KM-RDA: A New Meta-Heuristic Approach for Data Clustering Problem

Data Clustering is the process of allocating appropriate clusters to a given set of objects such that objects within a cluster are related to each other while no relation exists between the objects of different clusters. Clustering can be viewed as an optimization problem where the main goal is to find the optimal cluster centroids. The K-Means method is among the oldest and widely utilized methods that are used to deal with this problem. Additionally, meta-heuristic algorithms are also combined with k-means algorithm in past for better results. This work combines recently introduced swarm intelligence based meta-heuristic algorithm red deer algorithm (RDA) with traditional k-means algorithm to address data clustering issue. The proposed work aims at solving the data clustering problem more effectively and efficiently. A number of benchmark clustering datasets are used to assess the effectiveness of the proposed algorithm, and the outcomes are contrasted with standard clustering metrics. The finding indicates that the proposed algorithm surpasses other algorithms in terms of clustering results.