IEEE Transactions on Consumer Electronics最新文献_第8页

Multiple-Copy Group Data Sharing Scheme With Integrity Auditing Function for Consumer Electronics 具有完整性审计功能的消费类电子产品多副本组数据共享方案

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-03-09 DOI: 10.1109/TCE.2026.3672187

Youtong Wang;Jinyong Chang;Ru Meng;Peiru Yang;Xia Zhou

{"title":"Multiple-Copy Group Data Sharing Scheme With Integrity Auditing Function for Consumer Electronics","authors":"Youtong Wang;Jinyong Chang;Ru Meng;Peiru Yang;Xia Zhou","doi":"10.1109/TCE.2026.3672187","DOIUrl":"https://doi.org/10.1109/TCE.2026.3672187","url":null,"abstract":"The proliferation of consumer electronics (CE), particularly IoT devices such as smart home hubs and in-vehicle systems, is generating massive amounts of user data, creating an urgent need for secure and manageable cloud storage solutions tailored for consumer technology environments. While cloud storage alleviates the burden on local devices and enables convenient data access, it introduces significant security concerns for consumer applications: potential data loss from cloud servers and unauthorized access during data sharing. Existing attribute-based encryption (ABE) implementations often suffer from low efficiency, which in turn leads to substantial storage overhead, while existing schemes seldom account for the organizational structures common in consumer scenarios—such as a family unit or a fleet of interconnected devices. This paper proposes an efficient data sharing mechanism with integrity auditing functionality for cloud storage. Specifically designed for such consumer-grade IoT environments, the mechanism combines flexible access control with multi-replica cloud storage to reduce the risk of data loss. We design a group manager (GM)-driven upload management subsystem to efficiently handle data uploads from organizational entities. Finally, security and performance analyses were conducted on the integrated system designed in this article. The results indicate that the proposed scheme has good security and strong performance advantages.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5495-5507"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837076","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}

引用次数: 0

Resilient Energy Management for Islanded Microgrids With Renewable Integration in Smart Consumer Applications 智能消费者应用中可再生能源集成孤岛微电网的弹性能源管理

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-04-21 DOI: 10.1109/TCE.2026.3686067

Vivek Narayanan;Bhim Singh

{"title":"Resilient Energy Management for Islanded Microgrids With Renewable Integration in Smart Consumer Applications","authors":"Vivek Narayanan;Bhim Singh","doi":"10.1109/TCE.2026.3686067","DOIUrl":"https://doi.org/10.1109/TCE.2026.3686067","url":null,"abstract":"This paper presents a resilient and consumer-oriented control framework for optimizing the performance of islanded microgrid powered by sensorless wind and solar energy systems. An adaptive filtering technique is leveraged to address the challenges of renewable intermittency and voltage stability, crucial for reliable operation in consumer energy environments. Central to design is sensorless control of a switched reluctance generator (SRG) using an observer method, which accurately estimates rotor position and speed to maximize wind energy extraction. To enhance system robustness, traditional signum switching function is replaced with a saturation block, effectively eliminating chattering and improving computational efficiency. A battery energy storage system (BES) is integrated to stabilize power supply and to mitigate harmonic distortions caused by renewable fluctuations. In parallel, a solar photovoltaic array (SPVA) equipped with a peak power tracking algorithm ensures maximum solar energy harvesting. The use of a time-varying adaptive filter further improves voltage regulation at the point of common coupling (PCC), significantly enhancing overall microgrid stability. Proposed approach offers a sustainable, cost-effective, and resilient energy management solution, paving the way for intelligent, self-sustaining microgrids that can reliably meet the energy needs of remote and off-grid consumer communities.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5694-5705"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837212","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}

引用次数: 0

Functional Analysis and Convergence Dynamics of the Decoder-Only Transformer 纯解码器变压器的功能分析与收敛动力学

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-04-29 DOI: 10.1109/TCE.2026.3688624

Runsen Guan;Jiawei Wang;Lulu Sun;Choujun Zhan

{"title":"Functional Analysis and Convergence Dynamics of the Decoder-Only Transformer","authors":"Runsen Guan;Jiawei Wang;Lulu Sun;Choujun Zhan","doi":"10.1109/TCE.2026.3688624","DOIUrl":"https://doi.org/10.1109/TCE.2026.3688624","url":null,"abstract":"Transformers, as a class of fundamental neural networks with an Attention Mechanism, have contributed to sectors associated with Artificial Intelligence (AI) and provoked extensive discussion on their interpretability. The Transformer comprises two major components: the Encoder and the Decoder. Although the interpretability of the Transformer is often analyzed, the decoder-only Transformer lacks dedicated research on approximation theory, parameterized function space, and training hyperparameter settings. To fill the gap, this study establishes an approximation theory for the decoder-only Transformer by Functional Analysis and Measure Theory, characterizing the norm and the orthogonal bases of the parameterized function space. Furthermore, we introduce the concept of the probabilistic convexity of the loss function to investigate the upper bounds on the learning rate, which is crucial for the convergence analysis of the Gradient Descent (GD) and the Stochastic Gradient Descent (SGD) for the decoder-only Transformer. As a result, we derive a formula for the training epoch with respect to the prescribed loss with high probability, and substantiate it through explicit experiments. In essence, our study provides a concrete foundation for understanding the functional space construction and the convergence dynamics of the decoder-only Transformer, even when processing random inputs.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5780-5790"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837221","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}

引用次数: 0

A Privacy-Preserving Federated Learning Framework for Securing Consumer Health Wearables Against AI-Enabled Poisoning Attacks 保护消费者健康可穿戴设备免受人工智能中毒攻击的隐私保护联邦学习框架

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-03-11 DOI: 10.1109/TCE.2026.3673064

Ambarish G. Mohapatra;Anita Mohanty;Eatedal Alabdulkreem;Ibrahim Abunadi;Essa Alyounis;Somia A. Asklany;Nouf Atiahallah Alghanmi;Deepak Gupta

{"title":"A Privacy-Preserving Federated Learning Framework for Securing Consumer Health Wearables Against AI-Enabled Poisoning Attacks","authors":"Ambarish G. Mohapatra;Anita Mohanty;Eatedal Alabdulkreem;Ibrahim Abunadi;Essa Alyounis;Somia A. Asklany;Nouf Atiahallah Alghanmi;Deepak Gupta","doi":"10.1109/TCE.2026.3673064","DOIUrl":"https://doi.org/10.1109/TCE.2026.3673064","url":null,"abstract":"The popularity of consumer-friendly health wearables has provided fresh opportunities to AI-based personalized healthcare, but it also poses serious privacy and security threats. Federated Learning (FL) can be identified as a privacy-by-design framework, but due to its decentralisation, it can be susceptible to AI-based poisoning attacks that poison the global model. The existing Byzantine-robust defenses cannot typically perform well in the non-Independent and Identically Distributed (non-IID) and highly heterogeneous (wearable) data settings, where they falsely identify benign user data as malicious. This paper presents a new defense paradigm, which is a change in the focus of geometric anomaly detection to behavioural anomaly detection. We introduce a new tiered defense in the form of Robust Privacy-Preserving Federated Aggregation (RP-FedAgg), a combination of client-side Local Differential Privacy (LDP) and a two-step server-side filter. RP-FedAgg is resilient to a significant level when applied to human activity recognition when using wearable sensor data. On a simulated targeted label-flipping attack scenario with 30% malicious clients, our framework attains 91.33% accuracy and a low Attack Success Rate (ASR) of only 2.18, which is significantly better than standard FedAvg (92.45% ASR) and Krum (15.60% ASR) and also matches the privacy of users and the utility of the model.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7311-7318"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837329","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}

引用次数: 0

Boosting Knowledge Tracing With Structure-Preserving Adaptive Contrastive Learning 用保留结构的自适应对比学习促进知识追踪

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2025-08-04 DOI: 10.1109/TCE.2025.3595201

Shun Mao;Gang Li;Yuncheng Jiang

{"title":"Boosting Knowledge Tracing With Structure-Preserving Adaptive Contrastive Learning","authors":"Shun Mao;Gang Li;Yuncheng Jiang","doi":"10.1109/TCE.2025.3595201","DOIUrl":"https://doi.org/10.1109/TCE.2025.3595201","url":null,"abstract":"Knowledge tracing (KT) is a vital task in intelligent tutoring systems, aiming to assess learners’ knowledge states by analyzing their learning interactions. However, current KT research faces two significant challenges: (1) The exercise representations derived through Contrastive Learning (CL) often suffer from misguidance due to the use of random perturbations, and fail to capture long-distance dependencies that are closely related but distant within the knowledge structure. (2) The impact of learning efficiency on KT has not been adequately addressed. To address these issues, this paper proposed a novel KT model, named Cross-view contRastive leArning facilitatiNg Efficiency-aware knowledge tracing (CRANE). This model is designed to explore high-quality exercise representations and the impact of dynamically changing learning efficiency. Specifically, (1) to tackle the first challenge, a contrastive paradigm is introduced based on the generated relationship graphs to enhance the effectiveness of self-supervised signals, while an adaptive sampling method uncovers long-distance dependencies among exercises. (2) To address the second challenge, an efficiency gate is proposed to capture periodic learning gains, thereby quantifying learning efficiency and its impact on the learning process. Experiments on three common datasets demonstrate the superiority of our model and confirm the effectiveness of CRANE through visualization of exercise representations.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5258-5269"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148837372","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}

引用次数: 0

Quantum-Assisted Cyber-Forensic Techniques for Investigating Security Vulnerabilities in Smart Consumer Electronics 调查智能消费电子产品安全漏洞的量子辅助网络取证技术

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-02-18 DOI: 10.1109/TCE.2026.3666000

Surbhi B. Khan;K. M. Karthick Raghunath;T. R. Mahesh;Ahmed Alyahya;Fatima Asiri;Ahlam Almusharraf

{"title":"Quantum-Assisted Cyber-Forensic Techniques for Investigating Security Vulnerabilities in Smart Consumer Electronics","authors":"Surbhi B. Khan;K. M. Karthick Raghunath;T. R. Mahesh;Ahmed Alyahya;Fatima Asiri;Ahlam Almusharraf","doi":"10.1109/TCE.2026.3666000","DOIUrl":"https://doi.org/10.1109/TCE.2026.3666000","url":null,"abstract":"Smart home appliances are more susceptible to security threats with multiple cybersecurity vulnerabilities and thus end up leaking data, and failing to work. Existing forensic techniques fall short, and novel adaptive solutions are needed. This study introduces a novel Quantum-Driven Intrusion Detection and Anomaly Resolution (QIDAR) approach, which implements quantum computing fundamentals coupled with deep-learning hybrid analytics and blockchain-proof verification to discover intrusions of smart appliances and system failures. Further, in QIDAR, Quantum-Enhanced Cryptographic Logging (QECL) operates as QIDAR’s tamper-proof logging system through quantum cryptography to monitor anomalies extensively. Four fundamental processes from QIDAR enable the investigation of cyber incidents in smart appliances. Quantum-Assisted Anomaly Detection (Q-AAD) is based on integrating quantum operations into neural networks, which dynamically classify security risks. Adaptive Blockchain Ledger Forensics (ABLF) provides a secure method for storing forensic records using the blockchain as well as validating records through smart contracts. Multi-Modal AI Forensic Reconstruction (MMAFR) uses deep learning to rebuild cyberattacks from the past, allowing teams to predict threats and discover hidden data. Blockchain-Integrated Quantum Provenance Chain (BIQPC) is a quantum-secured forensic ledger that ensures traceability and non-repudiation of anomalies. QIDAR achieves exceptional achievements in consumer electronics, including 72% shorter forensic investigation duration as well as 98.5% efficient anomaly detection alongside a 67% superior data log tamper-resistance rate than traditional forensic methods.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7294-7302"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148925327","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}

引用次数: 0

A Low Sidelobe Virtual Array Beamforming Optimization Method for Smart Devices 一种智能设备低旁瓣虚拟阵列波束形成优化方法

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-03-08 DOI: 10.1109/TCE.2026.3691312

Lin Li;Hang Zhao;Wenbo Zhang;Junning Han

引用次数: 0

Dependent Task Offloading and Dynamic Load Balancing in Edge Computing Using Deep Reinforcement Learning With Consistent Hash 基于一致性哈希的深度强化学习边缘计算中的依赖任务卸载和动态负载平衡

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-03-11 DOI: 10.1109/TCE.2026.3691109

Jingyang Chen;Xiaohui Li;Yuemin Ding;Yi Wang;Bin Cai;Jin Liu;Jun Liu

{"title":"Dependent Task Offloading and Dynamic Load Balancing in Edge Computing Using Deep Reinforcement Learning With Consistent Hash","authors":"Jingyang Chen;Xiaohui Li;Yuemin Ding;Yi Wang;Bin Cai;Jin Liu;Jun Liu","doi":"10.1109/TCE.2026.3691109","DOIUrl":"https://doi.org/10.1109/TCE.2026.3691109","url":null,"abstract":"Multi-access edge computing is widely used to solve the problem of delay and energy consumption when deploying compute-intensive applications on user devices at the network edge. Optimizing offloading strategy for dependent tasks of user devices and load balancing of edge servers is crucial for multi-access edge computing. However, due to the limited computational resources of edge servers, reasonable offloading and allocation for dependent tasks is a great challenge in multi-access edge computing. To address this problem, this paper proposes an optimization approach for dependent task offloading and dynamic load balancing in edge computing using multi-agent soft actor-critic. The proposed approach designs the computing model and dependent task model by taking dependent task operational constraints and dynamic load balancing into account. Then the offloading strategy of dependent tasks is optimized to get lower delays and energy consumption by the multi-agent soft actor-critic integration with a kind of consistent hash-based load balancing mechanism. Simulation results show that the proposed approach has obvious advantages in terms of energy consumption of user devices, execution delay of tasks, and load balancing of edge servers.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"5884-5896"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836476","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}

引用次数: 0

An Ultra-Flat Cryogenic CMOS LNA With Pole-Aligning Technique and Robustness Against Conductivity Variation for Quantum Computing 量子计算中具有极对准技术和抗电导率变化鲁棒性的超扁平低温CMOS LNA

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-04-29 DOI: 10.1109/TCE.2026.3688836

Woong Joo Chang;Junhee Kwon;Geunyong Kim;Jaeho Shin;Hui-Dong Gwon;Joo-Hyung Chae;Kwang Ho Jang;Tae Hwan Jang

引用次数: 0

Protecting Consumer Healthcare Imaging Data From AI-Tampering via Blind Reversible Watermarking 通过盲可逆水印保护消费者医疗保健成像数据免受人工智能篡改

IF 9.9 2区计算机科学

IEEE Transactions on Consumer Electronics Pub Date : 2026-08-01 Epub Date: 2026-03-05 DOI: 10.1109/TCE.2026.3670869

Wei Min;Abdelkader Laouid;Mohammad Hammoudeh;Brahim Ferik;Farag Azzedin

{"title":"Protecting Consumer Healthcare Imaging Data From AI-Tampering via Blind Reversible Watermarking","authors":"Wei Min;Abdelkader Laouid;Mohammad Hammoudeh;Brahim Ferik;Farag Azzedin","doi":"10.1109/TCE.2026.3670869","DOIUrl":"https://doi.org/10.1109/TCE.2026.3670869","url":null,"abstract":"Medical images are increasingly processed across consumer-facing healthcare pathways—teleradiology portals, mobile viewers, MIoT and edge gateways. These images are vulnerable to tampering, privacy abuse, and AI-driven manipulation, such as GAN forgeries and adversarial perturbations, that can mislead diagnosis. We propose a blind, reversible watermarking framework that employs a rotation-invariant biometric fingerprint while preserving diagnostic fidelity through exact reconstruction. The approach generates an Orientation-Guided BSIF (OG-BSIF) signature, protects it with a lightweight FlexenTech permutation, and embeds it in the integer wavelet domain using an adaptive spread-spectrum strategy that combines STDM for robustness with Local Histogram Shifting (LHS) for bit-exact recovery. Experiments on multi-modal datasets, including CT, MRI, ultrasound, and X-ray, achieve high imperceptibility, with average PSNR > 54 dB, SSIM <inline-formula> <tex-math>$approx ~0.997$ </tex-math></inline-formula>, and perfect reversibility, with a reconstruction PSNR of 90.28 dB. OG-BSIF preserves > 99.9% of features under severe rotation, enabling reliable authentication, and the framework remains robust under FGSM and PGD perturbations, with sub-second execution supporting real-time deployment in consumer and point-of-care settings.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"72 3","pages":"7348-7361"},"PeriodicalIF":9.9,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148836428","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}

引用次数: 0