A New Particle Swarm Optimization Algorithm for Optimizing Big Data Clustering
Clustering is an ideal tool for working with big data and searching for structures in the data set. Clustering aims at maximizing the similarity between the data within a cluster and minimizing the similarity between the data between different clusters. This study presents a new and improved Particle Swarm Optimization (PSO) algorithm using pattern reduction and reducing the clustering calculation time with Multistart Pattern Reduction-Enhanced PSO (MPREPSO). This method adds two pattern reduction operators and multistart operators into the PSO algorithms. The goal of the pattern reduction operator is to reduce the computational time from the compression of static patterns. The purpose of the multistart operator is to avoid falling into the local optimal by enforcing diversity in the population. Two pattern reduction and multistart operators are combined with the PSO algorithm to evaluate the performance of this method.
Hashemi, Seyed Emadedin; Tavana, Madjid; and Bakhshi, Maryam, "A New Particle Swarm Optimization Algorithm for Optimizing Big Data Clustering" (2022). Business Systems and Analytics Faculty Work. 19.