An artificial immune network for multimodal function optimization

This paper presents the adaptation of an immune network model, originally proposed to perform information compression and data clustering, to solve multimodal function optimization problems. The algorithm is described theoretically and empirically compared with similar approaches from the literature. The main features of the algorithm include: automatic determination of the population size, combination of local with global search (exploitation plus exploration of the fitness landscape), defined convergence criterion, and capability of locating and maintaining stable local optima solutions.

I. INTRODUCTION

In spite of the broad applicability of artificial immune systems (AIS) to innumerable domains, the field is only now, around 15 years after its “birth date”, receiving a more careful attention from a theoretical and formal perspective. Y. Ishida and collaborators edited the first book in the year 1998 on immune-based systems. This text was written in Japanese, what considerably restricted its diffusion. In early 1999, another volume [2] with a collection of papers on theoretical immunology and artificial immune systems was edited.