Ontological user modelling and semantic rule-based reasoning for personalisation of Help-On-Demand services in pervasive environments
Existing context-aware applications are limited in their support of user personalisation. Nevertheless, the increase in the use of context-aware technologies has sparked the growth in assistive applications resulting in a need to enable adaptation to reflect the changes in user behaviours. This paper introduces a systematic approach to service personalisation for mobile users in pervasive environments and presents a service-oriented distributed system architecture. The developed approach makes use of semantic technologies for user modelling and personalisation reasoning. In the paper we characterise user behaviours and needs in pervasive environments upon which ontological user models are created with special emphasis being placed on ontological modelling of dynamic and adaptive user profiles. We develop a rule-based personalisation mechanism that exploits semantic web rule mark-up language for rule design and a combination of semantic and rule-based reasoning for personalisation. We use two case studies focusing on providing personalised travel assistance for people using Help-on-Demand services deployed on a smart-phone to contextualise the discussions within the paper. The proposed approach is implemented in a prototype system, which includes Help-on-Demand services, content management services, user models and personalisation mechanisms in addition to application specific rules. Experiments have been designed and conducted to test and evaluate the approach with initial results demonstrating the functionality of the approach.
The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
Citation : Skillena, K. L. et al. (2014) Ontological user modelling and semantic rule-based reasoning for personalisation of Help-On-Demand services in pervasive environments. Future Generation Computer System (FGCS), 34, pp.97-109
ISSN : 0167-739X
Research Institute : Cyber Technology Institute (CTI)
Peer Reviewed : Yes