Ulster University Logo

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

Vance, Philip, Das, Gautham, McGinnity, TM, Coleman, SA and Maguire, LP (2014) Novelty Detection in User Behavioural Models within Ambient Assisted Living Applications: An Experimental Evaluation. In: IEEE International Conference on Robotics and Biometrics, Bali, Indonesia. IEEE. 6 pp. [Conference contribution]

Full text not available from this repository.

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.

Item Type:Conference contribution (Lecture)
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Intelligent Systems
Research Institutes and Groups:Computer Science Research Institute > Intelligent Systems Research Centre
Computer Science Research Institute
ID Code:30973
Deposited By: Dr Sonya Coleman
Deposited On:26 Feb 2015 16:55
Last Modified:26 Feb 2015 16:55

Repository Staff Only: item control page