Genetic Algorithms with diversity measures for multiple classifier systems
Date:
The combination of classifiers is an active research area of the machine learning and pattern recognition communities. Many theoretical and empirical studies have been published demonstrating the advantages of the paradigm of combination of classifiers over the individual classifiers. When combining classifiers it is important to guarantee the diversity among them. Some statistical measures can be used to estimate how diverse the ensembles of classifiers are. Genetic algorithms play a significant role as search technique for handling complex spaces in many fields. They are based on the underlying genetic process in biological organisms and on the natural evolution principles of populations. These algorithms process a population of chromosomes, which represent search space solutions, with three operations: selection, crossover and mutation. Under its initial formulation, the search space of solutions is coded using the binary alphabet. In this work some diversity measures are presented and a variant of a Genetic Algorithm is implemented in order to obtain, from all the possible combinations of a large number of base classifiers, a combination that ensures greater diversity among the chosen classifiers and multiple classifier system accuracy