Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network
Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2017-07-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | http://journal.frontiersin.org/article/10.3389/fnins.2017.00379/full |
id |
doaj-3e2b8a7dba61460da6dd4547db50ba04 |
---|---|
record_format |
Article |
spelling |
doaj-3e2b8a7dba61460da6dd4547db50ba042020-11-25T00:12:30ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2017-07-011110.3389/fnins.2017.00379266372Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural NetworkXiaolong Zhai0Beth Jelfs1Beth Jelfs2Rosa H. M. Chan3Rosa H. M. Chan4Chung Tin5Chung Tin6Chung Tin7Department of Mechanical and Biomedical Engineering, City University of Hong KongHong Kong, Hong KongDepartment of Electronic Engineering, City University of Hong KongHong Kong, Hong KongCentre for Biosystems, Neuroscience, and Nanotechnology, City University of Hong KongHong Kong, Hong KongDepartment of Electronic Engineering, City University of Hong KongHong Kong, Hong KongCentre for Biosystems, Neuroscience, and Nanotechnology, City University of Hong KongHong Kong, Hong KongDepartment of Mechanical and Biomedical Engineering, City University of Hong KongHong Kong, Hong KongCentre for Biosystems, Neuroscience, and Nanotechnology, City University of Hong KongHong Kong, Hong KongCentre for Robotics and Automation, City University of Hong KongHong Kong, Hong KongHand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.http://journal.frontiersin.org/article/10.3389/fnins.2017.00379/fullmyoelectric controlnon-stationary EMGclassificationhand gesturepattern recognitionconvolutional neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaolong Zhai Beth Jelfs Beth Jelfs Rosa H. M. Chan Rosa H. M. Chan Chung Tin Chung Tin Chung Tin |
spellingShingle |
Xiaolong Zhai Beth Jelfs Beth Jelfs Rosa H. M. Chan Rosa H. M. Chan Chung Tin Chung Tin Chung Tin Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network Frontiers in Neuroscience myoelectric control non-stationary EMG classification hand gesture pattern recognition convolutional neural network |
author_facet |
Xiaolong Zhai Beth Jelfs Beth Jelfs Rosa H. M. Chan Rosa H. M. Chan Chung Tin Chung Tin Chung Tin |
author_sort |
Xiaolong Zhai |
title |
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network |
title_short |
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network |
title_full |
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network |
title_fullStr |
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network |
title_full_unstemmed |
Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network |
title_sort |
self-recalibrating surface emg pattern recognition for neuroprosthesis control based on convolutional neural network |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroscience |
issn |
1662-453X |
publishDate |
2017-07-01 |
description |
Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications. |
topic |
myoelectric control non-stationary EMG classification hand gesture pattern recognition convolutional neural network |
url |
http://journal.frontiersin.org/article/10.3389/fnins.2017.00379/full |
work_keys_str_mv |
AT xiaolongzhai selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT bethjelfs selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT bethjelfs selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT rosahmchan selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT rosahmchan selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT chungtin selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT chungtin selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork AT chungtin selfrecalibratingsurfaceemgpatternrecognitionforneuroprosthesiscontrolbasedonconvolutionalneuralnetwork |
_version_ |
1725399313860788224 |