TY - GEN
T1 - Limb-position robust classification of myoelectric signals for prosthesis control using sparse representations
AU - Betthauser, Joseph L.
AU - Hunt, Christopher L.
AU - Osborn, Luke E.
AU - Kaliki, Rahul R.
AU - Thakor, Nitish V.
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/13
Y1 - 2016/10/13
N2 - The fundamental objective in non-invasive myoelectric prosthesis control is to determine the user's intended movements from corresponding skin-surface recorded electromyographic (sEMG) activation signals as quickly and accurately as possible. Linear Discriminant Analysis (LDA) has emerged as the de facto standard for real-time movement classification due to its ease of use, calculation speed, and remarkable classification accuracy under controlled training conditions. However, performance of cluster-based methods like LDA for sEMG pattern recognition degrades significantly when real-world testing conditions do not resemble the trained conditions, limiting the utility of myoelectrically controlled prosthesis devices. We propose an enhanced classification method that is more robust to generic deviations from training conditions by constructing sparse representations of the input data dictionary comprised of sEMG time-frequency features. We apply our method in the context of upper-limb position changes to demonstrate pattern recognition robustness and improvement over LDA across discrete positions not explicitly trained. For single position training we report an accuracy improvement in untrained positions of 7.95%, p ≪.001, in addition to significant accuracy improvements across all multiposition training conditions, p <.001.
AB - The fundamental objective in non-invasive myoelectric prosthesis control is to determine the user's intended movements from corresponding skin-surface recorded electromyographic (sEMG) activation signals as quickly and accurately as possible. Linear Discriminant Analysis (LDA) has emerged as the de facto standard for real-time movement classification due to its ease of use, calculation speed, and remarkable classification accuracy under controlled training conditions. However, performance of cluster-based methods like LDA for sEMG pattern recognition degrades significantly when real-world testing conditions do not resemble the trained conditions, limiting the utility of myoelectrically controlled prosthesis devices. We propose an enhanced classification method that is more robust to generic deviations from training conditions by constructing sparse representations of the input data dictionary comprised of sEMG time-frequency features. We apply our method in the context of upper-limb position changes to demonstrate pattern recognition robustness and improvement over LDA across discrete positions not explicitly trained. For single position training we report an accuracy improvement in untrained positions of 7.95%, p ≪.001, in addition to significant accuracy improvements across all multiposition training conditions, p <.001.
KW - Amputee
KW - Classification
KW - Clinical need
KW - Limb-position effect
KW - Myoelectric control
KW - Non-invasive
KW - Pattern recognition
KW - Robust
KW - SFT1
KW - Sparse representation
KW - Upper-limb prosthesis
UR - http://www.scopus.com/inward/record.url?scp=85009111565&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009111565&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2016.7592186
DO - 10.1109/EMBC.2016.7592186
M3 - Conference contribution
C2 - 28325032
AN - SCOPUS:85009111565
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 6373
EP - 6376
BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
Y2 - 16 August 2016 through 20 August 2016
ER -