Virus Evolution Based Gene Expression Programming for Classification Rules Mining
Gene Expression Programming(GEP) is a novel and accurate approach for classification. With the shortcoming of GEP, it often falls into the local optimums. In this paper, we introduce the virus evolutionary mechanism into GEP, with the infection operation of virus population, the diversity of the host population is increased, and the system is much easier to jump out of the local optimums, and much faster to obtain better results. Experiments on several benchmark data sets show that our approach can get close average accuracy and much better best accuracy compared with available results. What’s more, the average execution time is largely decreased due to smaller population size and maximum generation.
W. H. Wang et al., "Virus Evolution Based Gene Expression Programming for Classification Rules Mining", Key Engineering Materials, Vols. 467-469, pp. 1392-1397, 2011