Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework

Human activity recognition via triaxial accelerometers can provide valuable information for evaluating functional abilities. In this paper, we present an accelerometer sensor-based approach for human activity recognition. Our proposed recognition method used a hierarchical scheme, where the recognit...

Full description

Saved in:
Bibliographic Details
Main Author: Yuhuang Zheng
Format: Article
Language:English
Published: Wiley 2015-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2015/140820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832547678656921600
author Yuhuang Zheng
author_facet Yuhuang Zheng
author_sort Yuhuang Zheng
collection DOAJ
description Human activity recognition via triaxial accelerometers can provide valuable information for evaluating functional abilities. In this paper, we present an accelerometer sensor-based approach for human activity recognition. Our proposed recognition method used a hierarchical scheme, where the recognition of ten activity classes was divided into five distinct classification problems. Every classifier used the Least Squares Support Vector Machine (LS-SVM) and Naive Bayes (NB) algorithm to distinguish different activity classes. The activity class was recognized based on the mean, variance, entropy of magnitude, and angle of triaxial accelerometer signal features. Our proposed activity recognition method recognized ten activities with an average accuracy of 95.6% using only a single triaxial accelerometer.
format Article
id doaj-art-f75a120d14284f3fa67c970c0c4c63f4
institution Kabale University
issn 2090-0147
2090-0155
language English
publishDate 2015-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-f75a120d14284f3fa67c970c0c4c63f42025-02-03T06:43:53ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552015-01-01201510.1155/2015/140820140820Human Activity Recognition Based on the Hierarchical Feature Selection and Classification FrameworkYuhuang Zheng0Department of Physics, Guangdong University of Education, Guangzhou 510303, ChinaHuman activity recognition via triaxial accelerometers can provide valuable information for evaluating functional abilities. In this paper, we present an accelerometer sensor-based approach for human activity recognition. Our proposed recognition method used a hierarchical scheme, where the recognition of ten activity classes was divided into five distinct classification problems. Every classifier used the Least Squares Support Vector Machine (LS-SVM) and Naive Bayes (NB) algorithm to distinguish different activity classes. The activity class was recognized based on the mean, variance, entropy of magnitude, and angle of triaxial accelerometer signal features. Our proposed activity recognition method recognized ten activities with an average accuracy of 95.6% using only a single triaxial accelerometer.http://dx.doi.org/10.1155/2015/140820
spellingShingle Yuhuang Zheng
Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
Journal of Electrical and Computer Engineering
title Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
title_full Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
title_fullStr Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
title_full_unstemmed Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
title_short Human Activity Recognition Based on the Hierarchical Feature Selection and Classification Framework
title_sort human activity recognition based on the hierarchical feature selection and classification framework
url http://dx.doi.org/10.1155/2015/140820
work_keys_str_mv AT yuhuangzheng humanactivityrecognitionbasedonthehierarchicalfeatureselectionandclassificationframework