基于边缘设备的实时肌电模式识别系统的高效卷积神经网络

Jimmy Lu, Philip Liang, Jin Chul Rhim, Xiaorong Zhang, Zhuwei Qin
{"title":"基于边缘设备的实时肌电模式识别系统的高效卷积神经网络","authors":"Jimmy Lu, Philip Liang, Jin Chul Rhim, Xiaorong Zhang, Zhuwei Qin","doi":"10.1109/NER52421.2023.10123741","DOIUrl":null,"url":null,"abstract":"With the advancement of deep learning (DL) technologies, applying DL methods to processing surface electromyo-graphic (sEMG) signals for movement intent recognition has gained increasing interest in the research community. Compared to conventional non-DL methods commonly used for EMG pattern recognition (PR), DL algorithms have the advantage of automatically extracting sEMG features without the cumbersome manual feature engineering step and are especially effective in processing sEMG signals collected from 1-dimentional (1D) or 2D sensor arrays. However, a key challenge to the deployment of DL methods in sEMG-controlled neural-machine interface (NMI) applications (e.g., myoelectric controlled prostheses) is the high computational cost associated with DL algorithms (e.g., convolutional neural network (CNN)) since most NMI applications need to be implemented on resource-constrained embedded computer systems and have real-time requirements. In this paper, we designed and implemented EffiE - an efficient CNN for real-time EMG PR system on edge devices. The development of the EffiE system integrated several strategies including a deep transfer learning strategy to adaptively and quickly update the pre-trained CNN model based on the user's newly collected data on the edge device, and a deep learning quantization method that can dramatically reduce the memory consumption and computational load of the CNN model without sacrificing the model accuracy. The proposed EffiE system has been implemented on a Sony Spresense 6-core microcontroller board as a working prototype for real-time NMIs. The embedded NMI prototype has integrated input/output interfaces as well as efficient memory management and precise timing control schemes to achieve real-time DL-based myoelectric control of a bionic arm using hand gestures. We released all the source code at: https://github.com/MIC-Laboratory/EffiE","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EffiE: Efficient Convolutional Neural Network for Real-Time EMG Pattern Recognition System on Edge Devices\",\"authors\":\"Jimmy Lu, Philip Liang, Jin Chul Rhim, Xiaorong Zhang, Zhuwei Qin\",\"doi\":\"10.1109/NER52421.2023.10123741\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the advancement of deep learning (DL) technologies, applying DL methods to processing surface electromyo-graphic (sEMG) signals for movement intent recognition has gained increasing interest in the research community. Compared to conventional non-DL methods commonly used for EMG pattern recognition (PR), DL algorithms have the advantage of automatically extracting sEMG features without the cumbersome manual feature engineering step and are especially effective in processing sEMG signals collected from 1-dimentional (1D) or 2D sensor arrays. However, a key challenge to the deployment of DL methods in sEMG-controlled neural-machine interface (NMI) applications (e.g., myoelectric controlled prostheses) is the high computational cost associated with DL algorithms (e.g., convolutional neural network (CNN)) since most NMI applications need to be implemented on resource-constrained embedded computer systems and have real-time requirements. In this paper, we designed and implemented EffiE - an efficient CNN for real-time EMG PR system on edge devices. The development of the EffiE system integrated several strategies including a deep transfer learning strategy to adaptively and quickly update the pre-trained CNN model based on the user's newly collected data on the edge device, and a deep learning quantization method that can dramatically reduce the memory consumption and computational load of the CNN model without sacrificing the model accuracy. The proposed EffiE system has been implemented on a Sony Spresense 6-core microcontroller board as a working prototype for real-time NMIs. The embedded NMI prototype has integrated input/output interfaces as well as efficient memory management and precise timing control schemes to achieve real-time DL-based myoelectric control of a bionic arm using hand gestures. We released all the source code at: https://github.com/MIC-Laboratory/EffiE\",\"PeriodicalId\":201841,\"journal\":{\"name\":\"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)\",\"volume\":\"30 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NER52421.2023.10123741\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NER52421.2023.10123741","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

随着深度学习(DL)技术的进步,将深度学习方法应用于处理表面肌电图(sEMG)信号以进行运动意图识别已经引起了研究界越来越多的兴趣。与肌电信号模式识别(PR)常用的传统非深度学习方法相比,深度学习算法具有自动提取肌电信号特征的优点,无需繁琐的手动特征工程步骤,并且在处理从一维(1D)或二维传感器阵列收集的肌电信号时特别有效。然而,在表面肌电控制的神经-机器接口(NMI)应用(如肌电控制的假体)中部署深度学习方法的一个关键挑战是与深度学习算法(如卷积神经网络(CNN))相关的高计算成本,因为大多数NMI应用需要在资源受限的嵌入式计算机系统上实现,并且具有实时性要求。本文设计并实现了一种用于边缘设备实时肌电PR系统的高效CNN EffiE。EffiE系统的开发集成了多种策略,包括深度迁移学习策略,可以根据用户在边缘设备上新收集的数据自适应快速更新预训练的CNN模型,以及深度学习量化方法,可以在不牺牲模型精度的情况下显著降低CNN模型的内存消耗和计算负荷。所提出的EffiE系统已在索尼Spresense 6核微控制器板上实现,作为实时NMIs的工作原型。嵌入式NMI原型具有集成的输入/输出接口以及高效的内存管理和精确的定时控制方案,可以使用手势实现基于dl的仿生手臂的实时肌电控制。我们在https://github.com/MIC-Laboratory/EffiE上发布了所有的源代码
本文章由计算机程序翻译,如有差异,请以英文原文为准。
EffiE: Efficient Convolutional Neural Network for Real-Time EMG Pattern Recognition System on Edge Devices
With the advancement of deep learning (DL) technologies, applying DL methods to processing surface electromyo-graphic (sEMG) signals for movement intent recognition has gained increasing interest in the research community. Compared to conventional non-DL methods commonly used for EMG pattern recognition (PR), DL algorithms have the advantage of automatically extracting sEMG features without the cumbersome manual feature engineering step and are especially effective in processing sEMG signals collected from 1-dimentional (1D) or 2D sensor arrays. However, a key challenge to the deployment of DL methods in sEMG-controlled neural-machine interface (NMI) applications (e.g., myoelectric controlled prostheses) is the high computational cost associated with DL algorithms (e.g., convolutional neural network (CNN)) since most NMI applications need to be implemented on resource-constrained embedded computer systems and have real-time requirements. In this paper, we designed and implemented EffiE - an efficient CNN for real-time EMG PR system on edge devices. The development of the EffiE system integrated several strategies including a deep transfer learning strategy to adaptively and quickly update the pre-trained CNN model based on the user's newly collected data on the edge device, and a deep learning quantization method that can dramatically reduce the memory consumption and computational load of the CNN model without sacrificing the model accuracy. The proposed EffiE system has been implemented on a Sony Spresense 6-core microcontroller board as a working prototype for real-time NMIs. The embedded NMI prototype has integrated input/output interfaces as well as efficient memory management and precise timing control schemes to achieve real-time DL-based myoelectric control of a bionic arm using hand gestures. We released all the source code at: https://github.com/MIC-Laboratory/EffiE
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信