Stacked sparse autoencoders for EMG-based classification of hand motions

A comparative multi day analyses between surface and intramuscular EMG

Muhammad Zia ur Rehman, Syed Omer Gilani, Asim Waris, Imran Khan Niazi, Gregory Slabaugh, Dario Farina, Ernest Nlandu Kamavuako

Research output: Contribution to journalJournal articleResearchpeer-review

5 Citations (Scopus)
138 Downloads (Pure)

Abstract

Advances in myoelectric interfaces have increased the use of wearable prosthetics including robotic arms. Although promising results have been achieved with pattern recognition-based control schemes, control robustness requires improvement to increase user acceptance of prosthetic hands. The aim of this study was to quantify the performance of stacked sparse autoencoders (SSAE), an emerging deep learning technique used to improve myoelectric control and to compare multiday surface electromyography (sEMG) and intramuscular (iEMG) recordings. Ten able-bodied and six amputee subjects with average ages of 24.5 and 34.5 years, respectively, were evaluated using offline classification error as the performance matric. Surface and intramuscular EMG were concurrently recorded while each subject performed 11 hand motions. Performance of SSAE was compared with that of linear discriminant analysis (LDA) classifier. Within-day analysis showed that SSAE (1.38 ± 1.38%) outperformed LDA (8.09 ± 4.53%) using both the sEMG and iEMG data from both able-bodied and amputee subjects (p < 0.001). In the between-day analysis, SSAE outperformed LDA (7.19 ± 9.55% vs. 22.25 ± 11.09%) using both sEMG and iEMG data from both able-bodied and amputee subjects. No significant difference in performance was observed for within-day and pairs of days with eight-fold validation when using iEMG and sEMG with SSAE, whereas sEMG outperformed iEMG (p < 0.001) in between-day analysis both with two-fold and seven-fold validation schemes. The results obtained in this study imply that SSAE can significantly improve the performance of pattern recognition-based myoelectric control scheme and has the strength to extract deep information hidden in the EMG data.

Original languageEnglish
Article number1126
JournalApplied Sciences
Volume8
Issue number7
Number of pages14
ISSN1454-5101
DOIs
Publication statusPublished - 11 Jul 2018

Fingerprint

electromyography
Electromyography
Discriminant analysis
Prosthetics
pattern recognition
Pattern recognition
robot arms
Robotic arms
classifiers
acceptability
learning
emerging
Classifiers
recording

Keywords

  • Autoencoders
  • Biomedical signal processing
  • Deep networks
  • Intramuscular EMG
  • Myocontrol
  • Surface EMG

Cite this

Rehman, Muhammad Zia ur ; Gilani, Syed Omer ; Waris, Asim ; Niazi, Imran Khan ; Slabaugh, Gregory ; Farina, Dario ; Kamavuako, Ernest Nlandu. / Stacked sparse autoencoders for EMG-based classification of hand motions : A comparative multi day analyses between surface and intramuscular EMG. In: Applied Sciences. 2018 ; Vol. 8, No. 7.
@article{f04c29bbac4b4dc1b5a256cea76639a4,
title = "Stacked sparse autoencoders for EMG-based classification of hand motions: A comparative multi day analyses between surface and intramuscular EMG",
abstract = "Advances in myoelectric interfaces have increased the use of wearable prosthetics including robotic arms. Although promising results have been achieved with pattern recognition-based control schemes, control robustness requires improvement to increase user acceptance of prosthetic hands. The aim of this study was to quantify the performance of stacked sparse autoencoders (SSAE), an emerging deep learning technique used to improve myoelectric control and to compare multiday surface electromyography (sEMG) and intramuscular (iEMG) recordings. Ten able-bodied and six amputee subjects with average ages of 24.5 and 34.5 years, respectively, were evaluated using offline classification error as the performance matric. Surface and intramuscular EMG were concurrently recorded while each subject performed 11 hand motions. Performance of SSAE was compared with that of linear discriminant analysis (LDA) classifier. Within-day analysis showed that SSAE (1.38 ± 1.38{\%}) outperformed LDA (8.09 ± 4.53{\%}) using both the sEMG and iEMG data from both able-bodied and amputee subjects (p < 0.001). In the between-day analysis, SSAE outperformed LDA (7.19 ± 9.55{\%} vs. 22.25 ± 11.09{\%}) using both sEMG and iEMG data from both able-bodied and amputee subjects. No significant difference in performance was observed for within-day and pairs of days with eight-fold validation when using iEMG and sEMG with SSAE, whereas sEMG outperformed iEMG (p < 0.001) in between-day analysis both with two-fold and seven-fold validation schemes. The results obtained in this study imply that SSAE can significantly improve the performance of pattern recognition-based myoelectric control scheme and has the strength to extract deep information hidden in the EMG data.",
keywords = "Autoencoders, Biomedical signal processing, Deep networks, Intramuscular EMG, Myocontrol, Surface EMG",
author = "Rehman, {Muhammad Zia ur} and Gilani, {Syed Omer} and Asim Waris and Niazi, {Imran Khan} and Gregory Slabaugh and Dario Farina and Kamavuako, {Ernest Nlandu}",
year = "2018",
month = "7",
day = "11",
doi = "10.3390/app8071126",
language = "English",
volume = "8",
journal = "Applied Sciences",
issn = "1454-5101",
publisher = "Balkan Society of Geometers",
number = "7",

}

Stacked sparse autoencoders for EMG-based classification of hand motions : A comparative multi day analyses between surface and intramuscular EMG. / Rehman, Muhammad Zia ur; Gilani, Syed Omer; Waris, Asim; Niazi, Imran Khan; Slabaugh, Gregory; Farina, Dario; Kamavuako, Ernest Nlandu.

In: Applied Sciences, Vol. 8, No. 7, 1126, 11.07.2018.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Stacked sparse autoencoders for EMG-based classification of hand motions

T2 - A comparative multi day analyses between surface and intramuscular EMG

AU - Rehman, Muhammad Zia ur

AU - Gilani, Syed Omer

AU - Waris, Asim

AU - Niazi, Imran Khan

AU - Slabaugh, Gregory

AU - Farina, Dario

AU - Kamavuako, Ernest Nlandu

PY - 2018/7/11

Y1 - 2018/7/11

N2 - Advances in myoelectric interfaces have increased the use of wearable prosthetics including robotic arms. Although promising results have been achieved with pattern recognition-based control schemes, control robustness requires improvement to increase user acceptance of prosthetic hands. The aim of this study was to quantify the performance of stacked sparse autoencoders (SSAE), an emerging deep learning technique used to improve myoelectric control and to compare multiday surface electromyography (sEMG) and intramuscular (iEMG) recordings. Ten able-bodied and six amputee subjects with average ages of 24.5 and 34.5 years, respectively, were evaluated using offline classification error as the performance matric. Surface and intramuscular EMG were concurrently recorded while each subject performed 11 hand motions. Performance of SSAE was compared with that of linear discriminant analysis (LDA) classifier. Within-day analysis showed that SSAE (1.38 ± 1.38%) outperformed LDA (8.09 ± 4.53%) using both the sEMG and iEMG data from both able-bodied and amputee subjects (p < 0.001). In the between-day analysis, SSAE outperformed LDA (7.19 ± 9.55% vs. 22.25 ± 11.09%) using both sEMG and iEMG data from both able-bodied and amputee subjects. No significant difference in performance was observed for within-day and pairs of days with eight-fold validation when using iEMG and sEMG with SSAE, whereas sEMG outperformed iEMG (p < 0.001) in between-day analysis both with two-fold and seven-fold validation schemes. The results obtained in this study imply that SSAE can significantly improve the performance of pattern recognition-based myoelectric control scheme and has the strength to extract deep information hidden in the EMG data.

AB - Advances in myoelectric interfaces have increased the use of wearable prosthetics including robotic arms. Although promising results have been achieved with pattern recognition-based control schemes, control robustness requires improvement to increase user acceptance of prosthetic hands. The aim of this study was to quantify the performance of stacked sparse autoencoders (SSAE), an emerging deep learning technique used to improve myoelectric control and to compare multiday surface electromyography (sEMG) and intramuscular (iEMG) recordings. Ten able-bodied and six amputee subjects with average ages of 24.5 and 34.5 years, respectively, were evaluated using offline classification error as the performance matric. Surface and intramuscular EMG were concurrently recorded while each subject performed 11 hand motions. Performance of SSAE was compared with that of linear discriminant analysis (LDA) classifier. Within-day analysis showed that SSAE (1.38 ± 1.38%) outperformed LDA (8.09 ± 4.53%) using both the sEMG and iEMG data from both able-bodied and amputee subjects (p < 0.001). In the between-day analysis, SSAE outperformed LDA (7.19 ± 9.55% vs. 22.25 ± 11.09%) using both sEMG and iEMG data from both able-bodied and amputee subjects. No significant difference in performance was observed for within-day and pairs of days with eight-fold validation when using iEMG and sEMG with SSAE, whereas sEMG outperformed iEMG (p < 0.001) in between-day analysis both with two-fold and seven-fold validation schemes. The results obtained in this study imply that SSAE can significantly improve the performance of pattern recognition-based myoelectric control scheme and has the strength to extract deep information hidden in the EMG data.

KW - Autoencoders

KW - Biomedical signal processing

KW - Deep networks

KW - Intramuscular EMG

KW - Myocontrol

KW - Surface EMG

UR - http://www.scopus.com/inward/record.url?scp=85049912372&partnerID=8YFLogxK

U2 - 10.3390/app8071126

DO - 10.3390/app8071126

M3 - Journal article

VL - 8

JO - Applied Sciences

JF - Applied Sciences

SN - 1454-5101

IS - 7

M1 - 1126

ER -