For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
User Preference Modelling for Access Selection in Multiple Radio Access Environments
Elaheh HOMAYOUNVALA A. Hamid AGHVAMI
IEICE TRANSACTIONS on Communications
Publication Date: 2005/11/01
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Software Defined Radio Technology and Its Applications)
Bayesian networks, user preferences, personalisation, access selection,
Full Text: PDF(657.7KB)>>
Access selection in future multiple radio access environments is considered in this paper from a new perspective, that of the consumer. A model is proposed for the automatic acquisition of user preferences to assist in access selection decision making. The proposed approach uses a two-level Bayesian C-Metanetwork that models individual user preferences in terms of affordable cost, acceptable level of quality of service and reputation of the access networks. User preferences under different contexts, such as leisure and business, are also considered. The model also adapts to the change of user preferences over time. A simulator has been developed to evaluate the proposed model and the simulation results are promising in terms of the proportion of correct preference predictions after a small number of training samples.