Big Data Clustering Method Based on an Improved PSO-Means Algorithm

There are problems in big data clustering processing, such as poor clustering effect of different types of data and long clustering time. Therefore, a big data clustering processing method based on the improved PSO-Means (Particle Swarm Optimization Means) algorithm is proposed. This method uses the particle swarm algorithm to determine the flight time and flight direction of the unit particle in a clustering process, pre-sets the selection range of the initial clustering center, and appropriately adjusts the inertia weight of the unit particle to eliminate the clustering defects caused by particle oscillation, and successfully obtains the clustering center based on large-scale data. Combined with the spanning tree algorithm, the PSO algorithm is optimized from two aspects: sample deviation and centroid skewness, and the optimized clustering center is input into the -means clustering algorithm to realize big data clustering processing. Experimental results show that the improved PSO-Means method can effectively cluster different types of data, and the clustering time is only 0.3 s, which verifies that this method has good clustering performance and clustering efficiency.