Myoelectric pattern recognition using dynamic motions with limb position changes

Sungtae Shin, Reza Tafreshi, Reza Langari

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

4 Citations (Scopus)

Abstract

Myoelectric pattern recognition discriminates myoelectric signal patterns to recognize human gestures because myoelectric signal exhibits muscular activities of human motions. This technique has been broadly researched for prosthetic devices and human computer interface. However, it still has robustness issues caused by various conditions: limb position changes, long-term uses, electrode shifts, and skin condition changes. These issues have compromised the reliability of pattern recognition technique in myoelectric systems. In order to increase the reliability in the limb position effect, this paper develops a myoelectric system using dynamic motions. For the classification of dynamic motions, dynamic time warping technique was used for the alignment of two different time-length motions and correlation coefficient was then calculated as a similarity metric. For comparison purposes, static motions were classified by Naïve Bayesian classifier for the classification and Fisher's Linear Discriminant Analysis for the dimensionality reduction. Static and dynamic motions were collected at four different limb positions for estimating the robustness to the limb position effect. The statistical analysis, t-test (p<0.05), showed that dynamic motions were more robust to the limb position effect than static motions from all eight subjects when training and validation sets were extracted from different limb positions. Subject 5 showed the best classification accuracy: 97.59% with 3.54% standard deviation (SD) for dynamic motions and 71.85% with 12.62% SD for static motions when training and validation sets were picked from different limb positions.

Original languageEnglish
Title of host publication2016 American Control Conference, ACC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4901-4906
Number of pages6
Volume2016-July
ISBN (Electronic)9781467386821
DOIs
Publication statusPublished - 28 Jul 2016
Event2016 American Control Conference, ACC 2016 - Boston, United States
Duration: 6 Jul 20168 Jul 2016

Other

Other2016 American Control Conference, ACC 2016
CountryUnited States
CityBoston
Period6/7/168/7/16

Fingerprint

Pattern recognition
Discriminant analysis
Prosthetics
Interfaces (computer)
Statistical methods
Skin
Dynamical systems
Classifiers
Electrodes

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Shin, S., Tafreshi, R., & Langari, R. (2016). Myoelectric pattern recognition using dynamic motions with limb position changes. In 2016 American Control Conference, ACC 2016 (Vol. 2016-July, pp. 4901-4906). [7526129] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACC.2016.7526129

Myoelectric pattern recognition using dynamic motions with limb position changes. / Shin, Sungtae; Tafreshi, Reza; Langari, Reza.

2016 American Control Conference, ACC 2016. Vol. 2016-July Institute of Electrical and Electronics Engineers Inc., 2016. p. 4901-4906 7526129.

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

Shin, S, Tafreshi, R & Langari, R 2016, Myoelectric pattern recognition using dynamic motions with limb position changes. in 2016 American Control Conference, ACC 2016. vol. 2016-July, 7526129, Institute of Electrical and Electronics Engineers Inc., pp. 4901-4906, 2016 American Control Conference, ACC 2016, Boston, United States, 6/7/16. https://doi.org/10.1109/ACC.2016.7526129
Shin S, Tafreshi R, Langari R. Myoelectric pattern recognition using dynamic motions with limb position changes. In 2016 American Control Conference, ACC 2016. Vol. 2016-July. Institute of Electrical and Electronics Engineers Inc. 2016. p. 4901-4906. 7526129 https://doi.org/10.1109/ACC.2016.7526129
Shin, Sungtae ; Tafreshi, Reza ; Langari, Reza. / Myoelectric pattern recognition using dynamic motions with limb position changes. 2016 American Control Conference, ACC 2016. Vol. 2016-July Institute of Electrical and Electronics Engineers Inc., 2016. pp. 4901-4906
@inproceedings{cd1f77b7f7094746b52deca377525ef5,
title = "Myoelectric pattern recognition using dynamic motions with limb position changes",
abstract = "Myoelectric pattern recognition discriminates myoelectric signal patterns to recognize human gestures because myoelectric signal exhibits muscular activities of human motions. This technique has been broadly researched for prosthetic devices and human computer interface. However, it still has robustness issues caused by various conditions: limb position changes, long-term uses, electrode shifts, and skin condition changes. These issues have compromised the reliability of pattern recognition technique in myoelectric systems. In order to increase the reliability in the limb position effect, this paper develops a myoelectric system using dynamic motions. For the classification of dynamic motions, dynamic time warping technique was used for the alignment of two different time-length motions and correlation coefficient was then calculated as a similarity metric. For comparison purposes, static motions were classified by Na{\"i}ve Bayesian classifier for the classification and Fisher's Linear Discriminant Analysis for the dimensionality reduction. Static and dynamic motions were collected at four different limb positions for estimating the robustness to the limb position effect. The statistical analysis, t-test (p<0.05), showed that dynamic motions were more robust to the limb position effect than static motions from all eight subjects when training and validation sets were extracted from different limb positions. Subject 5 showed the best classification accuracy: 97.59{\%} with 3.54{\%} standard deviation (SD) for dynamic motions and 71.85{\%} with 12.62{\%} SD for static motions when training and validation sets were picked from different limb positions.",
author = "Sungtae Shin and Reza Tafreshi and Reza Langari",
year = "2016",
month = "7",
day = "28",
doi = "10.1109/ACC.2016.7526129",
language = "English",
volume = "2016-July",
pages = "4901--4906",
booktitle = "2016 American Control Conference, ACC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Myoelectric pattern recognition using dynamic motions with limb position changes

AU - Shin, Sungtae

AU - Tafreshi, Reza

AU - Langari, Reza

PY - 2016/7/28

Y1 - 2016/7/28

N2 - Myoelectric pattern recognition discriminates myoelectric signal patterns to recognize human gestures because myoelectric signal exhibits muscular activities of human motions. This technique has been broadly researched for prosthetic devices and human computer interface. However, it still has robustness issues caused by various conditions: limb position changes, long-term uses, electrode shifts, and skin condition changes. These issues have compromised the reliability of pattern recognition technique in myoelectric systems. In order to increase the reliability in the limb position effect, this paper develops a myoelectric system using dynamic motions. For the classification of dynamic motions, dynamic time warping technique was used for the alignment of two different time-length motions and correlation coefficient was then calculated as a similarity metric. For comparison purposes, static motions were classified by Naïve Bayesian classifier for the classification and Fisher's Linear Discriminant Analysis for the dimensionality reduction. Static and dynamic motions were collected at four different limb positions for estimating the robustness to the limb position effect. The statistical analysis, t-test (p<0.05), showed that dynamic motions were more robust to the limb position effect than static motions from all eight subjects when training and validation sets were extracted from different limb positions. Subject 5 showed the best classification accuracy: 97.59% with 3.54% standard deviation (SD) for dynamic motions and 71.85% with 12.62% SD for static motions when training and validation sets were picked from different limb positions.

AB - Myoelectric pattern recognition discriminates myoelectric signal patterns to recognize human gestures because myoelectric signal exhibits muscular activities of human motions. This technique has been broadly researched for prosthetic devices and human computer interface. However, it still has robustness issues caused by various conditions: limb position changes, long-term uses, electrode shifts, and skin condition changes. These issues have compromised the reliability of pattern recognition technique in myoelectric systems. In order to increase the reliability in the limb position effect, this paper develops a myoelectric system using dynamic motions. For the classification of dynamic motions, dynamic time warping technique was used for the alignment of two different time-length motions and correlation coefficient was then calculated as a similarity metric. For comparison purposes, static motions were classified by Naïve Bayesian classifier for the classification and Fisher's Linear Discriminant Analysis for the dimensionality reduction. Static and dynamic motions were collected at four different limb positions for estimating the robustness to the limb position effect. The statistical analysis, t-test (p<0.05), showed that dynamic motions were more robust to the limb position effect than static motions from all eight subjects when training and validation sets were extracted from different limb positions. Subject 5 showed the best classification accuracy: 97.59% with 3.54% standard deviation (SD) for dynamic motions and 71.85% with 12.62% SD for static motions when training and validation sets were picked from different limb positions.

UR - http://www.scopus.com/inward/record.url?scp=84992151615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992151615&partnerID=8YFLogxK

U2 - 10.1109/ACC.2016.7526129

DO - 10.1109/ACC.2016.7526129

M3 - Conference contribution

VL - 2016-July

SP - 4901

EP - 4906

BT - 2016 American Control Conference, ACC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -