The Data Mining Technology of Particle Swarm Optimization Algorithm in Earthquake Prediction

Abstract

Data mining technology based on the particle swarm optimization algorithm applied in earthquake prediction was presented. Making use of the characteristics of abnormally high-dimensional data of earthquake precursor, this paper studies an earthquake prediction model based on the Particle Swarm Optimization Clustering Algorithm. This model analyzes the relationship between earthquake precursor data and earthquake magnitude. Inputs are 14 abnormal indexes such as belt, seismic gap and short leveling, and output is earthquake magnitude classification. The cluster average-distance is set as the evaluation function of the Particle Swarm Optimization Algorithm. The experimental results indicate that, this model can effectively and validly predict the earthquake magnitude in accordance with the earthquake precursor data. Compared with the traditional clustering k-means Algorithm model, this stability is stronger, and the correctness of forecast is much higher. Through the research and analysis of the example of history source seismic data, the model of this paper is one of approaches to improve the efficiency of earthquake forecast.