Mining emerging sequential patterns for activity recognition in body sensor networks

Tao Gu; Liang Wang; Hanhua Chen; Guimei Liu; Xianping Tao; Jian Lu

doi:10.1007/978-3-642-29154-8_9

Mining emerging sequential patterns for activity recognition in body sensor networks

Tao Gu, Liang Wang, Hanhua Chen, Guimei Liu, Xianping Tao, Jian Lu

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

1 Citation (Scopus)

Abstract

Body Sensor Networks offer many applications in healthcare, well-being and entertainment. One of the emerging applications is recognizing activities of daily living. In this paper, we introduce a novel knowledge pattern named Emerging Sequential Pattern (ESP)—a sequential pattern that discovers significant class differences—to recognize both simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities. Based on ESPs, we build our complex activity models directly upon the sequential model to recognize both activity types. We conduct comprehensive empirical studies to evaluate and compare our solution with the state-of-the-art solutions. The results demonstrate that our approach achieves an overall accuracy of 91.89%, outperforming the existing solutions.

Original language	English
Title of host publication	Mobile and Ubiquitous Systems: Computing, Networking, and Services
Subtitle of host publication	7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers
Editors	Patrick Sénac, Max Ott, Aruna Seneviratne
Place of Publication	Heidelberg, Germany
Publisher	Springer, Springer Nature
Pages	102-113
Number of pages	12
ISBN (Electronic)	9783642291548
ISBN (Print)	9783642291531
DOIs	https://doi.org/10.1007/978-3-642-29154-8_9
Publication status	Published - 2012
Externally published	Yes
Event	International ICST Conference on Mobile and Ubiquitous Systems : Computing, Networking and Services (7th : 2010) - Sydney Duration: 6 Dec 2010 → 9 Dec 2010

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Volume	73
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	International ICST Conference on Mobile and Ubiquitous Systems : Computing, Networking and Services (7th : 2010)
City	Sydney
Period	6/12/10 → 9/12/10

Keywords

Body sensor networks
activity recognition
data mining

Access to Document

10.1007/978-3-642-29154-8_9

Cite this

Gu, T., Wang, L., Chen, H., Liu, G., Tao, X., & Lu, J. (2012). Mining emerging sequential patterns for activity recognition in body sensor networks. In P. Sénac, M. Ott, & A. Seneviratne (Eds.), Mobile and Ubiquitous Systems: Computing, Networking, and Services: 7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers (pp. 102-113). (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 73). Springer, Springer Nature. https://doi.org/10.1007/978-3-642-29154-8_9

Gu, Tao ; Wang, Liang ; Chen, Hanhua et al. / Mining emerging sequential patterns for activity recognition in body sensor networks. Mobile and Ubiquitous Systems: Computing, Networking, and Services: 7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers. editor / Patrick Sénac ; Max Ott ; Aruna Seneviratne. Heidelberg, Germany : Springer, Springer Nature, 2012. pp. 102-113 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering).

@inproceedings{6617fc0a6e044882bbc1deb671455809,

title = "Mining emerging sequential patterns for activity recognition in body sensor networks",

abstract = "Body Sensor Networks offer many applications in healthcare, well-being and entertainment. One of the emerging applications is recognizing activities of daily living. In this paper, we introduce a novel knowledge pattern named Emerging Sequential Pattern (ESP)—a sequential pattern that discovers significant class differences—to recognize both simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities. Based on ESPs, we build our complex activity models directly upon the sequential model to recognize both activity types. We conduct comprehensive empirical studies to evaluate and compare our solution with the state-of-the-art solutions. The results demonstrate that our approach achieves an overall accuracy of 91.89%, outperforming the existing solutions.",

keywords = "Body sensor networks, activity recognition, data mining",

author = "Tao Gu and Liang Wang and Hanhua Chen and Guimei Liu and Xianping Tao and Jian Lu",

year = "2012",

doi = "10.1007/978-3-642-29154-8_9",

language = "English",

isbn = "9783642291531",

series = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",

publisher = "Springer, Springer Nature",

pages = "102--113",

editor = "Patrick S{\'e}nac and Max Ott and Aruna Seneviratne",

booktitle = "Mobile and Ubiquitous Systems: Computing, Networking, and Services",

address = "United States",

note = "International ICST Conference on Mobile and Ubiquitous Systems : Computing, Networking and Services (7th : 2010) ; Conference date: 06-12-2010 Through 09-12-2010",

}

Gu, T, Wang, L, Chen, H, Liu, G, Tao, X & Lu, J 2012, Mining emerging sequential patterns for activity recognition in body sensor networks. in P Sénac, M Ott & A Seneviratne (eds), Mobile and Ubiquitous Systems: Computing, Networking, and Services: 7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 73, Springer, Springer Nature, Heidelberg, Germany, pp. 102-113, International ICST Conference on Mobile and Ubiquitous Systems : Computing, Networking and Services (7th : 2010), Sydney, 6/12/10. https://doi.org/10.1007/978-3-642-29154-8_9

Mining emerging sequential patterns for activity recognition in body sensor networks. / Gu, Tao; Wang, Liang; Chen, Hanhua et al.
Mobile and Ubiquitous Systems: Computing, Networking, and Services: 7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers. ed. / Patrick Sénac; Max Ott; Aruna Seneviratne. Heidelberg, Germany: Springer, Springer Nature, 2012. p. 102-113 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 73).

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

TY - GEN

T1 - Mining emerging sequential patterns for activity recognition in body sensor networks

AU - Gu, Tao

AU - Wang, Liang

AU - Chen, Hanhua

AU - Liu, Guimei

AU - Tao, Xianping

AU - Lu, Jian

PY - 2012

Y1 - 2012

N2 - Body Sensor Networks offer many applications in healthcare, well-being and entertainment. One of the emerging applications is recognizing activities of daily living. In this paper, we introduce a novel knowledge pattern named Emerging Sequential Pattern (ESP)—a sequential pattern that discovers significant class differences—to recognize both simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities. Based on ESPs, we build our complex activity models directly upon the sequential model to recognize both activity types. We conduct comprehensive empirical studies to evaluate and compare our solution with the state-of-the-art solutions. The results demonstrate that our approach achieves an overall accuracy of 91.89%, outperforming the existing solutions.

AB - Body Sensor Networks offer many applications in healthcare, well-being and entertainment. One of the emerging applications is recognizing activities of daily living. In this paper, we introduce a novel knowledge pattern named Emerging Sequential Pattern (ESP)—a sequential pattern that discovers significant class differences—to recognize both simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities. Based on ESPs, we build our complex activity models directly upon the sequential model to recognize both activity types. We conduct comprehensive empirical studies to evaluate and compare our solution with the state-of-the-art solutions. The results demonstrate that our approach achieves an overall accuracy of 91.89%, outperforming the existing solutions.

KW - Body sensor networks

KW - activity recognition

KW - data mining

U2 - 10.1007/978-3-642-29154-8_9

DO - 10.1007/978-3-642-29154-8_9

M3 - Conference proceeding contribution

SN - 9783642291531

T3 - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

SP - 102

EP - 113

BT - Mobile and Ubiquitous Systems: Computing, Networking, and Services

A2 - Sénac, Patrick

A2 - Ott, Max

A2 - Seneviratne, Aruna

PB - Springer, Springer Nature

CY - Heidelberg, Germany

T2 - International ICST Conference on Mobile and Ubiquitous Systems : Computing, Networking and Services (7th : 2010)

Y2 - 6 December 2010 through 9 December 2010

ER -

Gu T, Wang L, Chen H, Liu G, Tao X, Lu J. Mining emerging sequential patterns for activity recognition in body sensor networks. In Sénac P, Ott M, Seneviratne A, editors, Mobile and Ubiquitous Systems: Computing, Networking, and Services: 7th International ICST Conference, MobiQuitous 2010 Sydney, Australia, December 6-9, 2010 Revised Selected Papers. Heidelberg, Germany: Springer, Springer Nature. 2012. p. 102-113. (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering). doi: 10.1007/978-3-642-29154-8_9

Mining emerging sequential patterns for activity recognition in body sensor networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this