Cargando…
Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals
We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a pr...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Molecular Diversity Preservation International (MDPI)
2011
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3274015/ https://www.ncbi.nlm.nih.gov/pubmed/22319378 http://dx.doi.org/10.3390/s110201721 |
_version_ | 1782222991477702656 |
---|---|
author | Ayrulu-Erdem, Birsel Barshan, Billur |
author_facet | Ayrulu-Erdem, Birsel Barshan, Billur |
author_sort | Ayrulu-Erdem, Birsel |
collection | PubMed |
description | We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWT decomposition and reconstruction. |
format | Online Article Text |
id | pubmed-3274015 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2011 |
publisher | Molecular Diversity Preservation International (MDPI) |
record_format | MEDLINE/PubMed |
spelling | pubmed-32740152012-02-08 Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals Ayrulu-Erdem, Birsel Barshan, Billur Sensors (Basel) Article We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWT decomposition and reconstruction. Molecular Diversity Preservation International (MDPI) 2011-01-28 /pmc/articles/PMC3274015/ /pubmed/22319378 http://dx.doi.org/10.3390/s110201721 Text en © 2011 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/3.0/). |
spellingShingle | Article Ayrulu-Erdem, Birsel Barshan, Billur Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title | Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title_full | Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title_fullStr | Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title_full_unstemmed | Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title_short | Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals |
title_sort | leg motion classification with artificial neural networks using wavelet-based features of gyroscope signals |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3274015/ https://www.ncbi.nlm.nih.gov/pubmed/22319378 http://dx.doi.org/10.3390/s110201721 |
work_keys_str_mv | AT ayruluerdembirsel legmotionclassificationwithartificialneuralnetworksusingwaveletbasedfeaturesofgyroscopesignals AT barshanbillur legmotionclassificationwithartificialneuralnetworksusingwaveletbasedfeaturesofgyroscopesignals |