The Internet of Things (IoT) has proliferated ubiquitous information exchange between the physical and cyber worlds through consumer electronics, with a focus on moving computing power to edge terminals. Computing-in-memory (CIM) technology has emerged as a competitive candidate for edge computing because of its low power consumption and high performance. In order to achieve accurate inference for neural network models, it is crucial to comprehend the source of errors in the CIM-based analog computing paradigm. In this work, we analyzed the impact of random noises and output stabling times on the Programmable Linear Random Access Memory (PLRAM)-based CIM chip. Experimental results show that the impact of random noise is negligible. The output stabling time can be treated as RC delay, which is related to the weight distribution. We proposed a weight reordering strategy to achieve better performance without sacrificing computation accuracy. Experiments with a commercial 11-keyword speech recognition model show a 74.4% runtime reduction while maintaining a 95.6% classification accuracy.
{"title":"Mitigating RC-Delay Induced Accuracy Loss in Analog In-Memory Computing: A Non-Compromising Approach","authors":"Saike Zhu;Cimang Lu;Xiang Qiu;Shifan Gao;Xiang Ding;Youngseo Kim;Yi Zhao","doi":"10.1109/TCE.2024.3445341","DOIUrl":"10.1109/TCE.2024.3445341","url":null,"abstract":"The Internet of Things (IoT) has proliferated ubiquitous information exchange between the physical and cyber worlds through consumer electronics, with a focus on moving computing power to edge terminals. Computing-in-memory (CIM) technology has emerged as a competitive candidate for edge computing because of its low power consumption and high performance. In order to achieve accurate inference for neural network models, it is crucial to comprehend the source of errors in the CIM-based analog computing paradigm. In this work, we analyzed the impact of random noises and output stabling times on the Programmable Linear Random Access Memory (PLRAM)-based CIM chip. Experimental results show that the impact of random noise is negligible. The output stabling time can be treated as RC delay, which is related to the weight distribution. We proposed a weight reordering strategy to achieve better performance without sacrificing computation accuracy. Experiments with a commercial 11-keyword speech recognition model show a 74.4% runtime reduction while maintaining a 95.6% classification accuracy.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"7544-7550"},"PeriodicalIF":4.3,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189674","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}
Pub Date : 2024-08-16DOI: 10.1109/TCE.2024.3445139
Xu Zhang;Xiaoyu Hu;Deyu Zhou
With the growth of the consumer electronics market, the software development industry is facing new opportunities and an increased focus on code retrieval techniques to improve efficiency and reduce costs. Code search aims to retrieve and reuse code from extensive repositories based on a search query with specific requirements. Recently, pre-trained model-based approaches have become popular because of grasping semantic representations of code snippets and search queries accurately. However, such approaches ignore the inconsistency between code and query statements due to the redundant tokens, such as definitions and punctuation marks in the code snippets, which hinder the matching accuracy. To tackle such disadvantage, in this paper, two strategies are proposed based on explicit or implicit code representation summarization. By summarizing the code representation, the redundancy in the code is removed and the inconsistency between code and query statements is alleviated. For the explicit code representation summarization-based strategy, different views of contextual information are obtained and summarized based on different scales of pyramidal dilated convolution. As to the implicit code representation summarization-based strategy, covariance is directly applied to constrain the code representation to ensure de-redundancy. Experimental results on six benchmark datasets show both strategies outperform the current State-Of-The-Art model CORES by 1.2% on average MRR scores.
{"title":"CORES: COde REpresentation Summarization for Code Search","authors":"Xu Zhang;Xiaoyu Hu;Deyu Zhou","doi":"10.1109/TCE.2024.3445139","DOIUrl":"10.1109/TCE.2024.3445139","url":null,"abstract":"With the growth of the consumer electronics market, the software development industry is facing new opportunities and an increased focus on code retrieval techniques to improve efficiency and reduce costs. Code search aims to retrieve and reuse code from extensive repositories based on a search query with specific requirements. Recently, pre-trained model-based approaches have become popular because of grasping semantic representations of code snippets and search queries accurately. However, such approaches ignore the inconsistency between code and query statements due to the redundant tokens, such as definitions and punctuation marks in the code snippets, which hinder the matching accuracy. To tackle such disadvantage, in this paper, two strategies are proposed based on explicit or implicit code representation summarization. By summarizing the code representation, the redundancy in the code is removed and the inconsistency between code and query statements is alleviated. For the explicit code representation summarization-based strategy, different views of contextual information are obtained and summarized based on different scales of pyramidal dilated convolution. As to the implicit code representation summarization-based strategy, covariance is directly applied to constrain the code representation to ensure de-redundancy. Experimental results on six benchmark datasets show both strategies outperform the current State-Of-The-Art model CORES by 1.2% on average MRR scores.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 3","pages":"6095-6104"},"PeriodicalIF":4.3,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189728","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}
Pub Date : 2024-08-16DOI: 10.1109/tce.2024.3444824
Altaf Hussain, Wajahat Akbar, Tariq Hussain, Ali Kashif Bashir, Maryam M. Al Dabel, Farman Ali, Bailin Yang
{"title":"Ensuring Zero Trust IoT Data Privacy: Differential Privacy in Blockchain using Federated Learning","authors":"Altaf Hussain, Wajahat Akbar, Tariq Hussain, Ali Kashif Bashir, Maryam M. Al Dabel, Farman Ali, Bailin Yang","doi":"10.1109/tce.2024.3444824","DOIUrl":"https://doi.org/10.1109/tce.2024.3444824","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"79 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189720","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}
Pub Date : 2024-08-14DOI: 10.1109/tce.2024.3442015
Soumya Ranjan Jena, Mohammad Zia Ur Rahman, Deepak K. Sinha, P. Rajendra kumar, Vrince Vimal, Kamred Udham Singh, Thalakola Syamsundararao, J.N.V.R. Swarup Kumar, Balajee J
{"title":"An Innovative Secure and Privacy-Preserving Federated Learning Based Hybrid Deep Learning Model for Intrusion Detection in Internet-Enabled Wireless Sensor Networks","authors":"Soumya Ranjan Jena, Mohammad Zia Ur Rahman, Deepak K. Sinha, P. Rajendra kumar, Vrince Vimal, Kamred Udham Singh, Thalakola Syamsundararao, J.N.V.R. Swarup Kumar, Balajee J","doi":"10.1109/tce.2024.3442015","DOIUrl":"https://doi.org/10.1109/tce.2024.3442015","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"30 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189681","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}
Pub Date : 2024-08-13DOI: 10.1109/tce.2024.3442932
Zeinab Teimoori, Abdulsalam Yassine, M. Shamim Hossain
{"title":"Empowering Consumer Electric Vehicle Mobile Charging Services With Secure Profit Optimization","authors":"Zeinab Teimoori, Abdulsalam Yassine, M. Shamim Hossain","doi":"10.1109/tce.2024.3442932","DOIUrl":"https://doi.org/10.1109/tce.2024.3442932","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"10 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189685","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":"Joint Optimization of Service Caching and Task Offloading for Customer Application in MEC: A Hybrid SAC Scheme","authors":"Yang Xu, Ziyu Peng, Nanxi Song, Yu Qiu, Cheng Zhang, Yaoxue Zhang","doi":"10.1109/tce.2024.3443168","DOIUrl":"https://doi.org/10.1109/tce.2024.3443168","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"27 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224479","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}
Pub Date : 2024-08-13DOI: 10.1109/tce.2024.3442882
Xiaoyue Ji, Liyan Zhu, Chenhao Hu, Yifeng Han, Donglian Qi
{"title":"A Semantic and Syntactic Enhanced Neuromorphic Computing System and its Application in Consumer Sentiment Analysis","authors":"Xiaoyue Ji, Liyan Zhu, Chenhao Hu, Yifeng Han, Donglian Qi","doi":"10.1109/tce.2024.3442882","DOIUrl":"https://doi.org/10.1109/tce.2024.3442882","url":null,"abstract":"","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"2011 1","pages":""},"PeriodicalIF":4.3,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189684","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}
Pub Date : 2024-08-13DOI: 10.1109/TCE.2024.3443022
Zhiguo Qu;Zhiwei Liang
Federated learning (FL) is an effective technique for image classification in consumer electronics. This paper proposes a new FL algorithm called FedHLC to address heterogeneous and long-tailed data. Its architecture comprises a feature extractor and a classifier. The training process of FedHLC is divided into two distinct stages. In the first stage, it focuses on training feature extractors on the client side and conducts feature representation learning. This approach develops a robust and generalizable representation for digital image data. The second stage involves retraining the classifier on the server side with generated virtual features. This step not only safeguards client privacy but also effectively mitigates model bias towards tail categories. In addition, FedHLC incorporates a novel balancing factor that dynamically adjusts the influence of regularization term. It allows a flexible focus shift between global objectives and local objectives. The simulation experiments on benchmark datasets demonstrate that FedHLC outperforms the baseline algorithms including CReFF, FedAvg, FedProx and FedNova in terms of accuracy when dealing with heterogeneous and long-tailed data. Furthermore, FedHLC can not only achieve good convergence but also attain an accuracy peak of 89.24%, marking a substantial advancement in the field of FL for image classification in consumer electronics. The code is available at https://github.com/Kiritoliang/FedHLC .
{"title":"FedHLC: A Novel Federated Learning Algorithm Targeting Heterogeneous and Long-Tailed Data for Efficient Image Classification in Consumer Electronics","authors":"Zhiguo Qu;Zhiwei Liang","doi":"10.1109/TCE.2024.3443022","DOIUrl":"10.1109/TCE.2024.3443022","url":null,"abstract":"Federated learning (FL) is an effective technique for image classification in consumer electronics. This paper proposes a new FL algorithm called FedHLC to address heterogeneous and long-tailed data. Its architecture comprises a feature extractor and a classifier. The training process of FedHLC is divided into two distinct stages. In the first stage, it focuses on training feature extractors on the client side and conducts feature representation learning. This approach develops a robust and generalizable representation for digital image data. The second stage involves retraining the classifier on the server side with generated virtual features. This step not only safeguards client privacy but also effectively mitigates model bias towards tail categories. In addition, FedHLC incorporates a novel balancing factor that dynamically adjusts the influence of regularization term. It allows a flexible focus shift between global objectives and local objectives. The simulation experiments on benchmark datasets demonstrate that FedHLC outperforms the baseline algorithms including CReFF, FedAvg, FedProx and FedNova in terms of accuracy when dealing with heterogeneous and long-tailed data. Furthermore, FedHLC can not only achieve good convergence but also attain an accuracy peak of 89.24%, marking a substantial advancement in the field of FL for image classification in consumer electronics. The code is available at \u0000<uri>https://github.com/Kiritoliang/FedHLC</uri>\u0000.","PeriodicalId":13208,"journal":{"name":"IEEE Transactions on Consumer Electronics","volume":"70 4","pages":"7266-7278"},"PeriodicalIF":4.3,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142189682","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：