A novel rule base representation and its inference method using the evidential reasoning approach

In this paper, a novel rule base, Certainty Rule Base (CeRB), and its inference method are proposed. This rule base is firstly designed with certainty degrees embedded in the antecedent terms as well as in the consequent terms. CeRB is shown to be capable of capturing vagueness, incompleteness, uncertainty, and nonlinear causal relationships in an integrated way. Secondly, the CeRB inference method using the evidential reasoning approach is provided. The overall representation and inference framework offer a further improvement and a great extension of the recently uncertainty inference methods. Namely, the knowledge is represented by CeRB and the evidential reasoning approach is applied to the rule combination. In the end, two case studies including a numerical example and a software defect prediction are provided to illustrate the proposed CeRB representation, generation and inference procedure as well as demonstrate its high performance by comparing with some existing approaches.