Computational requirments analysis on the conjunctive and disjunctive assumptions for The Belief Rule Base
Qi Xiong, Guiming Chen, Zhaojun Mao, Tianjun Liao, Leilei Chang · 2017
The Belief Rule Base (BRB) has been used in modeling the complex nonlinear systems. Traditionally, the construction of BRB is under the conjunctive assumption which requires covering each and every possible combination of all the referenced values of all the attributes. Later, the disjunctive assumption of BRB is proposed which does not require simultaneously taking the status of all the attributes under consideration. This study discusses the computational requirements reduction of the two assumptions by calculating the number of the parameters, the initial weights of the rules and the beliefs of the scales in the conclusion part. A numerical case is studied to demonstrate the computation requirements under either assumption. The case study results show that the disjunctive assumption can significantly reduce the computational requirements in comparison with the conventional conjunctive assumption. This study provides support for further study regarding on the theoretical and characteristic studies on the disjunctive assumption in BRB construction.