EMG Based Rehabilitation Gesture Recognition Using DAE-CNN-LSTM Hybrid Model

Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting patients' daily activities and causing profound psychological trauma. Rehabilitation gesture recognition, as one of the key means of acti...

Full description

Saved in:
Bibliographic Details
Published in:2024 World Rehabilitation Robot Convention (WRRC) pp. 1 - 6
Main Authors: Cao, Wujing, Guo, Xinqiang, Zou, Yupeng, Zhang, Shuo, Luo, Mingxiang, Kobsiriphat, Worawarit, Wu, Xinyu, Yin, Meng
Format: Conference Proceeding
Language:English
Published: IEEE 23.08.2024
Subjects:
Accuracy
CNN-LSTM algorithm
Convolutional neural networks
Deep learning
Electromyography
Feature extraction
Gesture recognition
Long short term memory
Noise
Rehabilitation
Stroke
Stroke (medical condition)
Support vector machines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting patients' daily activities and causing profound psychological trauma. Rehabilitation gesture recognition, as one of the key means of active rehabilitation medicine, holds significant potential in stroke rehabilitation, providing real-time feedback on patient progress and enabling personalized interventions to meet individual needs. Traditional gesture recognition methods face numerous challenges when dealing with stroke patient data, such as noise, motion blur, and individual differences. To address these challenges, this paper proposes a novel approach for stroke patient gesture recognition using deep learning models. We adopt a strategy combining denoising autoencoder (DAE), convolutional neural network (CNN), and long short-term memory (LSTM) to enhance the accurate recognition of hand movements in stroke patients. Specifically, DAE is utilized for denoising EMG signals, extracting features, and reducing noise to improve the signal's noise resistance. CNN is employed for spatial feature extraction, while LSTM captures temporal dependencies in gesture sequences. By integrating these three deep learning models, our aim is to enhance the accuracy and robustness of rehabilitation gesture recognition. We validate the proposed method's effectiveness on an EMG dataset from seven subjects through experiments and compare it with traditional machine learning and individual CNN and LSTM algorithms. Experimental results demonstrate significant performance improvements of our hybrid model in rehabilitation gesture recognition tasks, indicating promising application prospects and practical significance.
AbstractList Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting patients' daily activities and causing profound psychological trauma. Rehabilitation gesture recognition, as one of the key means of active rehabilitation medicine, holds significant potential in stroke rehabilitation, providing real-time feedback on patient progress and enabling personalized interventions to meet individual needs. Traditional gesture recognition methods face numerous challenges when dealing with stroke patient data, such as noise, motion blur, and individual differences. To address these challenges, this paper proposes a novel approach for stroke patient gesture recognition using deep learning models. We adopt a strategy combining denoising autoencoder (DAE), convolutional neural network (CNN), and long short-term memory (LSTM) to enhance the accurate recognition of hand movements in stroke patients. Specifically, DAE is utilized for denoising EMG signals, extracting features, and reducing noise to improve the signal's noise resistance. CNN is employed for spatial feature extraction, while LSTM captures temporal dependencies in gesture sequences. By integrating these three deep learning models, our aim is to enhance the accuracy and robustness of rehabilitation gesture recognition. We validate the proposed method's effectiveness on an EMG dataset from seven subjects through experiments and compare it with traditional machine learning and individual CNN and LSTM algorithms. Experimental results demonstrate significant performance improvements of our hybrid model in rehabilitation gesture recognition tasks, indicating promising application prospects and practical significance.
Author Luo, Mingxiang
Zhang, Shuo
Kobsiriphat, Worawarit
Yin, Meng
Cao, Wujing
Wu, Xinyu
Guo, Xinqiang
Zou, Yupeng
Author_xml – sequence: 1
  givenname: Wujing
  surname: Cao
  fullname: Cao, Wujing
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong Provincial Key Lab of Robotics and Intelligent System,Shenzhen,China,518005
– sequence: 2
  givenname: Xinqiang
  surname: Guo
  fullname: Guo, Xinqiang
  organization: School of Mechanical Engineering, China University of Petroleum,East China
– sequence: 3
  givenname: Yupeng
  surname: Zou
  fullname: Zou, Yupeng
  organization: School of Mechanical Engineering, China University of Petroleum,East China
– sequence: 4
  givenname: Shuo
  surname: Zhang
  fullname: Zhang, Shuo
  organization: School of Mechanical Engineering, China University of Petroleum,East China
– sequence: 5
  givenname: Mingxiang
  surname: Luo
  fullname: Luo, Mingxiang
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong Provincial Key Lab of Robotics and Intelligent System,Shenzhen,China,518005
– sequence: 6
  givenname: Worawarit
  surname: Kobsiriphat
  fullname: Kobsiriphat, Worawarit
  organization: National Metal and Materials Technology Center,Thailand
– sequence: 7
  givenname: Xinyu
  surname: Wu
  fullname: Wu, Xinyu
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong Provincial Key Lab of Robotics and Intelligent System,Shenzhen,China,518005
– sequence: 8
  givenname: Meng
  surname: Yin
  fullname: Yin, Meng
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong Provincial Key Lab of Robotics and Intelligent System,Shenzhen,China,518005
BookMark eNo1j8tKw0AYRkewC619A8F5gcSZfy7JLGuMqZC0ECMuy0znTx2IiSRx0be3eFkdOAc--K7JZT_0SMgdZzHnzNy_1XWmARiPgYGMOdNGJ1pckJVJTCoUE0pxEFekzKuCPtgJPa3x3brQhdnOYehpgdP8NeJZH4ZjH37c6xT6I31c51G23UblS1PRzcmNwdNq8NjdkEVruwlXf1yS5ilvsk1U7ornbF1GwfA58oorA056qzSTqcVWA_PqwJ0SSjtUKXgpIEGnWJtqNK2QcA7WegSZWLEkt7-zARH3n2P4sONp__9RfAP8qUpK
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/WRRC62201.2024.10696763
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore Digital Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350355123
EndPage 6
ExternalDocumentID 10696763
Genre orig-research
GrantInformation_xml – fundername: Shenzhen Science and Technology Program
  grantid: JCYJ20220818101602005,2021A1515110486
  funderid: 10.13039/501100013385
– fundername: National Natural Science Foundation of China
  grantid: 62203428
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i91t-d51592b4da56048aef620d5c1b5356be582d4327eb50f86e9f34256baade247a3
IEDL.DBID RIE
IngestDate Wed Oct 09 06:12:58 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i91t-d51592b4da56048aef620d5c1b5356be582d4327eb50f86e9f34256baade247a3
PageCount 6
ParticipantIDs ieee_primary_10696763
PublicationCentury 2000
PublicationDate 2024-Aug.-23
PublicationDateYYYYMMDD 2024-08-23
PublicationDate_xml – month: 08
  year: 2024
  text: 2024-Aug.-23
  day: 23
PublicationDecade 2020
PublicationTitle 2024 World Rehabilitation Robot Convention (WRRC)
PublicationTitleAbbrev WRRC
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8807298
Snippet Stroke, as one of the leading causes of long-term disability globally, often results in motor impairments, particularly in the hands, significantly affecting...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
CNN-LSTM algorithm
Convolutional neural networks
Deep learning
Electromyography
Feature extraction
Gesture recognition
Long short term memory
Noise
Rehabilitation
Stroke
Stroke (medical condition)
Support vector machines
Title EMG Based Rehabilitation Gesture Recognition Using DAE-CNN-LSTM Hybrid Model
URI https://ieeexplore.ieee.org/document/10696763
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62ePCkYsU3OXhN3U2yyeaotY9Du5S1YG8l2UygIK2sreC_N0lbpQcP3sIQSJgw-WaS-WYQuqfGySRXocKlrAinPmbVfsNEChO-scCmiY7NJmRR5NOpGm_J6pELAwAx-QzaYRj_8u2yWoenMm_hQglvEA3UkFJuyFrbnK00UQ-vZdkR1COaD_sob-9m7_VNibDRO_7ngieo9UvAw-MfaDlFB7A4Q8PuqI-fPOpYXO7V18Z9f7Wva8DlLhvIy2IuAH5-7JJOUZDhy2SEB1-BnoVD-7O3Fpr0upPOgGybIZC5SlfEBr-DGm61d1F4rsEJmtisSk3GMmEgy6nljEowWeJyAcoxb43CaG2BcqnZOWoulgu4QBic88CvmEq15pyD91B8VOYErxIApvQlagVNzN435S5mOyVc_SG_RkdB3-GhlbIb1FzVa7hFh9Xnav5R38VD-gZbQJKJ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPFtDl5Td7PZ7OaotQ9xu5R1wd5KsplAQVpZW8F_b5K2Sg8evIUhkDBh8s0k880gdEuVSYJUuAqXSUUYtTGrtBsmCVfuGwt0GEjfbCLJ83Q0EsMVWd1zYQDAJ59Byw39X76eVQv3VGYtnAtuDWIb7cSM0XBJ11plbYWBuHstijanFtNs4EdZaz1_o3OKB47uwT-XPETNXwoeHv6AyxHagukxyjqDHn6wuKNxsVFhG_fs5b6oARfrfCAr89kA-PG-Q9p5TrKXcoD7X46ghV0DtLcmKrudst0nq3YIZCLCOdHO86CKaWmdFJZKMJwGOq5CFUcxVxCnVLOIJqDiwKQchImsPXIlpQbKEhmdoMZ0NoVThMEYC_0iEqGUjDGwPoqNywxnVQAQCXmGmk4T4_dlwYvxWgnnf8hv0F6_HGTj7Cl_vkD7Tvfu2ZVGl6gxrxdwhXarz_nko772B_YNLNmV0A
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+World+Rehabilitation+Robot+Convention+%28WRRC%29&rft.atitle=EMG+Based+Rehabilitation+Gesture+Recognition+Using+DAE-CNN-LSTM+Hybrid+Model&rft.au=Cao%2C+Wujing&rft.au=Guo%2C+Xinqiang&rft.au=Zou%2C+Yupeng&rft.au=Zhang%2C+Shuo&rft.date=2024-08-23&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FWRRC62201.2024.10696763&rft.externalDocID=10696763