An Improved Hybrid Clustering Algorithm Based on Particle Swarm Optimization and K-means
Shuying Liu, Yanfei Zou · IOP Conference Series Materials Science and Engineering · 2020
Abstract The most common algorithm in data mining is cluster analysis. Cluster analysis algorithm has been widely used in many fields, especially in data analysis, market research and pattern recognition. K-means clustering algorithm(KMCA), as one of the common algorithms in clustering analysis, occupies an important position in clustering analysis and has relatively more applications. However, in recent years, with the deepening of the application of clustering analysis algorithm, it is found that there are a series of problems in KMCA, which directly affect the accuracy of data analysis results. On this basis, a bionic optimization algorithm, particle swarm optimization algorithm, is generated, which makes up for the shortcomings of KMCA. The aim of this paper is to establish the optimal algorithm for data analysis by means of the research on the improved hybrid clustering algorithm of particle swarm optimization and k-means. The experimental results show that the algorithm can effectively integrate the advantages of particle swarm optimization algorithm and KMCA, which not only improves the speed of the algorithm, but also guarantees the accuracy of the results.