An Improved Immune Genetic Algorithm and its Application on TSP

Conventional genetic operators; mutation, and crossover; are commonly semi-blind because of their random operation and lack of knowledge about the properties of the problem. In this paper, we have investigated the genetic algorithms with immunity, and we have studied the effect of immunity idea on one of the most used examples in genetic algorithms literature, which is the traveling salesman problem (TSP). We described the main concepts of vaccinations and immune selection steps that will help the normal genetic algorithms operators to do better behavior. Experiment results proved that the performance of the default genetic algorithms operators have been improved both in convergent speed and in the capability of obtaining optimum solution for traveling salesman problem.