EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors

Sumit Raurale; John McAllister; Jesus Martinez del Rincon

doi:10.1109/ICASSP.2018.8462409

EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors

Sumit Raurale, John McAllister, Jesus Martinez del Rincon

School of Electronics, Electrical Engineering and Computer Science

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

5 Citations (Scopus)

308 Downloads (Pure)

Abstract

This paper presents a unique real-time motion recognition system for Electromyographic (EMG) signal acquisition and classification. It is the first approach which can classify hand poses from multi-channel EMG signals gathered from randomly placed arm sensors as accurately as current placed-sensor EMG acquisition approaches. It combines time-domain feature extraction, Linear Discriminant Analysis (LDA) feature projection and Multilayer Perceptron (MLP) classification to allow nine distinct poses to be correctly identified more than 95% of the time. This is comparable to state-of-the-art placed-sensor EMG acquisition systems. Processing times of 11.70 ms also make this a viable candidate approach for real-time EMG acquisition and processing in practical prosthesis applications.

Original language	English
Title of host publication	2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings
Publisher	IEEE
Pages	1105-1109
Number of pages	5
DOIs	https://doi.org/10.1109/ICASSP.2018.8462409
Publication status	Published - 13 Sep 2018
Event	IEEE International Conference on Acoustics, Speech and Signal Processing - Calgary, Calgary, Canada Duration: 15 Jan 2018 → 20 Jan 2018 Conference number: 2018 https://2018.ieeeicassp.org/ https://2018.ieeeicassp.org

Publication series

Name	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings
Publisher	IEEE
ISSN (Electronic)	2379-190X

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP
Country	Canada
City	Calgary
Period	15/01/2018 → 20/01/2018
Internet address	https://2018.ieeeicassp.org/ https://2018.ieeeicassp.org

Keywords

Electromyographic (EMG), time-domain features, pattern recognition, linear discriminant analysis (LDA), multilayer perceptron (MLP).

Access to Document

10.1109/ICASSP.2018.8462409Licence: Unspecified

EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-Placed Sensors
Copyright 2018 IEEE. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 243 KBLicence: Unspecified

http://mirlab.org/conference_papers/International_Conference/ICASSP%202018/pdfs/0001105.pdf

Fingerprint Dive into the research topics of 'EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors'. Together they form a unique fingerprint.

Cite this

Raurale, S., McAllister, J., & Martinez del Rincon, J. (2018). EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings (pp. 1105-1109). (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings). IEEE . https://doi.org/10.1109/ICASSP.2018.8462409

Raurale, Sumit ; McAllister, John ; Martinez del Rincon, Jesus. / EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings. IEEE , 2018. pp. 1105-1109 (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings).

@inproceedings{d515a2a1bd91463f8f2adae78b3abb49,

title = "EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors",

abstract = "This paper presents a unique real-time motion recognition system for Electromyographic (EMG) signal acquisition and classification. It is the first approach which can classify hand poses from multi-channel EMG signals gathered from randomly placed arm sensors as accurately as current placed-sensor EMG acquisition approaches. It combines time-domain feature extraction, Linear Discriminant Analysis (LDA) feature projection and Multilayer Perceptron (MLP) classification to allow nine distinct poses to be correctly identified more than 95% of the time. This is comparable to state-of-the-art placed-sensor EMG acquisition systems. Processing times of 11.70 ms also make this a viable candidate approach for real-time EMG acquisition and processing in practical prosthesis applications.",

keywords = "Electromyographic (EMG), time-domain features, pattern recognition, linear discriminant analysis (LDA), multilayer perceptron (MLP).",

author = "Sumit Raurale and John McAllister and {Martinez del Rincon}, Jesus",

year = "2018",

month = sep,

day = "13",

doi = "10.1109/ICASSP.2018.8462409",

language = "English",

series = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings",

publisher = " IEEE ",

pages = "1105--1109",

booktitle = "2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP ; Conference date: 15-01-2018 Through 20-01-2018",

url = "https://2018.ieeeicassp.org/, https://2018.ieeeicassp.org",

}

Raurale, S, McAllister, J & Martinez del Rincon, J 2018, EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors. in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings, IEEE , pp. 1105-1109, IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, 15/01/2018. https://doi.org/10.1109/ICASSP.2018.8462409

EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors. / Raurale, Sumit; McAllister, John ; Martinez del Rincon, Jesus.

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings. IEEE , 2018. p. 1105-1109 (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings).

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

TY - GEN

T1 - EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors

AU - Raurale, Sumit

AU - McAllister, John

AU - Martinez del Rincon, Jesus

N1 - Conference code: 2018

PY - 2018/9/13

Y1 - 2018/9/13

N2 - This paper presents a unique real-time motion recognition system for Electromyographic (EMG) signal acquisition and classification. It is the first approach which can classify hand poses from multi-channel EMG signals gathered from randomly placed arm sensors as accurately as current placed-sensor EMG acquisition approaches. It combines time-domain feature extraction, Linear Discriminant Analysis (LDA) feature projection and Multilayer Perceptron (MLP) classification to allow nine distinct poses to be correctly identified more than 95% of the time. This is comparable to state-of-the-art placed-sensor EMG acquisition systems. Processing times of 11.70 ms also make this a viable candidate approach for real-time EMG acquisition and processing in practical prosthesis applications.

AB - This paper presents a unique real-time motion recognition system for Electromyographic (EMG) signal acquisition and classification. It is the first approach which can classify hand poses from multi-channel EMG signals gathered from randomly placed arm sensors as accurately as current placed-sensor EMG acquisition approaches. It combines time-domain feature extraction, Linear Discriminant Analysis (LDA) feature projection and Multilayer Perceptron (MLP) classification to allow nine distinct poses to be correctly identified more than 95% of the time. This is comparable to state-of-the-art placed-sensor EMG acquisition systems. Processing times of 11.70 ms also make this a viable candidate approach for real-time EMG acquisition and processing in practical prosthesis applications.

KW - Electromyographic (EMG), time-domain features, pattern recognition, linear discriminant analysis (LDA), multilayer perceptron (MLP).

UR - http://mirlab.org/conference_papers/International_Conference/ICASSP%202018/pdfs/0001105.pdf

U2 - 10.1109/ICASSP.2018.8462409

DO - 10.1109/ICASSP.2018.8462409

M3 - Conference contribution

T3 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings

SP - 1105

EP - 1109

BT - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings

PB - IEEE

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 15 January 2018 through 20 January 2018

ER -

Raurale S, McAllister J , Martinez del Rincon J. EMG Acquisition and Hand Pose Classification for Bionic Hands from Randomly-placed Sensors. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings. IEEE . 2018. p. 1105-1109. (IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings). https://doi.org/10.1109/ICASSP.2018.8462409