Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs

Although human activity recognition (HAR) has been studied extensively in the past decade, HAR on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing...

Full description

Saved in:
Bibliographic Details
Main Authors: Adil Mehmood Khan, Ali Tufail, Asad Masood Khattak, Teemu H. Laine
Format: Article
Language:English
Published: Wiley 2014-05-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2014/503291
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696923933474816
author Adil Mehmood Khan
Ali Tufail
Asad Masood Khattak
Teemu H. Laine
author_facet Adil Mehmood Khan
Ali Tufail
Asad Masood Khattak
Teemu H. Laine
author_sort Adil Mehmood Khan
collection DOAJ
description Although human activity recognition (HAR) has been studied extensively in the past decade, HAR on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing this goal is challenging, however. Firstly, these devices are low on resources, which limits the number of sensors that can be utilized. Secondly, to achieve optimum performance efficient feature extraction, feature selection and classification methods are required. This work implements a smartphone-based HAR scheme in accordance with these requirements. Time domain features are extracted from only three smartphone sensors, and a nonlinear discriminatory approach is employed to recognize 15 activities with a high accuracy. This approach not only selects the most relevant features from each sensor for each activity but it also takes into account the differences resulting from carrying a phone at different positions. Evaluations are performed in both offline and online settings. Our comparison results show that the proposed system outperforms some previous mobile phone-based HAR systems.
format Article
id doaj-art-5238e2c64c364804b9a616bf7f00215b
institution DOAJ
issn 1550-1477
language English
publishDate 2014-05-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-5238e2c64c364804b9a616bf7f00215b2025-08-20T03:19:19ZengWileyInternational Journal of Distributed Sensor Networks1550-14772014-05-011010.1155/2014/503291503291Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMsAdil Mehmood Khan0Ali Tufail1Asad Masood Khattak2Teemu H. Laine3 School of Information and Computer Engineering, Ajou University, San 5, Woncheon-dong, Suwon-si, Gyeonggi-do 443-749, Republic of Korea Department of Computer Engineering, Yildirim Beyazit University, Altindag Ulus, 06030 Ankara, Turkey Department of Computer Engineering, Kyung Hee University, 1 Seocheon-dong, Giheung-gu, Yongin-si, Gyeonggi-do 446-701, Republic of Korea School of Information and Computer Engineering, Ajou University, San 5, Woncheon-dong, Suwon-si, Gyeonggi-do 443-749, Republic of KoreaAlthough human activity recognition (HAR) has been studied extensively in the past decade, HAR on smartphones is a relatively new area. Smartphones are equipped with a variety of sensors. Fusing the data of these sensors could enable applications to recognize a large number of activities. Realizing this goal is challenging, however. Firstly, these devices are low on resources, which limits the number of sensors that can be utilized. Secondly, to achieve optimum performance efficient feature extraction, feature selection and classification methods are required. This work implements a smartphone-based HAR scheme in accordance with these requirements. Time domain features are extracted from only three smartphone sensors, and a nonlinear discriminatory approach is employed to recognize 15 activities with a high accuracy. This approach not only selects the most relevant features from each sensor for each activity but it also takes into account the differences resulting from carrying a phone at different positions. Evaluations are performed in both offline and online settings. Our comparison results show that the proposed system outperforms some previous mobile phone-based HAR systems.https://doi.org/10.1155/2014/503291
spellingShingle Adil Mehmood Khan
Ali Tufail
Asad Masood Khattak
Teemu H. Laine
Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
International Journal of Distributed Sensor Networks
title Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
title_full Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
title_fullStr Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
title_full_unstemmed Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
title_short Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs
title_sort activity recognition on smartphones via sensor fusion and kda based svms
url https://doi.org/10.1155/2014/503291
work_keys_str_mv AT adilmehmoodkhan activityrecognitiononsmartphonesviasensorfusionandkdabasedsvms
AT alitufail activityrecognitiononsmartphonesviasensorfusionandkdabasedsvms
AT asadmasoodkhattak activityrecognitiononsmartphonesviasensorfusionandkdabasedsvms
AT teemuhlaine activityrecognitiononsmartphonesviasensorfusionandkdabasedsvms