首页 | 本学科首页   官方微博 | 高级检索  
     

基于相空间重构和最小二乘支持向量机的滑坡预测
引用本文:刘清山,汤俊.基于相空间重构和最小二乘支持向量机的滑坡预测[J].浙江水利水电专科学校学报,2010,22(2):55-57.
作者姓名:刘清山  汤俊
作者单位:1. 浙江省水利水电勘测设计院,浙江,杭州,310000
2. 东华理工大学资环系,江西,南昌,330013
摘    要:针对滑坡位移时间序列的非线性特性,引入基于相空间重构和最小二乘支持向量机(LSSVM)的预测法.利用Cao氏方法确定嵌入维数,根据互信息法计算最佳延迟时间;然后在相空间中,利用最小二乘支持向量机(LSSVM)建立预测模型.试验结果表明,模型具有较高的精度,是科学可行的.

关 键 词:相空间重构  最小二乘支持向量机  滑坡预测

Landslide Prediction Based on Phase Space Reconstruction and LSSVM
LIU Qing-shan,TANG Jun.Landslide Prediction Based on Phase Space Reconstruction and LSSVM[J].Journal of Zhejiang Water Conservancy and Hydropower College,2010,22(2):55-57.
Authors:LIU Qing-shan  TANG Jun
Affiliation:1.Zhejiang Design Institute of Water Conservancy and Hydropower,Hangzhou 310000,China;2.Resources and Environmental Engineering Dept.of East China Institute of Technology,Nanchang 330013,China)
Abstract:In view of the nonlinear characteristics of landslide displacement time sequence,the prediction method based on phase space reconstruction and least squares support vector machine(LSSVM) is introduced in the essay.The best delay time is computed according to mutual information method and Cao's method to determine the embedding dimension.Therefore,the forecast model is established in the phase space,by using least squares support vector machine(LSSVM).The test results show that the model is scientific and feasible with high precision.
Keywords:phase space reconstruction  least squares support vector machine  landslide prediction
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号