A Dynamic Trust Model Based on Naive Bayes Classifier for Ubiquitous Environments

摘要

Computational models of trust have been proposed for use in ubiquitous computing environments to decide whether to provide services to requesters which are either unfamiliar with service providers or do not have enough access rights to certain services. Due to the highly dynamic and unpredictable characteristic of ubiquitous environments, the trust model should make trust decision dynamically. In this paper, we introduce a novel Naive Bayes classifier based trust model which can dynamically make trust decision in different situations. The trust evaluation is based on service provider's own prior knowledge in stead of assuming variable weights and pre-defined fixed thresholds. This model is also suitable to make decision when only limited information is available in ubiquitous environments. Finally we give the simulation results of our model and the comparison with the related works.