Fuzzy rule base generation for classification and its minimization via modified threshold accepting

This paper addresses the application of a modified threshold accepting algo rithm (MTA) for minimizing the number of rules in a fuzzy rule-based classi fication system, while guaranteeing high classification power. In terms of computational time required, the MTA outperforms the GA approaches, which a re applied to this multi-objective combinatorial optimization problem in th e literature. The number of rules used and the classification power are tak en as the objectives. The original model of Ishibuchi ct al, (IEEE Trans. F uzzy Systems 3 1995, 260-270) is further modified by employing various aggr egators such as the gamma -operator (compensatory and), fuzzy and and a con vex combinations of min and max operators in place of product and min opera tors, The performance of the present model is demonstrated in the case of F isher's well-known Iris data and other data appearing in literature. Less c omputational time needed in all cases and better classification rate in tes ting phase (in leave-one-out technique) are important contributions of the present model. (C) 2001 Elsevier Science B.V. All rights reserved.