Advancing from offline to online activity recognition with wearable sensors

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

53 Citations (Scopus)

Abstract

Activity recognition with wearable sensors could motivate people to perform a variety of different sports and other physical exercises. We have earlier developed algorithms for offline analysis of activity data collected with wearable sensors. In this paper, we present our current progress in advancing the platform for the existing algorithms to an online version, onto a PDA. Acceleration data are obtained from wireless motion bands which send the 3D raw acceleration signals via a Bluetooth link to the PDA which then performs the data collection, feature extraction and activity classification. As a proof-of-concept, the online activity system was tested with three subjects. All of them performed at least 5 minutes of each of the following activities: lying, sitting, standing, walking, running and cycling with an exercise bike. The average secondby-second classification accuracies for the subjects were 99%, 97%, and 82 %. These results suggest that earlier developed offline analysis methods for the acceleration data obtained from wearable sensors can be successfully implemented in an online activity recognition application.
Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages4451-4454
DOIs
Publication statusPublished - 2008
MoE publication typeA4 Article in a conference publication
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Personalized Healthcare through Technology - Vancouver, Canada
Duration: 20 Aug 200825 Aug 2008

Conference

Conference30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CountryCanada
CityVancouver
Period20/08/0825/08/08

Fingerprint

Personal digital assistants
Bluetooth
Sports
Feature extraction
Wearable sensors

Cite this

Ermes, M., Pärkkä, J., & Cluitmans, L. (2008). Advancing from offline to online activity recognition with wearable sensors. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008 (pp. 4451-4454). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IEMBS.2008.4650199
Ermes, Miikka ; Pärkkä, Juha ; Cluitmans, Luc. / Advancing from offline to online activity recognition with wearable sensors. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, 2008. pp. 4451-4454
@inproceedings{ef3159992d55486dbaea4fadcf2a3596,
title = "Advancing from offline to online activity recognition with wearable sensors",
abstract = "Activity recognition with wearable sensors could motivate people to perform a variety of different sports and other physical exercises. We have earlier developed algorithms for offline analysis of activity data collected with wearable sensors. In this paper, we present our current progress in advancing the platform for the existing algorithms to an online version, onto a PDA. Acceleration data are obtained from wireless motion bands which send the 3D raw acceleration signals via a Bluetooth link to the PDA which then performs the data collection, feature extraction and activity classification. As a proof-of-concept, the online activity system was tested with three subjects. All of them performed at least 5 minutes of each of the following activities: lying, sitting, standing, walking, running and cycling with an exercise bike. The average secondby-second classification accuracies for the subjects were 99{\%}, 97{\%}, and 82 {\%}. These results suggest that earlier developed offline analysis methods for the acceleration data obtained from wearable sensors can be successfully implemented in an online activity recognition application.",
author = "Miikka Ermes and Juha P{\"a}rkk{\"a} and Luc Cluitmans",
note = "Project code: 11060",
year = "2008",
doi = "10.1109/IEMBS.2008.4650199",
language = "English",
pages = "4451--4454",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - {"}Personalized Healthcare through Technology{"}. Vancouver, BC, Canada, 20 - 25 Aug. 2008",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Ermes, M, Pärkkä, J & Cluitmans, L 2008, Advancing from offline to online activity recognition with wearable sensors. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, pp. 4451-4454, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancouver, Canada, 20/08/08. https://doi.org/10.1109/IEMBS.2008.4650199

Advancing from offline to online activity recognition with wearable sensors. / Ermes, Miikka; Pärkkä, Juha; Cluitmans, Luc.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, 2008. p. 4451-4454.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Advancing from offline to online activity recognition with wearable sensors

AU - Ermes, Miikka

AU - Pärkkä, Juha

AU - Cluitmans, Luc

N1 - Project code: 11060

PY - 2008

Y1 - 2008

N2 - Activity recognition with wearable sensors could motivate people to perform a variety of different sports and other physical exercises. We have earlier developed algorithms for offline analysis of activity data collected with wearable sensors. In this paper, we present our current progress in advancing the platform for the existing algorithms to an online version, onto a PDA. Acceleration data are obtained from wireless motion bands which send the 3D raw acceleration signals via a Bluetooth link to the PDA which then performs the data collection, feature extraction and activity classification. As a proof-of-concept, the online activity system was tested with three subjects. All of them performed at least 5 minutes of each of the following activities: lying, sitting, standing, walking, running and cycling with an exercise bike. The average secondby-second classification accuracies for the subjects were 99%, 97%, and 82 %. These results suggest that earlier developed offline analysis methods for the acceleration data obtained from wearable sensors can be successfully implemented in an online activity recognition application.

AB - Activity recognition with wearable sensors could motivate people to perform a variety of different sports and other physical exercises. We have earlier developed algorithms for offline analysis of activity data collected with wearable sensors. In this paper, we present our current progress in advancing the platform for the existing algorithms to an online version, onto a PDA. Acceleration data are obtained from wireless motion bands which send the 3D raw acceleration signals via a Bluetooth link to the PDA which then performs the data collection, feature extraction and activity classification. As a proof-of-concept, the online activity system was tested with three subjects. All of them performed at least 5 minutes of each of the following activities: lying, sitting, standing, walking, running and cycling with an exercise bike. The average secondby-second classification accuracies for the subjects were 99%, 97%, and 82 %. These results suggest that earlier developed offline analysis methods for the acceleration data obtained from wearable sensors can be successfully implemented in an online activity recognition application.

U2 - 10.1109/IEMBS.2008.4650199

DO - 10.1109/IEMBS.2008.4650199

M3 - Conference article in proceedings

SP - 4451

EP - 4454

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Ermes M, Pärkkä J, Cluitmans L. Advancing from offline to online activity recognition with wearable sensors. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE. 2008. p. 4451-4454 https://doi.org/10.1109/IEMBS.2008.4650199