Cargando…

Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition

Body-worn sensors in general and accelerometers in particular have been widely used in order to detect human movements and activities. The execution of each type of movement by each particular individual generates sequences of time series of sensed data from which specific movement related patterns...

Descripción completa

Detalles Bibliográficos
Autores principales: Munoz-Organero, Mario, Ruiz-Blazquez, Ramona
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5336010/
https://www.ncbi.nlm.nih.gov/pubmed/28208736
http://dx.doi.org/10.3390/s17020319
_version_ 1782512141340770304
author Munoz-Organero, Mario
Ruiz-Blazquez, Ramona
author_facet Munoz-Organero, Mario
Ruiz-Blazquez, Ramona
author_sort Munoz-Organero, Mario
collection PubMed
description Body-worn sensors in general and accelerometers in particular have been widely used in order to detect human movements and activities. The execution of each type of movement by each particular individual generates sequences of time series of sensed data from which specific movement related patterns can be assessed. Several machine learning algorithms have been used over windowed segments of sensed data in order to detect such patterns in activity recognition based on intermediate features (either hand-crafted or automatically learned from data). The underlying assumption is that the computed features will capture statistical differences that can properly classify different movements and activities after a training phase based on sensed data. In order to achieve high accuracy and recall rates (and guarantee the generalization of the system to new users), the training data have to contain enough information to characterize all possible ways of executing the activity or movement to be detected. This could imply large amounts of data and a complex and time-consuming training phase, which has been shown to be even more relevant when automatically learning the optimal features to be used. In this paper, we present a novel generative model that is able to generate sequences of time series for characterizing a particular movement based on the time elasticity properties of the sensed data. The model is used to train a stack of auto-encoders in order to learn the particular features able to detect human movements. The results of movement detection using a newly generated database with information on five users performing six different movements are presented. The generalization of results using an existing database is also presented in the paper. The results show that the proposed mechanism is able to obtain acceptable recognition rates (F = 0.77) even in the case of using different people executing a different sequence of movements and using different hardware.
format Online
Article
Text
id pubmed-5336010
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-53360102017-03-16 Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition Munoz-Organero, Mario Ruiz-Blazquez, Ramona Sensors (Basel) Article Body-worn sensors in general and accelerometers in particular have been widely used in order to detect human movements and activities. The execution of each type of movement by each particular individual generates sequences of time series of sensed data from which specific movement related patterns can be assessed. Several machine learning algorithms have been used over windowed segments of sensed data in order to detect such patterns in activity recognition based on intermediate features (either hand-crafted or automatically learned from data). The underlying assumption is that the computed features will capture statistical differences that can properly classify different movements and activities after a training phase based on sensed data. In order to achieve high accuracy and recall rates (and guarantee the generalization of the system to new users), the training data have to contain enough information to characterize all possible ways of executing the activity or movement to be detected. This could imply large amounts of data and a complex and time-consuming training phase, which has been shown to be even more relevant when automatically learning the optimal features to be used. In this paper, we present a novel generative model that is able to generate sequences of time series for characterizing a particular movement based on the time elasticity properties of the sensed data. The model is used to train a stack of auto-encoders in order to learn the particular features able to detect human movements. The results of movement detection using a newly generated database with information on five users performing six different movements are presented. The generalization of results using an existing database is also presented in the paper. The results show that the proposed mechanism is able to obtain acceptable recognition rates (F = 0.77) even in the case of using different people executing a different sequence of movements and using different hardware. MDPI 2017-02-08 /pmc/articles/PMC5336010/ /pubmed/28208736 http://dx.doi.org/10.3390/s17020319 Text en © 2017 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 (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Munoz-Organero, Mario
Ruiz-Blazquez, Ramona
Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title_full Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title_fullStr Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title_full_unstemmed Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title_short Time-Elastic Generative Model for Acceleration Time Series in Human Activity Recognition
title_sort time-elastic generative model for acceleration time series in human activity recognition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5336010/
https://www.ncbi.nlm.nih.gov/pubmed/28208736
http://dx.doi.org/10.3390/s17020319
work_keys_str_mv AT munozorganeromario timeelasticgenerativemodelforaccelerationtimeseriesinhumanactivityrecognition
AT ruizblazquezramona timeelasticgenerativemodelforaccelerationtimeseriesinhumanactivityrecognition