Long-term behavioural change detection through pervasive sensing

John Kemp, Elena Gaura, Ramona Rednic, James Brusey

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

3 Citations (Scopus)
14 Downloads (Pure)

Abstract

The paper proposes an information generation and summarisation algorithm to detect behavioural change in applications such as long-term monitoring of vulnerable people. The algorithm learns the monitored subject's behaviour autonomously post-deployment and provides time-suppressed summaries of the activity types engaged with by the subject over the course of their day to day life. It transmits updates to external observers only when the summary changes by more than a defined threshold. This technique substantially reduces the number of transmission required by a wearable monitoring system, both through summarisation of the raw data into useful information and by preventing transmission of duplicated or predictable data and information. Based on evaluation using simulated activity data, the proposed algorithm results in an average of one transmission per month following an initial convergence period (reaching less than 1 transmission per day after only three days) and detects a change in behaviour after an average of 1.1 days.

Original languageEnglish
Title of host publication2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing
PublisherIEEE
Pages629-634
Number of pages5
ISBN (Electronic)978-0-7695-5005-3
ISBN (Print)978-1-4799-0371-9
DOIs
Publication statusPublished - 16 Sep 2013
Event14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing - Honolulu, United States
Duration: 1 Jul 20133 Jul 2013

Conference

Conference14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing
CountryUnited States
CityHonolulu
Period1/07/133/07/13

Fingerprint

Monitoring

Bibliographical note

Paper presented at the 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2013), held 1–3 July 2013, Honolulu Hawaii, U.S.A.
This paper is due to be published by IEEE in the conference proceedings, and full citation details will be updated once available.
© 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • body sensor networks
  • pervasive sensing
  • behavioural change detection
  • Monitoring
  • Biomedical monitoring
  • Sensors
  • Legged locomotion
  • TV
  • Temperature measurement
  • Change detection algorithms
  • ubiquitous computing
  • simulated activity data
  • long-term behavioural change detection
  • information generation
  • information summarisation algorithm
  • wearable monitoring system

Cite this

Kemp, J., Gaura, E., Rednic, R., & Brusey, J. (2013). Long-term behavioural change detection through pervasive sensing. In 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (pp. 629-634). IEEE. https://doi.org/10.1109/SNPD.2013.69

Long-term behavioural change detection through pervasive sensing. / Kemp, John; Gaura, Elena; Rednic, Ramona; Brusey, James.

2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. IEEE, 2013. p. 629-634.

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

Kemp, J, Gaura, E, Rednic, R & Brusey, J 2013, Long-term behavioural change detection through pervasive sensing. in 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. IEEE, pp. 629-634, 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, Honolulu, United States, 1/07/13. https://doi.org/10.1109/SNPD.2013.69
Kemp J, Gaura E, Rednic R, Brusey J. Long-term behavioural change detection through pervasive sensing. In 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. IEEE. 2013. p. 629-634 https://doi.org/10.1109/SNPD.2013.69
Kemp, John ; Gaura, Elena ; Rednic, Ramona ; Brusey, James. / Long-term behavioural change detection through pervasive sensing. 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. IEEE, 2013. pp. 629-634
@inproceedings{95c32e1c205744c0b8116118cf65217f,
title = "Long-term behavioural change detection through pervasive sensing",
abstract = "The paper proposes an information generation and summarisation algorithm to detect behavioural change in applications such as long-term monitoring of vulnerable people. The algorithm learns the monitored subject's behaviour autonomously post-deployment and provides time-suppressed summaries of the activity types engaged with by the subject over the course of their day to day life. It transmits updates to external observers only when the summary changes by more than a defined threshold. This technique substantially reduces the number of transmission required by a wearable monitoring system, both through summarisation of the raw data into useful information and by preventing transmission of duplicated or predictable data and information. Based on evaluation using simulated activity data, the proposed algorithm results in an average of one transmission per month following an initial convergence period (reaching less than 1 transmission per day after only three days) and detects a change in behaviour after an average of 1.1 days.",
keywords = "body sensor networks, pervasive sensing, behavioural change detection, Monitoring, Biomedical monitoring, Sensors, Legged locomotion, TV, Temperature measurement, Change detection algorithms, ubiquitous computing, simulated activity data, long-term behavioural change detection, information generation, information summarisation algorithm, wearable monitoring system",
author = "John Kemp and Elena Gaura and Ramona Rednic and James Brusey",
note = "Paper presented at the 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2013), held 1–3 July 2013, Honolulu Hawaii, U.S.A. This paper is due to be published by IEEE in the conference proceedings, and full citation details will be updated once available. {\circledC} 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2013",
month = "9",
day = "16",
doi = "10.1109/SNPD.2013.69",
language = "English",
isbn = "978-1-4799-0371-9",
pages = "629--634",
booktitle = "2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing",
publisher = "IEEE",
address = "United States",

}

TY - GEN

T1 - Long-term behavioural change detection through pervasive sensing

AU - Kemp, John

AU - Gaura, Elena

AU - Rednic, Ramona

AU - Brusey, James

N1 - Paper presented at the 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2013), held 1–3 July 2013, Honolulu Hawaii, U.S.A. This paper is due to be published by IEEE in the conference proceedings, and full citation details will be updated once available. © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2013/9/16

Y1 - 2013/9/16

N2 - The paper proposes an information generation and summarisation algorithm to detect behavioural change in applications such as long-term monitoring of vulnerable people. The algorithm learns the monitored subject's behaviour autonomously post-deployment and provides time-suppressed summaries of the activity types engaged with by the subject over the course of their day to day life. It transmits updates to external observers only when the summary changes by more than a defined threshold. This technique substantially reduces the number of transmission required by a wearable monitoring system, both through summarisation of the raw data into useful information and by preventing transmission of duplicated or predictable data and information. Based on evaluation using simulated activity data, the proposed algorithm results in an average of one transmission per month following an initial convergence period (reaching less than 1 transmission per day after only three days) and detects a change in behaviour after an average of 1.1 days.

AB - The paper proposes an information generation and summarisation algorithm to detect behavioural change in applications such as long-term monitoring of vulnerable people. The algorithm learns the monitored subject's behaviour autonomously post-deployment and provides time-suppressed summaries of the activity types engaged with by the subject over the course of their day to day life. It transmits updates to external observers only when the summary changes by more than a defined threshold. This technique substantially reduces the number of transmission required by a wearable monitoring system, both through summarisation of the raw data into useful information and by preventing transmission of duplicated or predictable data and information. Based on evaluation using simulated activity data, the proposed algorithm results in an average of one transmission per month following an initial convergence period (reaching less than 1 transmission per day after only three days) and detects a change in behaviour after an average of 1.1 days.

KW - body sensor networks

KW - pervasive sensing

KW - behavioural change detection

KW - Monitoring

KW - Biomedical monitoring

KW - Sensors

KW - Legged locomotion

KW - TV

KW - Temperature measurement

KW - Change detection algorithms

KW - ubiquitous computing

KW - simulated activity data

KW - long-term behavioural change detection

KW - information generation

KW - information summarisation algorithm

KW - wearable monitoring system

U2 - 10.1109/SNPD.2013.69

DO - 10.1109/SNPD.2013.69

M3 - Conference proceeding

SN - 978-1-4799-0371-9

SP - 629

EP - 634

BT - 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing

PB - IEEE

ER -