Improving human activity recognition using subspace clustering

Huiquan Zhang, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Activity recognition attracted much interest in pervasive sensing due to extensive application in human daily life from health monitoring to security monitoring. It utilizes collection of data from low level sensor to learn about human behaviors and activities, so that services can be provided by function of detecting anomalies, remote interventions or prompts. The approach of human activity modeling and recognition still confronted with a challenge on issues of modeling human activity in human perspective. However, the traditional learning-based approaches are not sufficient to capture the characteristics of human activity because they still use traditional clustering method to process sensor data which consists of multidimensional information. This paper describes a subspace clustering-based approach to recognize human activity and detect exceptional activities. Different from many approaches, the proposed approach use subspace clustering based approach to model of human activity in order to improve accuracy of activity recognition. Finally, the proposed approach has been validated on data collected from RFID-based systems, which results demonstrate the effectiveness of the proposed improvents.

Original languageEnglish
Title of host publicationProceedings - International Conference on Machine Learning and Cybernetics
Pages1058-1063
Number of pages6
Volume3
DOIs
Publication statusPublished - 2012
Event2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012 - Xian, Shaanxi
Duration: 2012 Jul 152012 Jul 17

Other

Other2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012
CityXian, Shaanxi
Period12/7/1512/7/17

Fingerprint

Monitoring
Sensors
Radio frequency identification (RFID)
Health

Keywords

  • Activity recognition
  • Multiple dimensional data
  • RFID
  • Subspaces clustering

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Zhang, H., & Yoshie, O. (2012). Improving human activity recognition using subspace clustering. In Proceedings - International Conference on Machine Learning and Cybernetics (Vol. 3, pp. 1058-1063). [6359501] https://doi.org/10.1109/ICMLC.2012.6359501

Improving human activity recognition using subspace clustering. / Zhang, Huiquan; Yoshie, Osamu.

Proceedings - International Conference on Machine Learning and Cybernetics. Vol. 3 2012. p. 1058-1063 6359501.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, H & Yoshie, O 2012, Improving human activity recognition using subspace clustering. in Proceedings - International Conference on Machine Learning and Cybernetics. vol. 3, 6359501, pp. 1058-1063, 2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012, Xian, Shaanxi, 12/7/15. https://doi.org/10.1109/ICMLC.2012.6359501
Zhang H, Yoshie O. Improving human activity recognition using subspace clustering. In Proceedings - International Conference on Machine Learning and Cybernetics. Vol. 3. 2012. p. 1058-1063. 6359501 https://doi.org/10.1109/ICMLC.2012.6359501
Zhang, Huiquan ; Yoshie, Osamu. / Improving human activity recognition using subspace clustering. Proceedings - International Conference on Machine Learning and Cybernetics. Vol. 3 2012. pp. 1058-1063
@inproceedings{0205e524572c4426b3194c4ac25fe098,
title = "Improving human activity recognition using subspace clustering",
abstract = "Activity recognition attracted much interest in pervasive sensing due to extensive application in human daily life from health monitoring to security monitoring. It utilizes collection of data from low level sensor to learn about human behaviors and activities, so that services can be provided by function of detecting anomalies, remote interventions or prompts. The approach of human activity modeling and recognition still confronted with a challenge on issues of modeling human activity in human perspective. However, the traditional learning-based approaches are not sufficient to capture the characteristics of human activity because they still use traditional clustering method to process sensor data which consists of multidimensional information. This paper describes a subspace clustering-based approach to recognize human activity and detect exceptional activities. Different from many approaches, the proposed approach use subspace clustering based approach to model of human activity in order to improve accuracy of activity recognition. Finally, the proposed approach has been validated on data collected from RFID-based systems, which results demonstrate the effectiveness of the proposed improvents.",
keywords = "Activity recognition, Multiple dimensional data, RFID, Subspaces clustering",
author = "Huiquan Zhang and Osamu Yoshie",
year = "2012",
doi = "10.1109/ICMLC.2012.6359501",
language = "English",
isbn = "9781467314855",
volume = "3",
pages = "1058--1063",
booktitle = "Proceedings - International Conference on Machine Learning and Cybernetics",

}

TY - GEN

T1 - Improving human activity recognition using subspace clustering

AU - Zhang, Huiquan

AU - Yoshie, Osamu

PY - 2012

Y1 - 2012

N2 - Activity recognition attracted much interest in pervasive sensing due to extensive application in human daily life from health monitoring to security monitoring. It utilizes collection of data from low level sensor to learn about human behaviors and activities, so that services can be provided by function of detecting anomalies, remote interventions or prompts. The approach of human activity modeling and recognition still confronted with a challenge on issues of modeling human activity in human perspective. However, the traditional learning-based approaches are not sufficient to capture the characteristics of human activity because they still use traditional clustering method to process sensor data which consists of multidimensional information. This paper describes a subspace clustering-based approach to recognize human activity and detect exceptional activities. Different from many approaches, the proposed approach use subspace clustering based approach to model of human activity in order to improve accuracy of activity recognition. Finally, the proposed approach has been validated on data collected from RFID-based systems, which results demonstrate the effectiveness of the proposed improvents.

AB - Activity recognition attracted much interest in pervasive sensing due to extensive application in human daily life from health monitoring to security monitoring. It utilizes collection of data from low level sensor to learn about human behaviors and activities, so that services can be provided by function of detecting anomalies, remote interventions or prompts. The approach of human activity modeling and recognition still confronted with a challenge on issues of modeling human activity in human perspective. However, the traditional learning-based approaches are not sufficient to capture the characteristics of human activity because they still use traditional clustering method to process sensor data which consists of multidimensional information. This paper describes a subspace clustering-based approach to recognize human activity and detect exceptional activities. Different from many approaches, the proposed approach use subspace clustering based approach to model of human activity in order to improve accuracy of activity recognition. Finally, the proposed approach has been validated on data collected from RFID-based systems, which results demonstrate the effectiveness of the proposed improvents.

KW - Activity recognition

KW - Multiple dimensional data

KW - RFID

KW - Subspaces clustering

UR - http://www.scopus.com/inward/record.url?scp=84871601812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871601812&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2012.6359501

DO - 10.1109/ICMLC.2012.6359501

M3 - Conference contribution

AN - SCOPUS:84871601812

SN - 9781467314855

VL - 3

SP - 1058

EP - 1063

BT - Proceedings - International Conference on Machine Learning and Cybernetics

ER -