Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation

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

1 Citation (Scopus)

Abstract

Current approaches to networked robot systems(or ecology of robots and sensors) in ambient assisted livingapplications (AAL) rely on pre-programmed models of theenvironment and do not evolve to address novel states of theenvironment. Envisaged as part of a robotic ecology in an AALenvironment to provide different services based on the eventsand user activities, a Markov based approach to establishing auser behavioural model through the use of a cognitive memorymodule is presented in this paper. Upon detecting changes inthe normal user behavioural pattern, the ecology tries to adaptits response to these changes in an intelligent manner. Theapproach is evaluated with physical robots and anexperimental evaluation is presented in this paper. A majorchallenge associated with data storage in a sensor richenvironment is the expanding memory requirements. In orderto address this, a bio-inspired data retention strategy is alsoproposed. These contributions can enable a robotic ecology toadapt to evolving environmental states while efficientlymanaging the memory footprint.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1868-1873
Number of pages6
Publication statusPublished - 5 Dec 2014
EventIEEE International Conference on Robotics and Biometrics - Bali, Indonesia
Duration: 5 Dec 2014 → …

Conference

ConferenceIEEE International Conference on Robotics and Biometrics
Period5/12/14 → …

Fingerprint

Ecology
Robots
Data storage equipment
Robotics
Sensors
Assisted living

Cite this

@inproceedings{d6865aa561ae4997818f23cd98c4d39b,
title = "Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation",
abstract = "Current approaches to networked robot systems(or ecology of robots and sensors) in ambient assisted livingapplications (AAL) rely on pre-programmed models of theenvironment and do not evolve to address novel states of theenvironment. Envisaged as part of a robotic ecology in an AALenvironment to provide different services based on the eventsand user activities, a Markov based approach to establishing auser behavioural model through the use of a cognitive memorymodule is presented in this paper. Upon detecting changes inthe normal user behavioural pattern, the ecology tries to adaptits response to these changes in an intelligent manner. Theapproach is evaluated with physical robots and anexperimental evaluation is presented in this paper. A majorchallenge associated with data storage in a sensor richenvironment is the expanding memory requirements. In orderto address this, a bio-inspired data retention strategy is alsoproposed. These contributions can enable a robotic ecology toadapt to evolving environmental states while efficientlymanaging the memory footprint.",
author = "Philip Vance and Gautham Das and TM McGinnity and SA Coleman and LP Maguire",
year = "2014",
month = "12",
day = "5",
language = "English",
pages = "1868--1873",
booktitle = "Unknown Host Publication",

}

Vance, P, Das, G, McGinnity, TM, Coleman, SA & Maguire, LP 2014, Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation. in Unknown Host Publication. pp. 1868-1873, IEEE International Conference on Robotics and Biometrics, 5/12/14.

Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation. / Vance, Philip; Das, Gautham; McGinnity, TM; Coleman, SA; Maguire, LP.

Unknown Host Publication. 2014. p. 1868-1873.

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

TY - GEN

T1 - Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation

AU - Vance, Philip

AU - Das, Gautham

AU - McGinnity, TM

AU - Coleman, SA

AU - Maguire, LP

PY - 2014/12/5

Y1 - 2014/12/5

N2 - Current approaches to networked robot systems(or ecology of robots and sensors) in ambient assisted livingapplications (AAL) rely on pre-programmed models of theenvironment and do not evolve to address novel states of theenvironment. Envisaged as part of a robotic ecology in an AALenvironment to provide different services based on the eventsand user activities, a Markov based approach to establishing auser behavioural model through the use of a cognitive memorymodule is presented in this paper. Upon detecting changes inthe normal user behavioural pattern, the ecology tries to adaptits response to these changes in an intelligent manner. Theapproach is evaluated with physical robots and anexperimental evaluation is presented in this paper. A majorchallenge associated with data storage in a sensor richenvironment is the expanding memory requirements. In orderto address this, a bio-inspired data retention strategy is alsoproposed. These contributions can enable a robotic ecology toadapt to evolving environmental states while efficientlymanaging the memory footprint.

AB - Current approaches to networked robot systems(or ecology of robots and sensors) in ambient assisted livingapplications (AAL) rely on pre-programmed models of theenvironment and do not evolve to address novel states of theenvironment. Envisaged as part of a robotic ecology in an AALenvironment to provide different services based on the eventsand user activities, a Markov based approach to establishing auser behavioural model through the use of a cognitive memorymodule is presented in this paper. Upon detecting changes inthe normal user behavioural pattern, the ecology tries to adaptits response to these changes in an intelligent manner. Theapproach is evaluated with physical robots and anexperimental evaluation is presented in this paper. A majorchallenge associated with data storage in a sensor richenvironment is the expanding memory requirements. In orderto address this, a bio-inspired data retention strategy is alsoproposed. These contributions can enable a robotic ecology toadapt to evolving environmental states while efficientlymanaging the memory footprint.

M3 - Conference contribution

SP - 1868

EP - 1873

BT - Unknown Host Publication

ER -