Body sensor networks for human activity recognition

Girija CHETTY, Matthew White

Research output: A Conference proceeding or a Chapter in BookConference contribution

11 Citations (Scopus)

Abstract

Body Sensor Networks aim to capture the state of the user and its environment by utilizing from information heterogeneous sensors, and allow continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in activity recognition for identity verification, health and ageing and sport and exercise monitoring applications. In this paper, the application of body sensor networks for automatic and intelligent daily activity monitoring for elderly people, using wireless body sensors and smartphone inertial sensors has been reported. The scheme uses information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Extensive experiments using different publicly available datasets of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.

Original languageEnglish
Title of host publicationProceedings Signal Processing and Information Networks (SPIN 2016)
EditorsM. K. Dutta, J. K. Rai P. Banerjee
Place of PublicationUnited States of America
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages660-665
Number of pages6
ISBN (Electronic)9781467391979
ISBN (Print)9781467391979
DOIs
Publication statusPublished - 2016
Event3rd International Conference on Signal Processing and Information Networks (SPIN 2016) - Delhi, Delhi, India
Duration: 11 Feb 201612 Feb 2016

Publication series

Name3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016

Conference

Conference3rd International Conference on Signal Processing and Information Networks (SPIN 2016)
Abbreviated titleSPIN 2016
CountryIndia
CityDelhi
Period11/02/1612/02/16

Fingerprint

Body sensor networks
Monitoring
Sensors
Smartphones
Information theory
Sports
Classifiers
Aging of materials
Health
Experiments

Cite this

CHETTY, G., & White, M. (2016). Body sensor networks for human activity recognition. In M. K. Dutta, & J. K. R. P. Banerjee (Eds.), Proceedings Signal Processing and Information Networks (SPIN 2016) (pp. 660-665). [7566779] (3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016). United States of America: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SPIN.2016.7566779
CHETTY, Girija ; White, Matthew. / Body sensor networks for human activity recognition. Proceedings Signal Processing and Information Networks (SPIN 2016). editor / M. K. Dutta ; J. K. Rai P. Banerjee. United States of America : IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 660-665 (3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016).
@inproceedings{3f397a008ad942288278f573b7f913f7,
title = "Body sensor networks for human activity recognition",
abstract = "Body Sensor Networks aim to capture the state of the user and its environment by utilizing from information heterogeneous sensors, and allow continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in activity recognition for identity verification, health and ageing and sport and exercise monitoring applications. In this paper, the application of body sensor networks for automatic and intelligent daily activity monitoring for elderly people, using wireless body sensors and smartphone inertial sensors has been reported. The scheme uses information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Extensive experiments using different publicly available datasets of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.",
keywords = "body-sensor-networks, activity-recognition, data-mining",
author = "Girija CHETTY and Matthew White",
year = "2016",
doi = "10.1109/SPIN.2016.7566779",
language = "English",
isbn = "9781467391979",
series = "3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "660--665",
editor = "Dutta, {M. K.} and Banerjee, {J. K. Rai P.}",
booktitle = "Proceedings Signal Processing and Information Networks (SPIN 2016)",
address = "United States",

}

CHETTY, G & White, M 2016, Body sensor networks for human activity recognition. in MK Dutta & JKRP Banerjee (eds), Proceedings Signal Processing and Information Networks (SPIN 2016)., 7566779, 3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016, IEEE, Institute of Electrical and Electronics Engineers, United States of America, pp. 660-665, 3rd International Conference on Signal Processing and Information Networks (SPIN 2016), Delhi, India, 11/02/16. https://doi.org/10.1109/SPIN.2016.7566779

Body sensor networks for human activity recognition. / CHETTY, Girija; White, Matthew.

Proceedings Signal Processing and Information Networks (SPIN 2016). ed. / M. K. Dutta; J. K. Rai P. Banerjee. United States of America : IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 660-665 7566779 (3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Body sensor networks for human activity recognition

AU - CHETTY, Girija

AU - White, Matthew

PY - 2016

Y1 - 2016

N2 - Body Sensor Networks aim to capture the state of the user and its environment by utilizing from information heterogeneous sensors, and allow continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in activity recognition for identity verification, health and ageing and sport and exercise monitoring applications. In this paper, the application of body sensor networks for automatic and intelligent daily activity monitoring for elderly people, using wireless body sensors and smartphone inertial sensors has been reported. The scheme uses information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Extensive experiments using different publicly available datasets of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.

AB - Body Sensor Networks aim to capture the state of the user and its environment by utilizing from information heterogeneous sensors, and allow continuous monitoring of numerous physiological signals, where these sensors are attached to the subject's body. This can be immensely useful in activity recognition for identity verification, health and ageing and sport and exercise monitoring applications. In this paper, the application of body sensor networks for automatic and intelligent daily activity monitoring for elderly people, using wireless body sensors and smartphone inertial sensors has been reported. The scheme uses information theory-based feature ranking algorithms and classifiers based on random forests, ensemble learning and lazy learning. Extensive experiments using different publicly available datasets of human activity show that the proposed approach can assist in the development of intelligent and automatic real time human activity monitoring technology for eHealth application scenarios for elderly, disabled and people with special needs.

KW - body-sensor-networks

KW - activity-recognition

KW - data-mining

UR - http://www.scopus.com/inward/record.url?scp=84991669655&partnerID=8YFLogxK

U2 - 10.1109/SPIN.2016.7566779

DO - 10.1109/SPIN.2016.7566779

M3 - Conference contribution

SN - 9781467391979

T3 - 3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016

SP - 660

EP - 665

BT - Proceedings Signal Processing and Information Networks (SPIN 2016)

A2 - Dutta, M. K.

A2 - Banerjee, J. K. Rai P.

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States of America

ER -

CHETTY G, White M. Body sensor networks for human activity recognition. In Dutta MK, Banerjee JKRP, editors, Proceedings Signal Processing and Information Networks (SPIN 2016). United States of America: IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 660-665. 7566779. (3rd International Conference on Signal Processing and Integrated Networks, SPIN 2016). https://doi.org/10.1109/SPIN.2016.7566779