Aiming to address the distributed consensus issues for Lipschitz nonlinear multiagent systems suffering from DoS attacks, this work develops a novel distributed event-triggered secure control (DETSC) schemes that achieve leader-follower consensus with fully distributed, strict Zeno-free manners. First, a distributed secure control scheme is proposed. A novel adaptive couple parameter, two kinds of state observers, and the distributed event-triggered mechanism working in tandem with the control scheme are further raised. For the elimination of global information reliance, the adaptive couple parameter with exponential term is designed, which helps in classifying Lyapunov function behavior separately in attack and normal intervals. Zeno behavior is excluded strictly by designing the upper limit and decay rate of the event-triggered function (ETF). By constructing a Lyapunov function incorporating both the exponential term and decay rate of the ETF, the time blocking caused by DoS attacks in stability analysis is overcome. Zeno-freeness analysis gives the strict positive minimum inter-event interval. Finally, the capability of the proposed DETSC scheme is tried out through the numerical simulations on a group of single-joint robotic arms.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6396-6406"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Generative Spatio-Temporal Graph Network for Long-Range Urban Mobility Prediction","authors":"Yangyan Zeng;Shen Yu;Gaoyi Deng;Yi Yang;Wei Liang;Xu Zhang;M. Jamal Deen;Xiaokang Zhou","doi":"10.1109/TCE.2026.3656431","DOIUrl":"https://doi.org/10.1109/TCE.2026.3656431","url":null,"abstract":"The integration of intelligent transportation systems with next-generation consumer electronics, ranging from electric vehicles to autonomous navigation tools, has created an urgent need for reliable, long-range urban mobility prediction. However, the accuracy of existing models degrades over extended horizons due to compounding errors and an inability to adapt to dynamic, evolving traffic patterns. To address this, we propose the Generative Spatio-Temporal Graph Network (G-STGN), a novel deep learning framework that synergistically integrates learnable temporal decomposition with conditional generative adversarial networks (cGAN) for stable, long-horizon forecasting. Our architecture first purifies complex traffic signals using a learnable multi-scale temporal decomposition mechanism, which adaptively separates flow data into interpretable trend, periodic, and residual components. A dynamic graph spatio-temporal encoder then models each component with tailored, evolving graph structures to capture nuanced network dependences. The core innovation is a generative prediction enhancement framework, where a cGAN learns the macroscopic distribution of future states. This provides a forward-looking guidance signal to proactively correct the step-by-step prediction process, effectively suppressing error propagation. Extensive experiments on major highway and urban mobility datasets confirm that G-STGN significantly outperforms five state-of-the-art baseline models. It achieves superior prediction accuracy, evidenced by substantially lower Mean Absolute Error and Root Mean Square Error, alongside faster and more stable convergence. This demonstrates the framework’s strong potential for reliable deployment in time-critical consumer electronics applications, paving the way for more efficient routing, improved energy management, and safer autonomous navigation systems.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"6924-6937"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}