Artificial immune system based neural networks for solving multi-objective programming problems

In this paper, a hybrid artificial intelligent approach based on the clonal selection principle of artificial immune system (AIS) and neural networks is proposed to solve multi-objective programming problems. Due to the sensitivity to the initial values of initial population of antibodies (Ab’s), neural networks is used to initialize the boundary of the antibodies for AIS to guarantee that all the initial population of Ab’s is feasible. The proposed approach uses dominance principle and feasibility to identify solutions that deserve to be cloned, and uses two types of mutation: uniform mutation is applied to the clones produced and non-uniform mutation is applied to the “not so good” antibodies. A secondary (or external) population that stores the nondominated solutions found along the search process is used. Such secondary population constitutes the elitist mechanism of our approach and it allows it to move towards the Pareto front.