Cargando…
Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm
New surface electromyography (sEMG) feature extraction approach combined with Empirical Mode Decomposition (EMD) and Dispersion Entropy (DisEn) is proposed for classifying aggressive and normal behaviors from sEMG data. In this study, we used the sEMG physical action dataset from the UC Irvine Machi...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7743341/ http://dx.doi.org/10.1093/geroni/igaa057.2262 |
_version_ | 1783624194517368832 |
---|---|
author | Kim, Youngjun David, Uchechukuwu Noh, Yeonsik |
author_facet | Kim, Youngjun David, Uchechukuwu Noh, Yeonsik |
author_sort | Kim, Youngjun |
collection | PubMed |
description | New surface electromyography (sEMG) feature extraction approach combined with Empirical Mode Decomposition (EMD) and Dispersion Entropy (DisEn) is proposed for classifying aggressive and normal behaviors from sEMG data. In this study, we used the sEMG physical action dataset from the UC Irvine Machine Learning repository. The raw sEMG was decomposed with EMD to obtain a set of Intrinsic Mode Functions (IMF). The IMF, which includes the most discriminant feature for each action, was selected based on the analysis by Hibert Transform (HT) in the time-frequency domain. Next, the DisEn of the selected IMF was calculated as a corresponding feature. Finally, the DisEn value was tested using five different classifiers, such as LDA, Quadratic DA, k-NN, SVM, and Extreme Learning Machine (ELM) for the classification task. Among these ML algorithms, we achieved classification accuracy, sensitivity, and specificity with ELM as 98.44%, 100%, and 96.72%, respectively. |
format | Online Article Text |
id | pubmed-7743341 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-77433412020-12-21 Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm Kim, Youngjun David, Uchechukuwu Noh, Yeonsik Innov Aging Abstracts New surface electromyography (sEMG) feature extraction approach combined with Empirical Mode Decomposition (EMD) and Dispersion Entropy (DisEn) is proposed for classifying aggressive and normal behaviors from sEMG data. In this study, we used the sEMG physical action dataset from the UC Irvine Machine Learning repository. The raw sEMG was decomposed with EMD to obtain a set of Intrinsic Mode Functions (IMF). The IMF, which includes the most discriminant feature for each action, was selected based on the analysis by Hibert Transform (HT) in the time-frequency domain. Next, the DisEn of the selected IMF was calculated as a corresponding feature. Finally, the DisEn value was tested using five different classifiers, such as LDA, Quadratic DA, k-NN, SVM, and Extreme Learning Machine (ELM) for the classification task. Among these ML algorithms, we achieved classification accuracy, sensitivity, and specificity with ELM as 98.44%, 100%, and 96.72%, respectively. Oxford University Press 2020-12-16 /pmc/articles/PMC7743341/ http://dx.doi.org/10.1093/geroni/igaa057.2262 Text en © The Author(s) 2020. Published by Oxford University Press on behalf of The Gerontological Society of America. http://creativecommons.org/licenses/by/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Abstracts Kim, Youngjun David, Uchechukuwu Noh, Yeonsik Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title | Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title_full | Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title_fullStr | Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title_full_unstemmed | Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title_short | Classification of Aggressive Behaviors Based on sEMG Feature Extraction and Machine Learning Algorithm |
title_sort | classification of aggressive behaviors based on semg feature extraction and machine learning algorithm |
topic | Abstracts |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7743341/ http://dx.doi.org/10.1093/geroni/igaa057.2262 |
work_keys_str_mv | AT kimyoungjun classificationofaggressivebehaviorsbasedonsemgfeatureextractionandmachinelearningalgorithm AT daviduchechukuwu classificationofaggressivebehaviorsbasedonsemgfeatureextractionandmachinelearningalgorithm AT nohyeonsik classificationofaggressivebehaviorsbasedonsemgfeatureextractionandmachinelearningalgorithm |