Exploring appropriate clusters in subspace for human activity recognition

Huiquan Zhang, Sha Luo, Osamu Yoshie

Research output: Contribution to journalArticle

Abstract

Activity recognition, which has emerged as a pivotal research topic in pervasive sensing over the last several years, utilizes a collection of data from sensors to capture human behavior, detect anomalies and provide warning or guidance information. This paper presents an approach to explore appropriate clusters in subspace for human activity recognition. The approach includes two major phases: discovery of human activity (extraction of human behavior patterns and generation of human activity clusters), and recognition of human activity (application of similarity function to recognize activities). Different from many existing works, the proposed approach applies a subspace clustering based algorithm to generate clusters of human activity. This approach aims to accumulate human activity by approximating the generated clusters to the activity from a conceptual human perspective. The experiments were implemented using radio-frequency identification (RFID) based systems. The results show that the proposed approach is effective in improving the accuracy of both activity discovery and activity recognition.

Original languageEnglish
Pages (from-to)2282-2290
Number of pages9
JournalIEEJ Transactions on Electronics, Information and Systems
Volume133
Issue number12
DOIs
Publication statusPublished - 2013

Fingerprint

Radio frequency identification (RFID)
Sensors
Experiments

Keywords

  • Activity recognition
  • Multi-dimensional data
  • Pattern extraction
  • Subspaces clustering

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Exploring appropriate clusters in subspace for human activity recognition. / Zhang, Huiquan; Luo, Sha; Yoshie, Osamu.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 133, No. 12, 2013, p. 2282-2290.

Research output: Contribution to journalArticle

@article{4857bcc9eb6d4f3e8e0184851ba45afb,
title = "Exploring appropriate clusters in subspace for human activity recognition",
abstract = "Activity recognition, which has emerged as a pivotal research topic in pervasive sensing over the last several years, utilizes a collection of data from sensors to capture human behavior, detect anomalies and provide warning or guidance information. This paper presents an approach to explore appropriate clusters in subspace for human activity recognition. The approach includes two major phases: discovery of human activity (extraction of human behavior patterns and generation of human activity clusters), and recognition of human activity (application of similarity function to recognize activities). Different from many existing works, the proposed approach applies a subspace clustering based algorithm to generate clusters of human activity. This approach aims to accumulate human activity by approximating the generated clusters to the activity from a conceptual human perspective. The experiments were implemented using radio-frequency identification (RFID) based systems. The results show that the proposed approach is effective in improving the accuracy of both activity discovery and activity recognition.",
keywords = "Activity recognition, Multi-dimensional data, Pattern extraction, Subspaces clustering",
author = "Huiquan Zhang and Sha Luo and Osamu Yoshie",
year = "2013",
doi = "10.1541/ieejeiss.133.2282",
language = "English",
volume = "133",
pages = "2282--2290",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "12",

}

TY - JOUR

T1 - Exploring appropriate clusters in subspace for human activity recognition

AU - Zhang, Huiquan

AU - Luo, Sha

AU - Yoshie, Osamu

PY - 2013

Y1 - 2013

N2 - Activity recognition, which has emerged as a pivotal research topic in pervasive sensing over the last several years, utilizes a collection of data from sensors to capture human behavior, detect anomalies and provide warning or guidance information. This paper presents an approach to explore appropriate clusters in subspace for human activity recognition. The approach includes two major phases: discovery of human activity (extraction of human behavior patterns and generation of human activity clusters), and recognition of human activity (application of similarity function to recognize activities). Different from many existing works, the proposed approach applies a subspace clustering based algorithm to generate clusters of human activity. This approach aims to accumulate human activity by approximating the generated clusters to the activity from a conceptual human perspective. The experiments were implemented using radio-frequency identification (RFID) based systems. The results show that the proposed approach is effective in improving the accuracy of both activity discovery and activity recognition.

AB - Activity recognition, which has emerged as a pivotal research topic in pervasive sensing over the last several years, utilizes a collection of data from sensors to capture human behavior, detect anomalies and provide warning or guidance information. This paper presents an approach to explore appropriate clusters in subspace for human activity recognition. The approach includes two major phases: discovery of human activity (extraction of human behavior patterns and generation of human activity clusters), and recognition of human activity (application of similarity function to recognize activities). Different from many existing works, the proposed approach applies a subspace clustering based algorithm to generate clusters of human activity. This approach aims to accumulate human activity by approximating the generated clusters to the activity from a conceptual human perspective. The experiments were implemented using radio-frequency identification (RFID) based systems. The results show that the proposed approach is effective in improving the accuracy of both activity discovery and activity recognition.

KW - Activity recognition

KW - Multi-dimensional data

KW - Pattern extraction

KW - Subspaces clustering

UR - http://www.scopus.com/inward/record.url?scp=84891797015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891797015&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.133.2282

DO - 10.1541/ieejeiss.133.2282

M3 - Article

AN - SCOPUS:84891797015

VL - 133

SP - 2282

EP - 2290

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 12

ER -