LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

Christopher Millar; N Siddique; Emmett Kerr

doi:10.1109/CcS49175.2020.9231515

LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

Christopher Millar, N Siddique, Emmett Kerr

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

256 Downloads (Pure)

Abstract

The electrical activity of the muscles that control finger movements can be extracted during the performance of these movements and using machine learning techniques, the myoelectric signals can be decoded and classified according to the movement that generated the specific signal. The focus of this paper is to classify sEMG signal using easily accessible cheap hardware to capture the signal. Furthermore, to employ neural networks to classify the signal using established methodology i.e. feature extraction, with the highest possible accuracy. To classify these sEMG signals, an LSTM network has been developed and was able to classify 12 individual finger movements with accuracies reaching 90%.

Original language	English
Title of host publication	2020 International Symposium on Community-Centric Systems, CcS 2020
Publisher	IEEE
Pages	1-8
Number of pages	8
ISBN (Electronic)	978-1-7281-8741-9
ISBN (Print)	978-1-7281-8742-6
DOIs	https://doi.org/10.1109/CcS49175.2020.9231515
Publication status	Published (in print/issue) - 20 Oct 2020

Publication series

Name	2020 International Symposium on Community-Centric Systems, CcS 2020

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Finger Movement Classification
LSTM
Myo
sEMG

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CcS49175.2020.9231515

FinalDraftAuthor Accepted Manuscript, 949 KB
CCS2020FDFinal published version, 986 KB

https://ieeexplore.ieee.org/document/9231515

Cite this

@inproceedings{ba88f5de92e84b769600dce7a33cc07e,

title = "LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor",

abstract = "The electrical activity of the muscles that control finger movements can be extracted during the performance of these movements and using machine learning techniques, the myoelectric signals can be decoded and classified according to the movement that generated the specific signal. The focus of this paper is to classify sEMG signal using easily accessible cheap hardware to capture the signal. Furthermore, to employ neural networks to classify the signal using established methodology i.e. feature extraction, with the highest possible accuracy. To classify these sEMG signals, an LSTM network has been developed and was able to classify 12 individual finger movements with accuracies reaching 90%.",

keywords = "Finger Movement Classification, LSTM, Myo, sEMG",

author = "Christopher Millar and N Siddique and Emmett Kerr",

year = "2020",

month = oct,

day = "20",

doi = "10.1109/CcS49175.2020.9231515",

language = "English",

isbn = "978-1-7281-8742-6",

series = "2020 International Symposium on Community-Centric Systems, CcS 2020",

publisher = "IEEE",

pages = "1--8",

booktitle = "2020 International Symposium on Community-Centric Systems, CcS 2020",

address = "United States",

}

LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor. / Millar, Christopher; Siddique, N ; Kerr, Emmett.
2020 International Symposium on Community-Centric Systems, CcS 2020. IEEE, 2020. p. 1-8 9231515 (2020 International Symposium on Community-Centric Systems, CcS 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

AU - Millar, Christopher

AU - Siddique, N

AU - Kerr, Emmett

PY - 2020/10/20

Y1 - 2020/10/20

N2 - The electrical activity of the muscles that control finger movements can be extracted during the performance of these movements and using machine learning techniques, the myoelectric signals can be decoded and classified according to the movement that generated the specific signal. The focus of this paper is to classify sEMG signal using easily accessible cheap hardware to capture the signal. Furthermore, to employ neural networks to classify the signal using established methodology i.e. feature extraction, with the highest possible accuracy. To classify these sEMG signals, an LSTM network has been developed and was able to classify 12 individual finger movements with accuracies reaching 90%.

AB - The electrical activity of the muscles that control finger movements can be extracted during the performance of these movements and using machine learning techniques, the myoelectric signals can be decoded and classified according to the movement that generated the specific signal. The focus of this paper is to classify sEMG signal using easily accessible cheap hardware to capture the signal. Furthermore, to employ neural networks to classify the signal using established methodology i.e. feature extraction, with the highest possible accuracy. To classify these sEMG signals, an LSTM network has been developed and was able to classify 12 individual finger movements with accuracies reaching 90%.

KW - Finger Movement Classification

KW - LSTM

KW - Myo

KW - sEMG

UR - http://www.scopus.com/inward/record.url?scp=85096583637&partnerID=8YFLogxK

U2 - 10.1109/CcS49175.2020.9231515

DO - 10.1109/CcS49175.2020.9231515

M3 - Conference contribution

SN - 978-1-7281-8742-6

T3 - 2020 International Symposium on Community-Centric Systems, CcS 2020

SP - 1

EP - 8

BT - 2020 International Symposium on Community-Centric Systems, CcS 2020

PB - IEEE

ER -

LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

Abstract

Publication series

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

LSTM Network Classification of Dexterous Individual Finger Movements

Cite this