Online mapping of EMG signals into kinematics by autoencoding
Abstract Background In this paper, we propose a nonlinear minimally supervised method based on autoencoding (AEN) of EMG for myocontrol. The proposed method was tested against the state-of-the-art (SOA) control scheme using a Fitts’ law approach. Methods Seven able-bodied subjects performed a series...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-03-01
|
Series: | Journal of NeuroEngineering and Rehabilitation |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12984-018-0363-1 |
id |
doaj-f25185f566b14ddd9ac7de88b9efa766 |
---|---|
record_format |
Article |
spelling |
doaj-f25185f566b14ddd9ac7de88b9efa7662020-11-24T22:00:39ZengBMCJournal of NeuroEngineering and Rehabilitation1743-00032018-03-011511910.1186/s12984-018-0363-1Online mapping of EMG signals into kinematics by autoencodingIvan Vujaklija0Vahid Shalchyan1Ernest N. Kamavuako2Ning Jiang3Hamid R. Marateb4Dario Farina5Department of Bioengineering, Imperial College LondonBiomedical Engineering Department, School of Electrical Engineering, Iran University of Science and TechnologyCentre for Robotics Research, Department of Informatics, King’s College LondonDepartment of Systems Design Engineering, University of WaterlooBiomedical Engineering Department, Engineering Faculty, University of IsfahanDepartment of Bioengineering, Imperial College LondonAbstract Background In this paper, we propose a nonlinear minimally supervised method based on autoencoding (AEN) of EMG for myocontrol. The proposed method was tested against the state-of-the-art (SOA) control scheme using a Fitts’ law approach. Methods Seven able-bodied subjects performed a series of target acquisition myoelectric control tasks using the AEN and SOA algorithms for controlling two degrees-of-freedom (radial/ulnar deviation and flexion/extension of the wrist), and their online performance was characterized by six metrics. Results Both methods allowed a completion rate close to 100%, however AEN outperformed SOA for all other performance metrics, e.g. it allowed to perform the tasks on average in half the time with respect to SOA. Moreover, the amount of information transferred by the proposed method in bit/s was nearly twice the throughput of SOA. Conclusions These results show that autoencoders can map EMG signals into kinematics with the potential of providing intuitive and dexterous control of artificial limbs for amputees.http://link.springer.com/article/10.1186/s12984-018-0363-1Prosthetic controlMyoelectric signal processingRegressionOnline performanceAutoencoding |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ivan Vujaklija Vahid Shalchyan Ernest N. Kamavuako Ning Jiang Hamid R. Marateb Dario Farina |
spellingShingle |
Ivan Vujaklija Vahid Shalchyan Ernest N. Kamavuako Ning Jiang Hamid R. Marateb Dario Farina Online mapping of EMG signals into kinematics by autoencoding Journal of NeuroEngineering and Rehabilitation Prosthetic control Myoelectric signal processing Regression Online performance Autoencoding |
author_facet |
Ivan Vujaklija Vahid Shalchyan Ernest N. Kamavuako Ning Jiang Hamid R. Marateb Dario Farina |
author_sort |
Ivan Vujaklija |
title |
Online mapping of EMG signals into kinematics by autoencoding |
title_short |
Online mapping of EMG signals into kinematics by autoencoding |
title_full |
Online mapping of EMG signals into kinematics by autoencoding |
title_fullStr |
Online mapping of EMG signals into kinematics by autoencoding |
title_full_unstemmed |
Online mapping of EMG signals into kinematics by autoencoding |
title_sort |
online mapping of emg signals into kinematics by autoencoding |
publisher |
BMC |
series |
Journal of NeuroEngineering and Rehabilitation |
issn |
1743-0003 |
publishDate |
2018-03-01 |
description |
Abstract Background In this paper, we propose a nonlinear minimally supervised method based on autoencoding (AEN) of EMG for myocontrol. The proposed method was tested against the state-of-the-art (SOA) control scheme using a Fitts’ law approach. Methods Seven able-bodied subjects performed a series of target acquisition myoelectric control tasks using the AEN and SOA algorithms for controlling two degrees-of-freedom (radial/ulnar deviation and flexion/extension of the wrist), and their online performance was characterized by six metrics. Results Both methods allowed a completion rate close to 100%, however AEN outperformed SOA for all other performance metrics, e.g. it allowed to perform the tasks on average in half the time with respect to SOA. Moreover, the amount of information transferred by the proposed method in bit/s was nearly twice the throughput of SOA. Conclusions These results show that autoencoders can map EMG signals into kinematics with the potential of providing intuitive and dexterous control of artificial limbs for amputees. |
topic |
Prosthetic control Myoelectric signal processing Regression Online performance Autoencoding |
url |
http://link.springer.com/article/10.1186/s12984-018-0363-1 |
work_keys_str_mv |
AT ivanvujaklija onlinemappingofemgsignalsintokinematicsbyautoencoding AT vahidshalchyan onlinemappingofemgsignalsintokinematicsbyautoencoding AT ernestnkamavuako onlinemappingofemgsignalsintokinematicsbyautoencoding AT ningjiang onlinemappingofemgsignalsintokinematicsbyautoencoding AT hamidrmarateb onlinemappingofemgsignalsintokinematicsbyautoencoding AT dariofarina onlinemappingofemgsignalsintokinematicsbyautoencoding |
_version_ |
1725843525805801472 |