Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions

Miikka Ermes, Juha Pärkkä, Jani Mäntyjärvi, Ilkka Korhonen

Research output: Contribution to journalArticleScientificpeer-review

456 Citations (Scopus)

Abstract

Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.
Original languageEnglish
Pages (from-to)20-26
JournalIEEE Transactions on Information Technology in Biomedicine
Volume12
Issue number1
DOIs
Publication statusPublished - 2008
MoE publication typeA1 Journal article-refereed

Fingerprint

Sports
Walking
Life Style
Classifiers
Exercise equipment
Football
Wrist
Accelerometers
Running
Global positioning system
Hip
Chronic Disease
Neural networks
Feedback
Wearable sensors

Cite this

@article{3a60c8d036d349e7b134f606c0989744,
title = "Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions",
abstract = "Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89{\%} that was only 1{\%} unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17{\%} unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.",
author = "Miikka Ermes and Juha P{\"a}rkk{\"a} and Jani M{\"a}ntyj{\"a}rvi and Ilkka Korhonen",
year = "2008",
doi = "10.1109/TITB.2007.899496",
language = "English",
volume = "12",
pages = "20--26",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2208",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
number = "1",

}

Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. / Ermes, Miikka; Pärkkä, Juha; Mäntyjärvi, Jani; Korhonen, Ilkka.

In: IEEE Transactions on Information Technology in Biomedicine, Vol. 12, No. 1, 2008, p. 20-26.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions

AU - Ermes, Miikka

AU - Pärkkä, Juha

AU - Mäntyjärvi, Jani

AU - Korhonen, Ilkka

PY - 2008

Y1 - 2008

N2 - Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.

AB - Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.

U2 - 10.1109/TITB.2007.899496

DO - 10.1109/TITB.2007.899496

M3 - Article

VL - 12

SP - 20

EP - 26

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2208

IS - 1

ER -