A Novel Multimodal Data Analytic Scheme for Human Activity Recognition

Girija CHETTY, Mohammad Yamin

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

1 Citation (Scopus)

Abstract

In this article, we propose a novel multimodal data analytics scheme for human activity recognition. Traditional data analysis schemes for activity recognition using heterogeneous sensor network setups for eHealth application scenarios are usually a heuristic process, involving underlying domain knowledge. Relying on such explicit knowledge is problematic when aiming to create automatic, unsupervised or semi-supervised monitoring and tracking of different activities, and detection of abnormal events. Experiments on a publicly available OPPORTUNITY activity recognition database from UCI machine learning repository demonstrates the potential of our approach to address next generation unsupervised automatic classification and detection approaches for remote activity recognition for novel, eHealth application scenarios, such as monitoring and tracking of elderly, disabled and those with special needs
Original languageEnglish
Title of host publicationService Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings
EditorsChangrui Yu, Kecheng Liu, Stephen R. Gulliver, Weizi Li
Place of PublicationBerlin, Germany
PublisherSpringer
Pages449-458
Number of pages10
Volume426
Edition426
ISBN (Electronic)9783642553554
ISBN (Print)9783642553547
DOIs
Publication statusPublished - 2014
Event15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014 - Shanghai, Shanghai, China
Duration: 23 May 201424 May 2014
http://www.orgsem.org/2014/

Publication series

NameIFIP Advances in Information and Communication Technology
Volume426
ISSN (Print)1868-4238

Conference

Conference15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014
CountryChina
CityShanghai
Period23/05/1424/05/14
Internet address

Fingerprint

Monitoring
Heterogeneous networks
Sensor networks
Learning systems
Experiments

Cite this

CHETTY, G., & Yamin, M. (2014). A Novel Multimodal Data Analytic Scheme for Human Activity Recognition. In C. Yu, K. Liu, S. R. Gulliver, & W. Li (Eds.), Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings (426 ed., Vol. 426, pp. 449-458). (IFIP Advances in Information and Communication Technology; Vol. 426). Berlin, Germany: Springer. https://doi.org/10.1007/978-3-642-55355-4_47
CHETTY, Girija ; Yamin, Mohammad. / A Novel Multimodal Data Analytic Scheme for Human Activity Recognition. Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings. editor / Changrui Yu ; Kecheng Liu ; Stephen R. Gulliver ; Weizi Li. Vol. 426 426. ed. Berlin, Germany : Springer, 2014. pp. 449-458 (IFIP Advances in Information and Communication Technology).
@inproceedings{4cd99e3f76174a0f9368717bce8d57e3,
title = "A Novel Multimodal Data Analytic Scheme for Human Activity Recognition",
abstract = "In this article, we propose a novel multimodal data analytics scheme for human activity recognition. Traditional data analysis schemes for activity recognition using heterogeneous sensor network setups for eHealth application scenarios are usually a heuristic process, involving underlying domain knowledge. Relying on such explicit knowledge is problematic when aiming to create automatic, unsupervised or semi-supervised monitoring and tracking of different activities, and detection of abnormal events. Experiments on a publicly available OPPORTUNITY activity recognition database from UCI machine learning repository demonstrates the potential of our approach to address next generation unsupervised automatic classification and detection approaches for remote activity recognition for novel, eHealth application scenarios, such as monitoring and tracking of elderly, disabled and those with special needs",
keywords = "Multimodal, Feature-Learning, Activity-Recognition",
author = "Girija CHETTY and Mohammad Yamin",
year = "2014",
doi = "10.1007/978-3-642-55355-4_47",
language = "English",
isbn = "9783642553547",
volume = "426",
series = "IFIP Advances in Information and Communication Technology",
publisher = "Springer",
pages = "449--458",
editor = "Changrui Yu and Kecheng Liu and Gulliver, {Stephen R.} and Weizi Li",
booktitle = "Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings",
address = "Netherlands",
edition = "426",

}

CHETTY, G & Yamin, M 2014, A Novel Multimodal Data Analytic Scheme for Human Activity Recognition. in C Yu, K Liu, SR Gulliver & W Li (eds), Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings. 426 edn, vol. 426, IFIP Advances in Information and Communication Technology, vol. 426, Springer, Berlin, Germany, pp. 449-458, 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Shanghai, China, 23/05/14. https://doi.org/10.1007/978-3-642-55355-4_47

A Novel Multimodal Data Analytic Scheme for Human Activity Recognition. / CHETTY, Girija; Yamin, Mohammad.

Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings. ed. / Changrui Yu; Kecheng Liu; Stephen R. Gulliver; Weizi Li. Vol. 426 426. ed. Berlin, Germany : Springer, 2014. p. 449-458 (IFIP Advances in Information and Communication Technology; Vol. 426).

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

TY - GEN

T1 - A Novel Multimodal Data Analytic Scheme for Human Activity Recognition

AU - CHETTY, Girija

AU - Yamin, Mohammad

PY - 2014

Y1 - 2014

N2 - In this article, we propose a novel multimodal data analytics scheme for human activity recognition. Traditional data analysis schemes for activity recognition using heterogeneous sensor network setups for eHealth application scenarios are usually a heuristic process, involving underlying domain knowledge. Relying on such explicit knowledge is problematic when aiming to create automatic, unsupervised or semi-supervised monitoring and tracking of different activities, and detection of abnormal events. Experiments on a publicly available OPPORTUNITY activity recognition database from UCI machine learning repository demonstrates the potential of our approach to address next generation unsupervised automatic classification and detection approaches for remote activity recognition for novel, eHealth application scenarios, such as monitoring and tracking of elderly, disabled and those with special needs

AB - In this article, we propose a novel multimodal data analytics scheme for human activity recognition. Traditional data analysis schemes for activity recognition using heterogeneous sensor network setups for eHealth application scenarios are usually a heuristic process, involving underlying domain knowledge. Relying on such explicit knowledge is problematic when aiming to create automatic, unsupervised or semi-supervised monitoring and tracking of different activities, and detection of abnormal events. Experiments on a publicly available OPPORTUNITY activity recognition database from UCI machine learning repository demonstrates the potential of our approach to address next generation unsupervised automatic classification and detection approaches for remote activity recognition for novel, eHealth application scenarios, such as monitoring and tracking of elderly, disabled and those with special needs

KW - Multimodal

KW - Feature-Learning

KW - Activity-Recognition

UR - http://www.scopus.com/inward/record.url?scp=84927725663&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-55355-4_47

DO - 10.1007/978-3-642-55355-4_47

M3 - Conference contribution

SN - 9783642553547

VL - 426

T3 - IFIP Advances in Information and Communication Technology

SP - 449

EP - 458

BT - Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings

A2 - Yu, Changrui

A2 - Liu, Kecheng

A2 - Gulliver, Stephen R.

A2 - Li, Weizi

PB - Springer

CY - Berlin, Germany

ER -

CHETTY G, Yamin M. A Novel Multimodal Data Analytic Scheme for Human Activity Recognition. In Yu C, Liu K, Gulliver SR, Li W, editors, Service Science and Knowledge Innovation - 15th IFIP WG 8.1 International Conference on Informatics and Semiotics in Organisations, ICISO 2014, Proceedings. 426 ed. Vol. 426. Berlin, Germany: Springer. 2014. p. 449-458. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-3-642-55355-4_47