An algorithm to identify clusters of solutions in Multimodal Optimisation

摘要: Clustering can be used to identify groups of similar solutions in Multimodal Optimisation. However, a poor clustering quality reduces the benefit this application. The vast majority methods literature operate by resorting priori assumptions about data, such as number cluster or radius. Clusters are forced conform these assumptions, which may not valid for considered population. latter have huge negative impact on quality. In paper, we apply method that does require knowledge. We demonstrate effectiveness and efficiency real synthetic data sets emulating Optimisation problems.