Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers

Yuni Teh, Richard B. Woodward, Levi J Hargrove

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

Abstract

Myoelectric pattern recognition using linear discriminant analysis (LDA) classifiers has been a wellestablished control method for upper limb prostheses for many years. More recently, linear regression (LR) controllers have been proposed as an alternative solution due to their ability to control multiple degrees of freedom (DOF) simultaneously. The aim of this experiment was to compare the online performance of LDA and LR control systems under three electromyographic (EMG) signal conditions: baseline, noise in all channels, and noise in a single channel. To simulate the last two conditions, different levels of Gaussian noise were added to the EMG signals. Completion rate, path efficiency, dwelling time, and completion time were computed after virtual Fitts' Law tasks. While both controllers were significantly affected by the lowest noise levels, we found no significant differences between the controllers under the baseline and all-channel noise conditions. However, the LDA controller outperformed the LR controller in the single-channel noise condition. Therefore, while both controllers are comparable in most cases, the added complexity of simultaneous control affects an LR controller's performance under certain noise conditions. Based on these results, neither control system should be dismissed in future developments.

Original languageEnglish (US)
Title of host publication40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2132-2135
Number of pages4
Volume2018-July
ISBN (Electronic)9781538636466
DOIs
StatePublished - Oct 26 2018
Event40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 - Honolulu, United States
Duration: Jul 18 2018Jul 21 2018

Other

Other40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
CountryUnited States
CityHonolulu
Period7/18/187/21/18

Fingerprint

Linear regression
Pattern recognition
Noise
Linear Models
Discriminant Analysis
Controllers
Discriminant analysis
Artificial Limbs
Upper Extremity
Control systems
Prosthetics
Classifiers
Experiments

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Teh, Y., Woodward, R. B., & Hargrove, L. J. (2018). Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (Vol. 2018-July, pp. 2132-2135). [8512693] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2018.8512693
Teh, Yuni ; Woodward, Richard B. ; Hargrove, Levi J. / Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. pp. 2132-2135
@inproceedings{83d303e3e8c7432d83cfeb38c67c108a,
title = "Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers",
abstract = "Myoelectric pattern recognition using linear discriminant analysis (LDA) classifiers has been a wellestablished control method for upper limb prostheses for many years. More recently, linear regression (LR) controllers have been proposed as an alternative solution due to their ability to control multiple degrees of freedom (DOF) simultaneously. The aim of this experiment was to compare the online performance of LDA and LR control systems under three electromyographic (EMG) signal conditions: baseline, noise in all channels, and noise in a single channel. To simulate the last two conditions, different levels of Gaussian noise were added to the EMG signals. Completion rate, path efficiency, dwelling time, and completion time were computed after virtual Fitts' Law tasks. While both controllers were significantly affected by the lowest noise levels, we found no significant differences between the controllers under the baseline and all-channel noise conditions. However, the LDA controller outperformed the LR controller in the single-channel noise condition. Therefore, while both controllers are comparable in most cases, the added complexity of simultaneous control affects an LR controller's performance under certain noise conditions. Based on these results, neither control system should be dismissed in future developments.",
author = "Yuni Teh and Woodward, {Richard B.} and Hargrove, {Levi J}",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/EMBC.2018.8512693",
language = "English (US)",
volume = "2018-July",
pages = "2132--2135",
booktitle = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Teh, Y, Woodward, RB & Hargrove, LJ 2018, Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. vol. 2018-July, 8512693, Institute of Electrical and Electronics Engineers Inc., pp. 2132-2135, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018, Honolulu, United States, 7/18/18. https://doi.org/10.1109/EMBC.2018.8512693

Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers. / Teh, Yuni; Woodward, Richard B.; Hargrove, Levi J.

40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July Institute of Electrical and Electronics Engineers Inc., 2018. p. 2132-2135 8512693.

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

TY - GEN

T1 - Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers

AU - Teh, Yuni

AU - Woodward, Richard B.

AU - Hargrove, Levi J

PY - 2018/10/26

Y1 - 2018/10/26

N2 - Myoelectric pattern recognition using linear discriminant analysis (LDA) classifiers has been a wellestablished control method for upper limb prostheses for many years. More recently, linear regression (LR) controllers have been proposed as an alternative solution due to their ability to control multiple degrees of freedom (DOF) simultaneously. The aim of this experiment was to compare the online performance of LDA and LR control systems under three electromyographic (EMG) signal conditions: baseline, noise in all channels, and noise in a single channel. To simulate the last two conditions, different levels of Gaussian noise were added to the EMG signals. Completion rate, path efficiency, dwelling time, and completion time were computed after virtual Fitts' Law tasks. While both controllers were significantly affected by the lowest noise levels, we found no significant differences between the controllers under the baseline and all-channel noise conditions. However, the LDA controller outperformed the LR controller in the single-channel noise condition. Therefore, while both controllers are comparable in most cases, the added complexity of simultaneous control affects an LR controller's performance under certain noise conditions. Based on these results, neither control system should be dismissed in future developments.

AB - Myoelectric pattern recognition using linear discriminant analysis (LDA) classifiers has been a wellestablished control method for upper limb prostheses for many years. More recently, linear regression (LR) controllers have been proposed as an alternative solution due to their ability to control multiple degrees of freedom (DOF) simultaneously. The aim of this experiment was to compare the online performance of LDA and LR control systems under three electromyographic (EMG) signal conditions: baseline, noise in all channels, and noise in a single channel. To simulate the last two conditions, different levels of Gaussian noise were added to the EMG signals. Completion rate, path efficiency, dwelling time, and completion time were computed after virtual Fitts' Law tasks. While both controllers were significantly affected by the lowest noise levels, we found no significant differences between the controllers under the baseline and all-channel noise conditions. However, the LDA controller outperformed the LR controller in the single-channel noise condition. Therefore, while both controllers are comparable in most cases, the added complexity of simultaneous control affects an LR controller's performance under certain noise conditions. Based on these results, neither control system should be dismissed in future developments.

UR - http://www.scopus.com/inward/record.url?scp=85056630986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056630986&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8512693

DO - 10.1109/EMBC.2018.8512693

M3 - Conference contribution

VL - 2018-July

SP - 2132

EP - 2135

BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Teh Y, Woodward RB, Hargrove LJ. Comparing the Effects of Signal Noise on Pattern Recognition and Linear Regression-Based Myoelectric Controllers. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Vol. 2018-July. Institute of Electrical and Electronics Engineers Inc. 2018. p. 2132-2135. 8512693 https://doi.org/10.1109/EMBC.2018.8512693