A Proposal of GA Using Symbiotic Evolutionary Viruses and its Virus Evaluation Techniques
Yoshiaki Sakakura*, Noriyuki Taniguchi**, Yukinobu Hoshino***, and Katsuari Kamei***
*Frontier Doctoral Program in Science and Engineering, Ritsumeikan University
**Graduate School of Science and Engineering, Ritsumeikan University
***Human and Computer Intelligence, College Information Science and Engineering, Ritsumeikan University, 1-1-1 Noji-higashi, Kusatsu, Shiga 525-8577, Japan
In this paper, we propose a Genetic Algorithm (GA) using symbiotic evolutionary viruses based on both the building block hypothesis and the virus theory of evolution. The proposed GA aims to control the destruction of building blocks by discovery, maintenance, and propagation of building blocks based on virus operation. We prepare a group of individuals and a group of viruses. The group of individuals searches for solutions and the group of viruses searches for building blocks. These searches are done based on the symbiotic relation of both groups. Also, our GA has two types of virus evaluation technique. In one type, each virus is evaluated by the difference of the fitness of an individual before and after virus infection. In the other type, all viruses are evaluated by the difference of the fitness of an individual before and after infection of all viruses. We applied the proposed GA to a minimum value search problem using a test function with some local minima far from the optimum. Finally, we also discuss the search behavior in the proposed GA based on each virus evaluation technique.