A performance comparison of emg classification methods for hand and finger motion

Sungtae Shin, Reza Langari, Reza Tafreshi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

For recognizing human motion intent, electromyogram (EMG) based pattern recognition app roaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical app lication, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: naïve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the timedomain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.

Original languageEnglish
Title of host publicationDynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing
PublisherAmerican Society of Mechanical Engineers
Volume2
ISBN (Electronic)9780791846193
DOIs
Publication statusPublished - 2014
EventASME 2014 Dynamic Systems and Control Conference, DSCC 2014 - San Antonio, United States
Duration: 22 Oct 201424 Oct 2014

Other

OtherASME 2014 Dynamic Systems and Control Conference, DSCC 2014
CountryUnited States
CitySan Antonio
Period22/10/1424/10/14

Fingerprint

Discriminant analysis
Application programs
Pattern recognition
Feature extraction
Discrete wavelet transforms
Multilayer neural networks
Principal component analysis
Support vector machines
Learning systems
Decomposition

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Cite this

Shin, S., Langari, R., & Tafreshi, R. (2014). A performance comparison of emg classification methods for hand and finger motion. In Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing (Vol. 2). [5993] American Society of Mechanical Engineers. https://doi.org/10.1115/DSCC2014-5993

A performance comparison of emg classification methods for hand and finger motion. / Shin, Sungtae; Langari, Reza; Tafreshi, Reza.

Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing. Vol. 2 American Society of Mechanical Engineers, 2014. 5993.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shin, S, Langari, R & Tafreshi, R 2014, A performance comparison of emg classification methods for hand and finger motion. in Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing. vol. 2, 5993, American Society of Mechanical Engineers, ASME 2014 Dynamic Systems and Control Conference, DSCC 2014, San Antonio, United States, 22/10/14. https://doi.org/10.1115/DSCC2014-5993
Shin S, Langari R, Tafreshi R. A performance comparison of emg classification methods for hand and finger motion. In Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing. Vol. 2. American Society of Mechanical Engineers. 2014. 5993 https://doi.org/10.1115/DSCC2014-5993
Shin, Sungtae ; Langari, Reza ; Tafreshi, Reza. / A performance comparison of emg classification methods for hand and finger motion. Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing. Vol. 2 American Society of Mechanical Engineers, 2014.
@inproceedings{8680d3f720364d348feba1f12dc01547,
title = "A performance comparison of emg classification methods for hand and finger motion",
abstract = "For recognizing human motion intent, electromyogram (EMG) based pattern recognition app roaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical app lication, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: na{\"i}ve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the timedomain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.",
author = "Sungtae Shin and Reza Langari and Reza Tafreshi",
year = "2014",
doi = "10.1115/DSCC2014-5993",
language = "English",
volume = "2",
booktitle = "Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing",
publisher = "American Society of Mechanical Engineers",

}

TY - GEN

T1 - A performance comparison of emg classification methods for hand and finger motion

AU - Shin, Sungtae

AU - Langari, Reza

AU - Tafreshi, Reza

PY - 2014

Y1 - 2014

N2 - For recognizing human motion intent, electromyogram (EMG) based pattern recognition app roaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical app lication, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: naïve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the timedomain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.

AB - For recognizing human motion intent, electromyogram (EMG) based pattern recognition app roaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical app lication, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: naïve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the timedomain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.

UR - http://www.scopus.com/inward/record.url?scp=84929245497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929245497&partnerID=8YFLogxK

U2 - 10.1115/DSCC2014-5993

DO - 10.1115/DSCC2014-5993

M3 - Conference contribution

AN - SCOPUS:84929245497

VL - 2

BT - Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing

PB - American Society of Mechanical Engineers

ER -