Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning

Joseph L. Betthauser, Christopher L. Hunt, Luke E. Osborn, Matthew R. Masters, Gyorgy Levay, Rahul Reddy Kaliki, Nitish V Thakor

Research output: Contribution to journalArticle

Abstract

Myoelectric signals can be used to predict the intended movements of an amputee for prosthesis control. However, untrained effects like limb position changes influence myoelectric signal characteristics, hindering the ability of pattern recognition algorithms to discriminate among motion classes. Despite frequent and long training sessions, these deleterious conditional influences may result in poor performance and device abandonment. Goal: We present a robust sparsity-based adaptive classification method that is significantly less sensitive to signal deviations resulting from untrained conditions. Methods: We compare this approach in the offline and online contexts of untrained upper-limb positions for amputee and able-bodied subjects to demonstrate its robustness compared against other myoelectric classification methods. Results: We report significant performance improvements (p<0.001) in untrained limb positions across all subject groups. Significance: The robustness of our suggested approach helps to ensure better untrained condition performance from fewer training conditions. Conclusions: This method of prosthesis control has the potential to deliver real-world clinical benefits to amputees: better condition-tolerant performance, reduced training burden in terms of frequency and duration, and increased adoption of myoelectric prostheses.

Original languageEnglish (US)
JournalIEEE Transactions on Biomedical Engineering
DOIs
StateAccepted/In press - Jun 23 2017

Fingerprint

Pattern recognition
Prosthetics
Prostheses and Implants

Keywords

  • amputee
  • EASRC
  • Electromyography
  • EMG
  • limb position
  • myoelectric
  • Pattern recognition
  • prosthesis
  • Prosthetics
  • Real-time systems
  • robust
  • Robustness
  • sparse
  • SRC
  • Training
  • Training data

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning. / Betthauser, Joseph L.; Hunt, Christopher L.; Osborn, Luke E.; Masters, Matthew R.; Levay, Gyorgy; Kaliki, Rahul Reddy; Thakor, Nitish V.

In: IEEE Transactions on Biomedical Engineering, 23.06.2017.

Research output: Contribution to journalArticle

Betthauser, Joseph L. ; Hunt, Christopher L. ; Osborn, Luke E. ; Masters, Matthew R. ; Levay, Gyorgy ; Kaliki, Rahul Reddy ; Thakor, Nitish V. / Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning. In: IEEE Transactions on Biomedical Engineering. 2017.
@article{96167bf6a0564ce990b96b0655304f68,
title = "Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning",
abstract = "Myoelectric signals can be used to predict the intended movements of an amputee for prosthesis control. However, untrained effects like limb position changes influence myoelectric signal characteristics, hindering the ability of pattern recognition algorithms to discriminate among motion classes. Despite frequent and long training sessions, these deleterious conditional influences may result in poor performance and device abandonment. Goal: We present a robust sparsity-based adaptive classification method that is significantly less sensitive to signal deviations resulting from untrained conditions. Methods: We compare this approach in the offline and online contexts of untrained upper-limb positions for amputee and able-bodied subjects to demonstrate its robustness compared against other myoelectric classification methods. Results: We report significant performance improvements (p<0.001) in untrained limb positions across all subject groups. Significance: The robustness of our suggested approach helps to ensure better untrained condition performance from fewer training conditions. Conclusions: This method of prosthesis control has the potential to deliver real-world clinical benefits to amputees: better condition-tolerant performance, reduced training burden in terms of frequency and duration, and increased adoption of myoelectric prostheses.",
keywords = "amputee, EASRC, Electromyography, EMG, limb position, myoelectric, Pattern recognition, prosthesis, Prosthetics, Real-time systems, robust, Robustness, sparse, SRC, Training, Training data",
author = "Betthauser, {Joseph L.} and Hunt, {Christopher L.} and Osborn, {Luke E.} and Masters, {Matthew R.} and Gyorgy Levay and Kaliki, {Rahul Reddy} and Thakor, {Nitish V}",
year = "2017",
month = "6",
day = "23",
doi = "10.1109/TBME.2017.2719400",
language = "English (US)",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations from Extreme Learning

AU - Betthauser, Joseph L.

AU - Hunt, Christopher L.

AU - Osborn, Luke E.

AU - Masters, Matthew R.

AU - Levay, Gyorgy

AU - Kaliki, Rahul Reddy

AU - Thakor, Nitish V

PY - 2017/6/23

Y1 - 2017/6/23

N2 - Myoelectric signals can be used to predict the intended movements of an amputee for prosthesis control. However, untrained effects like limb position changes influence myoelectric signal characteristics, hindering the ability of pattern recognition algorithms to discriminate among motion classes. Despite frequent and long training sessions, these deleterious conditional influences may result in poor performance and device abandonment. Goal: We present a robust sparsity-based adaptive classification method that is significantly less sensitive to signal deviations resulting from untrained conditions. Methods: We compare this approach in the offline and online contexts of untrained upper-limb positions for amputee and able-bodied subjects to demonstrate its robustness compared against other myoelectric classification methods. Results: We report significant performance improvements (p<0.001) in untrained limb positions across all subject groups. Significance: The robustness of our suggested approach helps to ensure better untrained condition performance from fewer training conditions. Conclusions: This method of prosthesis control has the potential to deliver real-world clinical benefits to amputees: better condition-tolerant performance, reduced training burden in terms of frequency and duration, and increased adoption of myoelectric prostheses.

AB - Myoelectric signals can be used to predict the intended movements of an amputee for prosthesis control. However, untrained effects like limb position changes influence myoelectric signal characteristics, hindering the ability of pattern recognition algorithms to discriminate among motion classes. Despite frequent and long training sessions, these deleterious conditional influences may result in poor performance and device abandonment. Goal: We present a robust sparsity-based adaptive classification method that is significantly less sensitive to signal deviations resulting from untrained conditions. Methods: We compare this approach in the offline and online contexts of untrained upper-limb positions for amputee and able-bodied subjects to demonstrate its robustness compared against other myoelectric classification methods. Results: We report significant performance improvements (p<0.001) in untrained limb positions across all subject groups. Significance: The robustness of our suggested approach helps to ensure better untrained condition performance from fewer training conditions. Conclusions: This method of prosthesis control has the potential to deliver real-world clinical benefits to amputees: better condition-tolerant performance, reduced training burden in terms of frequency and duration, and increased adoption of myoelectric prostheses.

KW - amputee

KW - EASRC

KW - Electromyography

KW - EMG

KW - limb position

KW - myoelectric

KW - Pattern recognition

KW - prosthesis

KW - Prosthetics

KW - Real-time systems

KW - robust

KW - Robustness

KW - sparse

KW - SRC

KW - Training

KW - Training data

UR - http://www.scopus.com/inward/record.url?scp=85023768533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023768533&partnerID=8YFLogxK

U2 - 10.1109/TBME.2017.2719400

DO - 10.1109/TBME.2017.2719400

M3 - Article

C2 - 28650804

AN - SCOPUS:85023768533

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

ER -