MHC-inspired Antibody Clone Algorithm for Multimodal Function Optimization

Intelligent optimization algorithms based on biological mechanisms have better performance than traditional ones in solving complex multimodal function optimization problems. Most of those intelligent algorithms, however, have the problems of degeneration and vibration, which will lead to poor global optimization and low convergence speed. Inspired by the features of MHC (Major Histocompatibility Complex) in the biological immune system, a novel MHC-inspired antibody clone algorithm (MOAMHC) was proposed to solve the above problems. This algorithm preserves elitist antibody genes through the MHC strings that emulate the MHC haplotype in order to improve its local search capability. It enhances the antibody population diversity by gene mutation that mimics the MHC polymorphism and polygenism to improve its global search capability. The convergence of MOAMHC is theoretically proved. The experiments of MOAMHC on some multimodal mathematical functions and a practical malicious code detector optimization problem are carried out. The proposed algorithm shows competitive results with improved diversity and convergence. It provides new opportunities for solving previously intractable function optimization problems.