{"title":"Privacy-Preserving Personalized Decentralized Learning With Fast Convergence","authors":"Jing Qiao;Zhenzhen Xie;Zhigao Zheng;Xiao Zhang;Zhenyu Zhang;Qun Zhang;Dongxiao Yu","doi":"10.1109/TCE.2024.3475370","DOIUrl":"https://doi.org/10.1109/TCE.2024.3475370","url":null,"abstract":"Personalized decentralized learning aims to train individual personalized models for each client to adapt to Non-IID data distributions and heterogeneous environments. However, the distributed nature of decentralized learning is insufficient for protecting client training data from gradient leakage danger. In this paper, we investigate a \u0000<underline>p</u>\u0000rivacy-preserving \u0000<underline>p</u>\u0000ersonalized \u0000<underline>d</u>\u0000ecentralized \u0000<underline>l</u>\u0000earning optimization mechanism instead of traditional SGD. We design the P2DL mechanism to optimize our proposed objective function, whereby adjusting the regularization term parameter for a resilient local-global trade-off. Instead of exchanging gradients or models, auxiliary variables with knowledge can be transferred among clients to avoid model inversion and reconstruction attacks. We also provide theoretical convergence guarantees for both synchronous and asynchronous settings. Particularly, in case of synchronous communication, its convergence rate \u0000<inline-formula> <tex-math>$mathcal {O}left ({{{}frac {1}{k}}}right)$ </tex-math></inline-formula>\u0000 matches with the optimal result in decentralized learning, where k is the number of communication rounds. Extensive experiments are conducted to verify the effectiveness of newly proposed P2DL comparing with the state of the arts.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6618-6629"},"PeriodicalIF":4.3,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918223","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":"Zippy Random Access Protocol for Critical Data Transmission in Consumer Healthcare Applications","authors":"Ambigavathi Munusamy;Mainak Adhikari","doi":"10.1109/TCE.2024.3472118","DOIUrl":"https://doi.org/10.1109/TCE.2024.3472118","url":null,"abstract":"Nowadays, consumer electronic devices have transformed the healthcare industry from telemedicine to accurate remote patient monitoring. This digital transformation helps to monitor patients and provide timely diagnoses with minimum delay. In such time-sensitive healthcare applications, short-range communication protocols always play a crucial role from data collection to the data computation phase. However, the traditional protocols fail to handle concurrent transmissions of time-critical data from multiple sensor nodes. Due to an inefficient backoff algorithm with a predefined contention window size, these protocols could not simultaneously allocate the time slots to more than one critical sensor node over a common channel. Further, it can increase the delay when two or more sensor nodes with critical data choose the same random backoff counter values and try to access the medium along with other non-critical nodes. To mitigate all these issues, this work aims to design a novel Zippy Random Access Protocol (ZRAP) using an Emergency Lookup Table (ELT) to dynamically assign and adjust the backoff counter values and effectively minimize the backoff value conflicts among the sensor nodes. The extensive simulation results show that the proposed ZRAP outperforms the state-of-the-art random-access protocols in terms of delay, failure probability, collision rate, reliability, and throughput.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6560-6567"},"PeriodicalIF":4.3,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918490","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":"Development of Realtime Co-Simulation Platform Harnessing Consumer Energy Flexibility Through an Aggregator to Provide Grid Support","authors":"Noman Shabbir;Roya Ahmadiahangar;Argo Rosin;Jako Kilter;João Martins","doi":"10.1109/TCE.2024.3470241","DOIUrl":"https://doi.org/10.1109/TCE.2024.3470241","url":null,"abstract":"The integration of renewable energy resources and nearly zero energy buildings (nZEBs) into the grid requires a balance between demand and supply, which makes energy flexibility (EF) very important. There is a lack of tools to fully characterize EF and evaluate its performance in power systems in real-time. This paper fills research gaps related to EF implementation and evaluation in a real-time scenario and proposes a co-simulation tool for characterizing EF. In this study, a co-simulation tool to evaluate the impact of consumers EF managed by an aggregator in real-time is developed. The aggregator utilizes a non-intrusive load monitoring (NILM) method and the XgBoost algorithm, extracting information about consumer device usage patterns in nZEBs and non-nZEBs to establish EF. The co-simulation tool connects the aggregator in MATLAB with the IEEE 13-bus distribution system implemented in RTDS for real-time analysis. The aggregator provides grid support by regulating the adjustment of the shiftable loads and maintaining the operating frequency and voltage of the network. The real-time simulation results demonstrate the aggregator’s ability to reduce frequency deviations and provide grid support.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6641-6652"},"PeriodicalIF":4.3,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10699401","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Output-Power-Controllable Parity-Time-Symmetric Wireless Power Transfer System With Soft Switching for Kitchen Appliances","authors":"Lihao Wu;Bo Zhang;Yanwei Jiang","doi":"10.1109/TCE.2024.3470112","DOIUrl":"https://doi.org/10.1109/TCE.2024.3470112","url":null,"abstract":"In this paper, using dual-frequency modulation (DFM) and phase synchronization method (PSM), a flexible and controllable wireless power transfer (WPT) system with soft switching based on parity-time (PT) symmetry is proposed for kitchen appliances. Here, the system outputs can be regulated by configuring the number ratio of two modulation pulses with different frequencies, without the need for extra DC-DC converters or changing the duty cycle of the inverter. Moreover, a control method for generating and arranging the hybrid frequencies pulse sequence is proposed based on PSM to satisfy the condition of PT symmetry. Theoretical analysis indicates that a controllable output power insensitive to the coupling coefficient can be acquired only by relying on a single-stage inverter while maintaining soft-switching or zero-voltage switching (ZVS) operation, thereby reducing power losses and improving system cost-effectiveness and integration. Furthermore, dual-side communication can be eliminated. The results of the experiment confirm that a controllable stable output power with a constant coil-coil efficiency of 95.8% and a peak DC-to-load efficiency of 93.8% can be maintained within a lateral tolerance range of 0-14 cm.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6630-6640"},"PeriodicalIF":4.3,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918403","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":"Blockchain-Based Secure 5G/6G Communication for Internet of Things Devices in Consumer Electronic Systems","authors":"Lulwah M. Alkwai;Kusum Yadav","doi":"10.1109/TCE.2024.3454299","DOIUrl":"https://doi.org/10.1109/TCE.2024.3454299","url":null,"abstract":"In recent years, blockchain technology has gained prominence beyond cryptocurrencies, finding applications in smart grids and the Internet of Things (IoT). With advancements in AI and next-generation networks, IoT device applications have expanded, requiring high computational resources and reliable data transmission. This study explores the use of 5G/6G communication networks and network slicing to enhance IoT-enabled environments. We propose a model integrating blockchain-based context-aware user authentication, handover, and secure network slicing to manage load and secure data forwarding in 6G networks. Performance evaluations show that our model outperforms existing blockchain-based techniques. The proposed model improves latency by approximately 17.33% compared to the existing model.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 3","pages":"6327-6338"},"PeriodicalIF":4.3,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821237","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":"LALDM: A Multimodal Aspect Level Text Analysis Method and Its Application in Online Consumer Electronics","authors":"Rui Li, Liwei Shao, Lei La, Yi Yang","doi":"10.1109/tce.2024.3456792","DOIUrl":"https://doi.org/10.1109/tce.2024.3456792","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"206 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142258677","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":"ECCPM: An Efficient Internal Data Migration Scheme for Flash Memory Systems","authors":"Haihua Hu;Guojun Han;Wenhua Wu;You Zhou;Chang Liu","doi":"10.1109/TCE.2024.3459892","DOIUrl":"10.1109/TCE.2024.3459892","url":null,"abstract":"The copyback command can be used to accelerate data migration in solid-state drives. However, the reliability of this command is not guaranteed, posing challenges for broad utilization within the consumer electronics device. The existing algorithms for predicting the copyback threshold do not consider two issues: 1) Due to page/wordline restrictions restrictions, the accumulation of errors across pages during copyback operations is asymmetrical; and 2) The controller lacks prior knowledge about the raw bit error rate (RBER) before decoding. As a result, it is impossible to predict the frequency of copyback command execution. In this paper, we explore the mathematical models of flash programs and read operations. We further develop the state transition probability matrix for wordline-level data migration within the same plane. Therefore, we propose a predictive model for the maximum copyback threshold within the same plane. To address these two issues, we conduct tests and analyse the characteristics of error accumulation in copyback using actual chips and substitute the relative entropy of the state distribution in our prediction model for RBER. By integrating these insights, we introduce an estimated copyback count prediction model (ECCPM). The simulation results demonstrate that the ECCPM can significantly reduce latency while minimally impacting write amplification.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6519-6532"},"PeriodicalIF":4.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142258678","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":"Improved Shunt Active Filter for Non-Ideal Grid Using Model Predictive and Sliding Mode Control","authors":"Abinash Rath;Bhanu Pratap Behera;Basant Kumar Sethi","doi":"10.1109/TCE.2024.3460736","DOIUrl":"10.1109/TCE.2024.3460736","url":null,"abstract":"Filters have become almost indispensable to counter the harmonics injection by the widely used power converters and other non-linear devices. Shunt active power filters (SAPF) controlled by direct power control (DPC) serve as a good option as they offer various advantages. The performance of the existing controllers deteriorates when the three-phase supply system deviates from its ideal situation of balanced and sinusoidal voltages. Unlike the existing methods, this work develops and employs a detailed and accurate system model based on the extended pq theory. With its proven high accuracy, the model predictive control (MPC) is used as the control algorithm for PWM generation. An in-depth comparison between MPC and other predictive methods is presented, aiming to substantiate the superior performance of MPC. Furthermore, an adaptive sliding mode control-based reactive power reference is proposed to eliminate the steady-state error in the reactive power. The proposed controller’s feasibility is rigorously evaluated through meticulous MATLAB simulations and real-world laboratory experiments. Comparative analysis against existing SAPF controllers in similar conditions undeniably establishes better grid power quality by lowering source current THD and overall reactive power consumption.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"6600-6608"},"PeriodicalIF":4.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142258679","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":"Co-Training-Based Personalized Federated Learning With Generative Adversarial Networks for Enhanced Mobile Smart Healthcare Diagnosis","authors":"Arikumar K. Selvaraj;Sahaya Beni Prathiba;A. Deepak Kumar;R. Dhanalakshmi;Thippa Reddy Gadekallu;Gautam Srivastava","doi":"10.1109/TCE.2024.3460469","DOIUrl":"10.1109/TCE.2024.3460469","url":null,"abstract":"The widespread implementation of Artificial Itelligence (AI) has led to significant advancements in disease diagnosis. Personalized Federated Learning (FL) trains models tailored to each patient’s needs but often overlooks model architecture heterogeneity. We propose a novel Co-training-based personalized FL with Generative Adversarial Networks (GANs) for Smart Healthcare Diagnosis (CFG-SHD). This approach allows privacy-preserving participation in FL by enabling patients to keep their model architectures and parameters private. Key contributions include integrating co-training into FL for leveraging multiple data views and using GANs to generate synthetic data, ensuring data privacy. By addressing model architecture heterogeneity our approach offers a robust solution for personalized healthcare diagnostics, aligning with the diverse needs of modern healthcare systems and advancing patient-centric AI applications. CFG-SHD enhances personalized diagnosis accuracy, achieving 97.16%, 98.04%, and 97.88% on the PAD-UFES-20, HAM10000, and PH2 datasets, respectively.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 3","pages":"6131-6139"},"PeriodicalIF":4.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142258684","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}