MMEATC: A Multimodal Multiobjective Evolutionary Algorithm with Three Clustering Mechanisms

To tackle the challenge of maintaining population diversity in the decision space for multimodal multiohjective optimization prohlems (MMOPs), this paper introduces a novel mating selection strategy based on kernel K-means clustering. By leveraging the ability of kernel K-means to identify solution clusters within complex decision spaces, the proposed method enhances the exploration of promising parent solutions during the mating selection process. This method, combined with the environmental selection approach used in MMOEA/DC, led to the development of a novel algorithm called Multimodal Multiobjective Evolutionary Algorithm with Three Clustering mechanisms, termed as MMEATC. To evaluate the effectiveness of MMEATC, we compare MMEATC against five state-of-the-art multimodal multiobjective evolutionary algorithms: MMOEA/DC, MO_Ring_PSO_SCD, TriMOEA-TA&R, MMEA-WI, and CoMMEA. Extensive experimental results show that MMEATC achieves competitive performance, highlighting its potential as an effective approach to solving MMOPs.