Abstract
Uncertainty and indeterminacy are two major problems in data analysis these days. Neutrosophy is a generalization of the fuzzy theory. Neutrosophic system is based on indeterminism and falsity of concepts in addition to truth degrees. Any neutrosophy variable or concept is defined by membership, indeterminacy and non-membership functions. Finding efficient and accurate definition for neutrosophic variables is a challenging process. This paper presents a framework of Ant Colony Optimization and entropy theory to define a neutrosophic variable from concrete data.
Ant Colony Optimization is an efficient search algorithm presented to define parameters of membership, indeterminacy and non-membership functions. The integrated framework of information theory measures and Ant Colony Optimization is proposed. Experimental results contain graphical representation of the membership, indeterminacy and non-membership functions for the temperature variable of the forest fires data set. The graphs demonstrate the effectiveness of the proposed framework.