Immune network based ensembles

Abstract

This paper presents a new method for constructing ensembles of classifiers based on immune network theory, one of the most interesting paradigms within the field of artificial immune systems. Ensembles of classifiers are a very interesting alternative to single classifiers when facing difficult problems. In general, ensembles are able to achieve better performance in terms of learning and generalisation error. Artificial immune system is a new paradigm within the field of bioinspired algorithms that mimics the behaviour of the natural immune system of animals to develop solutions for a given problem. Within artificial immune systems, one of the most innovative and appealing fields is immune network theory. We construct an immune network that constitutes an ensemble of classifiers. Using a neural network as base classifier we have compared the performance of this ensemble with five standard methods of ensemble construction. This comparison is made using 35 real-world classification problems from the UCI Machine Learning Repository. The results show that the proposed model exhibits a general advantage over the standard methods.