Skip to Main Content
Trust management in pervasive computing becomes increasingly important and obtained high attention a few years ago. Different methodologies have been proposed to improve trust management. These approaches can be classified into three groups as follows: the first group used Bayesian statistics and its derivation such as Dempster-Shaffer theory of evidence. The second group used game theory, and the third group depends on algebraic ordinary set operation and fuzzy logic. Despite the previous work in this area, a comprehensive security model to support trust management has yet been accomplished. The critical security threats in this environment necessitate a comprehensive trust and privacy models which require integration of different concepts to evaluate precisely the trustworthiness of entities. In this paper, we propose a trust management scheme by implementing a fusion of the support vector machine (SVM) and fuzzy logic system. The main motivation of the proposed scheme in using the support vector machine is to predict the optimal trust values for approximation purpose, and then those approximated values relate the fuzzy basis functions.