Adaptive immune genetic algorithm for logic circuit design
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
ICES'07 Proceedings of the 7th international conference on Evolvable systems: from biology to hardware
Hi-index | 0.00 |
Evolutionary design of circuits (EDC) is an important branch of evolvable hardware (EHW). It is proved to be able to provide more optimized and diversified designs of circuit than human designs. An Orthogonal Immune Genetic Algorithm (OIGA) is proposed in this paper to improve the speed and efficiency of analog circuit design. Several factors, including the orthogonal initialization, the cloning selection operator, the hyper mutation operator, and the immune memory operator, are incorporated in the operation of OIGA. This algorithm makes use of the orthogonal design to select initialization population in order to preserve the diversity in the feasible solution space. The proposed algorithm is applied in the design of filter circuit. The simulation results show that OIGA can find the optimal solutions. The performance of the OIGA is compared with the Adaptive Immune Genetic Algorithm (AIGA) in optimizing a filter circuit. The results show that the OIGA is effective in improving the converging speed and the efficiency of the analog circuit design.