Cargando…

Accelerometry-Based Classification of Human Activities Using Markov Modeling

Accelerometers are a popular choice as body-motion sensors: the reason is partly in their capability of extracting information that is useful for automatically inferring the physical activity in which the human subject is involved, beside their role in feeding biomechanical parameters estimators. Au...

Descripción completa

Detalles Bibliográficos
Autores principales: Mannini, Andrea, Sabatini, Angelo Maria
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3166724/
https://www.ncbi.nlm.nih.gov/pubmed/21904542
http://dx.doi.org/10.1155/2011/647858
_version_ 1782211174806323200
author Mannini, Andrea
Sabatini, Angelo Maria
author_facet Mannini, Andrea
Sabatini, Angelo Maria
author_sort Mannini, Andrea
collection PubMed
description Accelerometers are a popular choice as body-motion sensors: the reason is partly in their capability of extracting information that is useful for automatically inferring the physical activity in which the human subject is involved, beside their role in feeding biomechanical parameters estimators. Automatic classification of human physical activities is highly attractive for pervasive computing systems, whereas contextual awareness may ease the human-machine interaction, and in biomedicine, whereas wearable sensor systems are proposed for long-term monitoring. This paper is concerned with the machine learning algorithms needed to perform the classification task. Hidden Markov Model (HMM) classifiers are studied by contrasting them with Gaussian Mixture Model (GMM) classifiers. HMMs incorporate the statistical information available on movement dynamics into the classification process, without discarding the time history of previous outcomes as GMMs do. An example of the benefits of the obtained statistical leverage is illustrated and discussed by analyzing two datasets of accelerometer time series.
format Online
Article
Text
id pubmed-3166724
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-31667242011-09-08 Accelerometry-Based Classification of Human Activities Using Markov Modeling Mannini, Andrea Sabatini, Angelo Maria Comput Intell Neurosci Research Article Accelerometers are a popular choice as body-motion sensors: the reason is partly in their capability of extracting information that is useful for automatically inferring the physical activity in which the human subject is involved, beside their role in feeding biomechanical parameters estimators. Automatic classification of human physical activities is highly attractive for pervasive computing systems, whereas contextual awareness may ease the human-machine interaction, and in biomedicine, whereas wearable sensor systems are proposed for long-term monitoring. This paper is concerned with the machine learning algorithms needed to perform the classification task. Hidden Markov Model (HMM) classifiers are studied by contrasting them with Gaussian Mixture Model (GMM) classifiers. HMMs incorporate the statistical information available on movement dynamics into the classification process, without discarding the time history of previous outcomes as GMMs do. An example of the benefits of the obtained statistical leverage is illustrated and discussed by analyzing two datasets of accelerometer time series. Hindawi Publishing Corporation 2011 2011-09-04 /pmc/articles/PMC3166724/ /pubmed/21904542 http://dx.doi.org/10.1155/2011/647858 Text en Copyright © 2011 A. Mannini and A. M. Sabatini. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Mannini, Andrea
Sabatini, Angelo Maria
Accelerometry-Based Classification of Human Activities Using Markov Modeling
title Accelerometry-Based Classification of Human Activities Using Markov Modeling
title_full Accelerometry-Based Classification of Human Activities Using Markov Modeling
title_fullStr Accelerometry-Based Classification of Human Activities Using Markov Modeling
title_full_unstemmed Accelerometry-Based Classification of Human Activities Using Markov Modeling
title_short Accelerometry-Based Classification of Human Activities Using Markov Modeling
title_sort accelerometry-based classification of human activities using markov modeling
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3166724/
https://www.ncbi.nlm.nih.gov/pubmed/21904542
http://dx.doi.org/10.1155/2011/647858
work_keys_str_mv AT manniniandrea accelerometrybasedclassificationofhumanactivitiesusingmarkovmodeling
AT sabatiniangelomaria accelerometrybasedclassificationofhumanactivitiesusingmarkovmodeling