Study on interaction between temporal and spatial information in classification of EMG signals in myoelectric prostheses

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its offline performance and analyze their interdependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap a nd the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3 % below values achieved by able-bodied volunteers.
LanguageEnglish
Pages1832-1842
Number of pages11
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume25
Issue number10
Early online date19 Apr 2017
DOIs
Publication statusPublished - 31 Oct 2017

Fingerprint

Electromyography
Prosthetics
Prostheses and Implants
Amputees
Volunteers
Gestures
Classifiers
Extremities
Hand
Electrodes
Controllability
Forearm
Equipment and Supplies

Keywords

  • electromyography signal patterns
  • motion gesture
  • prosthetic devices

Cite this

@article{e1f5493e60e04d72917c290073900f2f,
title = "Study on interaction between temporal and spatial information in classification of EMG signals in myoelectric prostheses",
abstract = "Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its offline performance and analyze their interdependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap a nd the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3 {\%} below values achieved by able-bodied volunteers.",
keywords = "electromyography signal patterns, motion gesture, prosthetic devices",
author = "Radhika Menon and {Di Caterina}, Gaetano and Heba Lakany and Lykourgos Petropoulakis and Conway, {Bernard A.} and Soraghan, {John J.}",
note = "{\circledC} 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2017",
month = "10",
day = "31",
doi = "10.1109/TNSRE.2017.2687761",
language = "English",
volume = "25",
pages = "1832--1842",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
number = "10",

}

TY - JOUR

T1 - Study on interaction between temporal and spatial information in classification of EMG signals in myoelectric prostheses

AU - Menon, Radhika

AU - Di Caterina, Gaetano

AU - Lakany, Heba

AU - Petropoulakis, Lykourgos

AU - Conway, Bernard A.

AU - Soraghan, John J.

N1 - © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2017/10/31

Y1 - 2017/10/31

N2 - Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its offline performance and analyze their interdependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap a nd the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3 % below values achieved by able-bodied volunteers.

AB - Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its offline performance and analyze their interdependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap a nd the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3 % below values achieved by able-bodied volunteers.

KW - electromyography signal patterns

KW - motion gesture

KW - prosthetic devices

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7333

U2 - 10.1109/TNSRE.2017.2687761

DO - 10.1109/TNSRE.2017.2687761

M3 - Article

VL - 25

SP - 1832

EP - 1842

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

T2 - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 10

ER -