A CNN-LSTM model for six human ankle movements classification on different loads
This study aims to address three problems in current studies in decoding the ankle movement intention for robot-assisted bilateral rehabilitation using surface electromyogram (sEMG) signals: (1) only up to four ankle movements could be identified while six ankle movements should be classified to pro...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-03-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1101938/full |
_version_ | 1811158380031508480 |
---|---|
author | Min Li Jiale Wang Shiqi Yang Jun Xie Guanghua Xu Shan Luo |
author_facet | Min Li Jiale Wang Shiqi Yang Jun Xie Guanghua Xu Shan Luo |
author_sort | Min Li |
collection | DOAJ |
description | This study aims to address three problems in current studies in decoding the ankle movement intention for robot-assisted bilateral rehabilitation using surface electromyogram (sEMG) signals: (1) only up to four ankle movements could be identified while six ankle movements should be classified to provide better training; (2) feeding the raw sEMG signals directly into the neural network leads to high computational cost; and (3) load variation has large influence on classification accuracy. To achieve this, a convolutional neural network (CNN)—long short-term memory (LSTM) model, a time-domain feature selection method of the sEMG, and a two-step method are proposed. For the first time, the Boruta algorithm is used to select time-domain features of sEMG. The selected features, rather than raw sEMG signals are fed into the CNN-LSTM model. Hence, the number of model’s parameters is reduced from 331,938 to 155,042, by half. Experiments are conducted to validate the proposed method. The results show that our method could classify six ankle movements with relatively good accuracy (95.73%). The accuracy of CNN-LSTM, CNN, and LSTM models with sEMG features as input are all higher than that of corresponding models with raw sEMG as input. The overall accuracy is improved from 73.23% to 93.50% using our two-step method for identifying the ankle movements with different loads. Our proposed CNN-LSTM model have the highest accuracy for ankle movements classification compared with CNN, LSTM, and Support Vector Machine (SVM). |
first_indexed | 2024-04-10T05:23:41Z |
format | Article |
id | doaj.art-6f2cbe72f54246618cb596e3350612dd |
institution | Directory Open Access Journal |
issn | 1662-5161 |
language | English |
last_indexed | 2024-04-10T05:23:41Z |
publishDate | 2023-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Human Neuroscience |
spelling | doaj.art-6f2cbe72f54246618cb596e3350612dd2023-03-08T05:26:17ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612023-03-011710.3389/fnhum.2023.11019381101938A CNN-LSTM model for six human ankle movements classification on different loadsMin Li0Jiale Wang1Shiqi Yang2Jun Xie3Guanghua Xu4Shan Luo5Department of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Engineering, King’s College London, London, United KingdomThis study aims to address three problems in current studies in decoding the ankle movement intention for robot-assisted bilateral rehabilitation using surface electromyogram (sEMG) signals: (1) only up to four ankle movements could be identified while six ankle movements should be classified to provide better training; (2) feeding the raw sEMG signals directly into the neural network leads to high computational cost; and (3) load variation has large influence on classification accuracy. To achieve this, a convolutional neural network (CNN)—long short-term memory (LSTM) model, a time-domain feature selection method of the sEMG, and a two-step method are proposed. For the first time, the Boruta algorithm is used to select time-domain features of sEMG. The selected features, rather than raw sEMG signals are fed into the CNN-LSTM model. Hence, the number of model’s parameters is reduced from 331,938 to 155,042, by half. Experiments are conducted to validate the proposed method. The results show that our method could classify six ankle movements with relatively good accuracy (95.73%). The accuracy of CNN-LSTM, CNN, and LSTM models with sEMG features as input are all higher than that of corresponding models with raw sEMG as input. The overall accuracy is improved from 73.23% to 93.50% using our two-step method for identifying the ankle movements with different loads. Our proposed CNN-LSTM model have the highest accuracy for ankle movements classification compared with CNN, LSTM, and Support Vector Machine (SVM).https://www.frontiersin.org/articles/10.3389/fnhum.2023.1101938/fullSEMG signalankle movement classificationload variationCNNLSTM |
spellingShingle | Min Li Jiale Wang Shiqi Yang Jun Xie Guanghua Xu Shan Luo A CNN-LSTM model for six human ankle movements classification on different loads Frontiers in Human Neuroscience SEMG signal ankle movement classification load variation CNN LSTM |
title | A CNN-LSTM model for six human ankle movements classification on different loads |
title_full | A CNN-LSTM model for six human ankle movements classification on different loads |
title_fullStr | A CNN-LSTM model for six human ankle movements classification on different loads |
title_full_unstemmed | A CNN-LSTM model for six human ankle movements classification on different loads |
title_short | A CNN-LSTM model for six human ankle movements classification on different loads |
title_sort | cnn lstm model for six human ankle movements classification on different loads |
topic | SEMG signal ankle movement classification load variation CNN LSTM |
url | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1101938/full |
work_keys_str_mv | AT minli acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT jialewang acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT shiqiyang acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT junxie acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT guanghuaxu acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT shanluo acnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT minli cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT jialewang cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT shiqiyang cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT junxie cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT guanghuaxu cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads AT shanluo cnnlstmmodelforsixhumananklemovementsclassificationondifferentloads |