基于粒子群优化最小二乘向量机的地震预测模型

Earthquake Forecast Model Based on the Partical Swarm Optimization Algorithm Used in LSSVM

摘要:

为解决地震预测中最小二乘向量机(LSSVM)模型的参数难以确定的问题,利用粒子群算法(PSO)的收敛速度快和全局优化能力,优化LSSVM模型的惩罚因子和核函数参数,建立了PSO-LSSVM地震预测模型。通过对地震实例的预测仿真及其相关分析表明该方法的有效性。该方法优于传统的神经网络和支持向量机的地震预测方法,可以有效提高预测效能。

Abstract:

In order to overcome the problem of the uncertain parameters in LSSVM model, the PSO-LSSVM prediction model concerning earthquake forecast is developed, which is based on the particle swarm optimization algorithm with abilities of fast convergence and global optimization. The simulation results show that the proposed method is an effective tool for the prediction of earthquake, and it can effectively enhance the prediction accuracy compared with the way using neural network and support vector machine model.