Extraction of muscle synergies using temporal segmentation of the record: a preliminary analysis.

Peppino Tropea, Vito Monaco, Silvestro Micera

Research output: Contribution to journalArticle

Abstract

Muscle synergies are considered as a potential strategy to reduce the computational workload undergoing the estimation of muscle activity during different motor tasks. They are usually extracted by means of algebraic factorization algorithms able to capture the greatest communality of a set of electromyographic (EMG) signals. Usually EMG signals are pooled across different sub-movements (e.g., going forward and backward during reaching) in order to increase the complexity of the data set and, consequently, capture the maximum communality. Despite of these, this preliminary study was designed to investigate how the communality of EMG signals can be explained looking at narrow subset of recorded signals. Results corroborate the hypothesis that using a suitable subset of the whole dataset can significantly modify the values of weight coefficients. In this regard, further methodological investigations of algorithms adopted for synergy extraction are still required.

Fingerprint

Muscle
Muscles
Workload
Factorization
Weights and Measures
Datasets

ASJC Scopus subject areas

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

Cite this

@article{3134d88a5e294f5b971c4e82e9235a95,
title = "Extraction of muscle synergies using temporal segmentation of the record: a preliminary analysis.",
abstract = "Muscle synergies are considered as a potential strategy to reduce the computational workload undergoing the estimation of muscle activity during different motor tasks. They are usually extracted by means of algebraic factorization algorithms able to capture the greatest communality of a set of electromyographic (EMG) signals. Usually EMG signals are pooled across different sub-movements (e.g., going forward and backward during reaching) in order to increase the complexity of the data set and, consequently, capture the maximum communality. Despite of these, this preliminary study was designed to investigate how the communality of EMG signals can be explained looking at narrow subset of recorded signals. Results corroborate the hypothesis that using a suitable subset of the whole dataset can significantly modify the values of weight coefficients. In this regard, further methodological investigations of algorithms adopted for synergy extraction are still required.",
author = "Peppino Tropea and Vito Monaco and Silvestro Micera",
year = "2012",
language = "English",
pages = "3624--3627",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Extraction of muscle synergies using temporal segmentation of the record

T2 - a preliminary analysis.

AU - Tropea, Peppino

AU - Monaco, Vito

AU - Micera, Silvestro

PY - 2012

Y1 - 2012

N2 - Muscle synergies are considered as a potential strategy to reduce the computational workload undergoing the estimation of muscle activity during different motor tasks. They are usually extracted by means of algebraic factorization algorithms able to capture the greatest communality of a set of electromyographic (EMG) signals. Usually EMG signals are pooled across different sub-movements (e.g., going forward and backward during reaching) in order to increase the complexity of the data set and, consequently, capture the maximum communality. Despite of these, this preliminary study was designed to investigate how the communality of EMG signals can be explained looking at narrow subset of recorded signals. Results corroborate the hypothesis that using a suitable subset of the whole dataset can significantly modify the values of weight coefficients. In this regard, further methodological investigations of algorithms adopted for synergy extraction are still required.

AB - Muscle synergies are considered as a potential strategy to reduce the computational workload undergoing the estimation of muscle activity during different motor tasks. They are usually extracted by means of algebraic factorization algorithms able to capture the greatest communality of a set of electromyographic (EMG) signals. Usually EMG signals are pooled across different sub-movements (e.g., going forward and backward during reaching) in order to increase the complexity of the data set and, consequently, capture the maximum communality. Despite of these, this preliminary study was designed to investigate how the communality of EMG signals can be explained looking at narrow subset of recorded signals. Results corroborate the hypothesis that using a suitable subset of the whole dataset can significantly modify the values of weight coefficients. In this regard, further methodological investigations of algorithms adopted for synergy extraction are still required.

UR - http://www.scopus.com/inward/record.url?scp=84903865042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903865042&partnerID=8YFLogxK

M3 - Article

C2 - 23366712

SP - 3624

EP - 3627

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -