Capacities and overlap indexes with an application in fuzzy rule-based classification systems

In this work, we introduce a method for constructing capacities using overlap indexes between the fuzzy sets which are generated from the inputs of the considered problem. We also use these capacities to aggregate information by means of the Choquet integral in a fuzzy rule-based classifier. We observe that with these capacities the obtained results are better than those obtained with other measures. (C) 2016 Elsevier B.V. All rights reserved.