A Chaos Search for Multi-Objective Memetic Algorithm


In this research, the efficacy improvement of Multi-Objective Memetic Algorithms (MOMAs) was studied. For this matter, a Local Search referred to as Chaos Search is incorpor ated with the MOMA to achieve a better search result. The resulting method is called Multi-Objective Chaos Memetic Algorithm (MOCMA). In this research, such technique is applied to solve Multi-Objective equations i.e., DTLZ 1-4 ty pe 2 objectives. The resulted outcomes will then be measured for their capabilities to find out the best outcome group in 2 aspects, namely the capability to converge to the true outcome and the capability to spread the out come groups found. The capabilities of the technique are then compared with existing Multi-Objective genetic local search (MOGLS), a highly efficient Multi-Objective Memetic Algorithms. This research shows that the Convergence Measurement of MOCMA process has a better rate of convergence than that of MOGLS. Also the Spread Measurement of MOCMA is scattered more evenly than that of MOGLS. It can be seen that the value of MOCMA’s capability measurement in both aspects are closer to 0 than those of MOGLS.