A measure of competence based on random classification for dynamic ensemble selection

In this paper, a measure of competence based on random classification (MCR) for classifier ensembles is presented. The measure selects dynamically (i.e. for each test example) a subset of classifiers from the ensemble that perform better than a random classifier. Therefore, weak (incompetent) classifiers that would adversely affect the performance of a classification system are eliminated. When all classifiers in the ensemble are evaluated as incompetent, the classification accuracy of the system can be increased by using the random classifier instead. Theoretical justification for using the measure with the majority voting rule is given. Two MCR based systems were developed and their performance was compared against six multiple classifier systems using data sets taken from the UCI Machine Learning Repository and Ludmila Kuncheva Collection. The systems developed had typically the highest classification accuracies regardless of the ensemble type used (homogeneous or heterogeneous).

► A measure of competence based on random classification (MCR) is proposed.
► MCR dynamically selects classifiers that perform better than a random classifier.
► If there are no classifiers selected, the random classifier is used instead.
► Two MCR based classification systems were compared against six benchmark systems.
► MCR systems showed the best performance for homo/heterogeneous ensembles.