Analysis of Data using hybridized K-means clustering with PSO-JAYA algorithm

Despite decades of intensive study on grouping for small to medium-sized data sets, research into huge data clustering is gaining more and more attention from both business and academia. Contrary to clustering algorithms on small and large amounts of data, big data grouping requires more processing power and resources to handle the massive data retention and complex analysis of data. This research suggests an optimal method for data clustering to address this problem. In addition to the combined model of Particle Swarm Optimization and JAYA Approach, this strategy used the idea of K-means clustering to initiate the search for optimal clusters. The simulations are run using a Python program using the Pendigits dataset. The efficacy of the scheme is shown when compared to current state-of-the-art methodologies by analyzing the simulation outcomes in terms of NMI and FMI score.