Orchestra Clustering based on Partitions for Large Datasets Using Maximum Voting Process with K-Means, K-Medoids, and DBSCAN

with the increasing size of datasets in various fields such as communications, healthcare, and finance, the need for scalable clustering algorithms has become crucial.Traditional clustering algorithms face challenges when applied to large datasets due to high computational costs and memory usage.In this paper, an Orchestra Clustering based on partitions approach using a maximum voting process, leveraging three wellknown clustering algorithms: K-Means, K-Medoids, and DBSCAN.In the first stage, each of these algorithms independently partitions the dataset.In the second stage, the maximum voting process is applied to assign each instance of data to the cluster that receives the maximum votes from the three algorithms.The proposed method is evaluated on the Higgs Boson dataset, and results demonstrate that the Orchestra approach outperforms individual algorithms in terms of clustering accuracy and execution time.