Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis

Shourijeh, Mohammad S. ; Flaxman, Teresa E. and Benoit, Daniel L. LU (2016) In Journal of Electromyography and Kinesiology 26. p.36-43
Abstract

The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (>0.99; 0.99-1.0) compared to NMF (>0.26; range 0.26-0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.

Please use this url to cite or link to this publication:
author
; and
publishing date
type
Contribution to journal
publication status
published
keywords
Electromyography, Knee, Muscle synergy, Non-negative matrix factorization, Repeatability, Robustness
in
Journal of Electromyography and Kinesiology
volume
26
pages
36 - 43
publisher
Elsevier
external identifiers
  • pmid:26755163
  • scopus:84960195165
ISSN
1050-6411
DOI
10.1016/j.jelekin.2015.12.001
language
English
LU publication?
no
additional info
Publisher Copyright: © 2015 Elsevier Ltd.
id
cea35860-8a6b-42d9-9af1-da853daf2180
date added to LUP
2023-08-24 16:39:34
date last changed
2024-04-20 01:41:27
@article{cea35860-8a6b-42d9-9af1-da853daf2180,
  abstract     = {{<p>The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (&gt;0.99; 0.99-1.0) compared to NMF (&gt;0.26; range 0.26-0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.</p>}},
  author       = {{Shourijeh, Mohammad S. and Flaxman, Teresa E. and Benoit, Daniel L.}},
  issn         = {{1050-6411}},
  keywords     = {{Electromyography; Knee; Muscle synergy; Non-negative matrix factorization; Repeatability; Robustness}},
  language     = {{eng}},
  month        = {{02}},
  pages        = {{36--43}},
  publisher    = {{Elsevier}},
  series       = {{Journal of Electromyography and Kinesiology}},
  title        = {{An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis}},
  url          = {{http://dx.doi.org/10.1016/j.jelekin.2015.12.001}},
  doi          = {{10.1016/j.jelekin.2015.12.001}},
  volume       = {{26}},
  year         = {{2016}},
}