Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms

Bipasha Kundu; Desineni Subarram Naidu

doi:10.1109/ICECCE52056.2021.9514134

Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms

Bipasha Kundu, Desineni Subarram Naidu

Electrical Engineering

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

5 Scopus citations

Abstract

Prosthetic plays an important role for the amputees to improve the ability and mobility of their regular activities. Electromyography(EMG) has been used for decades in the control of the motorized upper-limb prosthesis. Processed EMG can imitate human movements. Mayo armband is a wireless sensor of low power, Bluetooth, and small interference which provides a good quality EMG signal. The Myo armband measures the EMG from the upper-limb. In this paper, the statistical time-domain features have been considered to classify different hand movements. The classification and comparison have been performed by 4 different Machine Learning based algorithms i.e. Support Vector Machine(SVM), Naïve Bayes(NB), Random Forest(RF), and K-Nearest Neighbor(KNN). The data has been collected from subjects (males and females) of different ages. The classifier model has used 80% data as a training set and the remaining 20% of data as the test set. The result shows that Random Forest and SVM outperform the other two algorithms with an accuracy of 98 %. Referring to the accuracy here, this classification model serves as a promising candidate for the input of prosthetic hand control systems.

Original language	English (US)
Title of host publication	3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665438971
DOIs	https://doi.org/10.1109/ICECCE52056.2021.9514134
State	Published - Jun 12 2021
Event	3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021 - Kuala Lumpur, Malaysia Duration: Jun 12 2021 → Jun 13 2021

Publication series

Name	3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021

Conference

Conference	3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021
Country/Territory	Malaysia
City	Kuala Lumpur
Period	6/12/21 → 6/13/21

Bibliographical note

Funding Information:
The first author would like to acknowledge her advisor Dr. Desineni Subbaram Naidu, for his patience and encouragement to work with Machine Learning and the people who voluntarily gave the EMG data for this work. Also thanks are due to EE department at University of Minnesota, Duluth (UMD) for supporting the first author's graduate study.

Publisher Copyright:
© 2021 IEEE.

Keywords

K Nearest Neighbor(KNN)
Naï ve Bayes(NB)
Random Forest(RF)
Support Vector Machine(SVM)
electromyography
machine learning
myo armband
prosthesis
time domain feature extraction

Access

10.1109/ICECCE52056.2021.9514134

OpenUrl availability

Full text

Cite this

Kundu, B., & Naidu, D. S. (2021). Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms. In 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021 (3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECCE52056.2021.9514134

Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms. / Kundu, Bipasha; Naidu, Desineni Subarram.
3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021).

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

Kundu, B & Naidu, DS 2021, Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms. in 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021. 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021, Institute of Electrical and Electronics Engineers Inc., 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021, Kuala Lumpur, Malaysia, 6/12/21. https://doi.org/10.1109/ICECCE52056.2021.9514134

Kundu B, Naidu DS. Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms. In 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021). doi: 10.1109/ICECCE52056.2021.9514134

Kundu, Bipasha ; Naidu, Desineni Subarram. / Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms. 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021).

@inproceedings{8a13983348644848927ccd3488ca58ad,

title = "Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms",

abstract = "Prosthetic plays an important role for the amputees to improve the ability and mobility of their regular activities. Electromyography(EMG) has been used for decades in the control of the motorized upper-limb prosthesis. Processed EMG can imitate human movements. Mayo armband is a wireless sensor of low power, Bluetooth, and small interference which provides a good quality EMG signal. The Myo armband measures the EMG from the upper-limb. In this paper, the statistical time-domain features have been considered to classify different hand movements. The classification and comparison have been performed by 4 different Machine Learning based algorithms i.e. Support Vector Machine(SVM), Na{\"i}ve Bayes(NB), Random Forest(RF), and K-Nearest Neighbor(KNN). The data has been collected from subjects (males and females) of different ages. The classifier model has used 80% data as a training set and the remaining 20% of data as the test set. The result shows that Random Forest and SVM outperform the other two algorithms with an accuracy of 98 %. Referring to the accuracy here, this classification model serves as a promising candidate for the input of prosthetic hand control systems.",

keywords = "K Nearest Neighbor(KNN), Na{\"i} ve Bayes(NB), Random Forest(RF), Support Vector Machine(SVM), electromyography, machine learning, myo armband, prosthesis, time domain feature extraction",

author = "Bipasha Kundu and Naidu, {Desineni Subarram}",

note = "Funding Information: The first author would like to acknowledge her advisor Dr. Desineni Subbaram Naidu, for his patience and encouragement to work with Machine Learning and the people who voluntarily gave the EMG data for this work. Also thanks are due to EE department at University of Minnesota, Duluth (UMD) for supporting the first author's graduate study. Publisher Copyright: {\textcopyright} 2021 IEEE.; 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021 ; Conference date: 12-06-2021 Through 13-06-2021",

year = "2021",

month = jun,

day = "12",

doi = "10.1109/ICECCE52056.2021.9514134",

language = "English (US)",

series = "3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021",

}

TY - GEN

T1 - Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms

AU - Kundu, Bipasha

AU - Naidu, Desineni Subarram

N1 - Funding Information: The first author would like to acknowledge her advisor Dr. Desineni Subbaram Naidu, for his patience and encouragement to work with Machine Learning and the people who voluntarily gave the EMG data for this work. Also thanks are due to EE department at University of Minnesota, Duluth (UMD) for supporting the first author's graduate study. Publisher Copyright: © 2021 IEEE.

PY - 2021/6/12

Y1 - 2021/6/12

N2 - Prosthetic plays an important role for the amputees to improve the ability and mobility of their regular activities. Electromyography(EMG) has been used for decades in the control of the motorized upper-limb prosthesis. Processed EMG can imitate human movements. Mayo armband is a wireless sensor of low power, Bluetooth, and small interference which provides a good quality EMG signal. The Myo armband measures the EMG from the upper-limb. In this paper, the statistical time-domain features have been considered to classify different hand movements. The classification and comparison have been performed by 4 different Machine Learning based algorithms i.e. Support Vector Machine(SVM), Naïve Bayes(NB), Random Forest(RF), and K-Nearest Neighbor(KNN). The data has been collected from subjects (males and females) of different ages. The classifier model has used 80% data as a training set and the remaining 20% of data as the test set. The result shows that Random Forest and SVM outperform the other two algorithms with an accuracy of 98 %. Referring to the accuracy here, this classification model serves as a promising candidate for the input of prosthetic hand control systems.

AB - Prosthetic plays an important role for the amputees to improve the ability and mobility of their regular activities. Electromyography(EMG) has been used for decades in the control of the motorized upper-limb prosthesis. Processed EMG can imitate human movements. Mayo armband is a wireless sensor of low power, Bluetooth, and small interference which provides a good quality EMG signal. The Myo armband measures the EMG from the upper-limb. In this paper, the statistical time-domain features have been considered to classify different hand movements. The classification and comparison have been performed by 4 different Machine Learning based algorithms i.e. Support Vector Machine(SVM), Naïve Bayes(NB), Random Forest(RF), and K-Nearest Neighbor(KNN). The data has been collected from subjects (males and females) of different ages. The classifier model has used 80% data as a training set and the remaining 20% of data as the test set. The result shows that Random Forest and SVM outperform the other two algorithms with an accuracy of 98 %. Referring to the accuracy here, this classification model serves as a promising candidate for the input of prosthetic hand control systems.

KW - K Nearest Neighbor(KNN)

KW - Naï ve Bayes(NB)

KW - Random Forest(RF)

KW - Support Vector Machine(SVM)

KW - electromyography

KW - machine learning

KW - myo armband

KW - prosthesis

KW - time domain feature extraction

UR - http://www.scopus.com/inward/record.url?scp=85115092984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115092984&partnerID=8YFLogxK

U2 - 10.1109/ICECCE52056.2021.9514134

DO - 10.1109/ICECCE52056.2021.9514134

M3 - Conference contribution

AN - SCOPUS:85115092984

T3 - 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021

BT - 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2021

Y2 - 12 June 2021 through 13 June 2021

ER -

Classification and Feature Extraction of Different Hand Movements from EMG Signal using Machine Leaning based Algorithms

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this