Human postures recognition based on D-S evidence theory and multi-sensor data fusion

W. Li; J. Bao; X. Fu; G. Fortino; S. Galzarano

doi:10.1109/CCGrid.2012.144

Human postures recognition based on D-S evidence theory and multi-sensor data fusion

W. Li, J. Bao, X. Fu, G. Fortino, S. Galzarano

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

19 Citations (Scopus)

2 Downloads (Pure)

Abstract

Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach for human posture recognition is proposed. Our BSN system relies on an information fusion method based on the D-S Evidence Theory, which is applied on the accelerometer data coming from multiple wearable sensors. Experimental results demonstrate that the developed prototype system is able to achieve a recognition accuracy between 98.5% and 100% for basic postures (standing, sitting, lying, squatting).

Original language	English
Title of host publication	Proceedings of the 12th IEEE International Symposium on Cluster Computing and the Grid Computing, 13-16 May 2012, Ottawa, Canada
Place of Publication	Piscataway
Publisher	IEEE Computer Society
Pages	912-917
ISBN (Print)	978-0-7695-4691-9
DOIs	https://doi.org/10.1109/CCGrid.2012.144
Publication status	Published - 2012

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CCGrid.2012.144

Cite this

@inproceedings{dce58f9501fe403fa778545da145ecab,

title = "Human postures recognition based on D-S evidence theory and multi-sensor data fusion",

abstract = "Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach for human posture recognition is proposed. Our BSN system relies on an information fusion method based on the D-S Evidence Theory, which is applied on the accelerometer data coming from multiple wearable sensors. Experimental results demonstrate that the developed prototype system is able to achieve a recognition accuracy between 98.5% and 100% for basic postures (standing, sitting, lying, squatting).",

author = "W. Li and J. Bao and X. Fu and G. Fortino and S. Galzarano",

year = "2012",

doi = "10.1109/CCGrid.2012.144",

language = "English",

isbn = "978-0-7695-4691-9",

pages = "912--917",

booktitle = "Proceedings of the 12th IEEE International Symposium on Cluster Computing and the Grid Computing, 13-16 May 2012, Ottawa, Canada",

publisher = "IEEE Computer Society",

address = "United States",

}

Human postures recognition based on D-S evidence theory and multi-sensor data fusion. / Li, W.; Bao, J.; Fu, X. et al.

Proceedings of the 12th IEEE International Symposium on Cluster Computing and the Grid Computing, 13-16 May 2012, Ottawa, Canada. Piscataway : IEEE Computer Society, 2012. p. 912-917.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Human postures recognition based on D-S evidence theory and multi-sensor data fusion

AU - Li, W.

AU - Bao, J.

AU - Fu, X.

AU - Fortino, G.

AU - Galzarano, S.

PY - 2012

Y1 - 2012

N2 - Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach for human posture recognition is proposed. Our BSN system relies on an information fusion method based on the D-S Evidence Theory, which is applied on the accelerometer data coming from multiple wearable sensors. Experimental results demonstrate that the developed prototype system is able to achieve a recognition accuracy between 98.5% and 100% for basic postures (standing, sitting, lying, squatting).

AB - Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach for human posture recognition is proposed. Our BSN system relies on an information fusion method based on the D-S Evidence Theory, which is applied on the accelerometer data coming from multiple wearable sensors. Experimental results demonstrate that the developed prototype system is able to achieve a recognition accuracy between 98.5% and 100% for basic postures (standing, sitting, lying, squatting).

U2 - 10.1109/CCGrid.2012.144

DO - 10.1109/CCGrid.2012.144

M3 - Conference contribution

SN - 978-0-7695-4691-9

SP - 912

EP - 917

BT - Proceedings of the 12th IEEE International Symposium on Cluster Computing and the Grid Computing, 13-16 May 2012, Ottawa, Canada

PB - IEEE Computer Society

CY - Piscataway

ER -

Human postures recognition based on D-S evidence theory and multi-sensor data fusion

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this