LANDSLIDE DEFORMATION PREDICTION BASED ON WAVELETANALYSIS AND LEAST SQUARE SUPPORT VECTOR MACHINE
Li Xiao 1) ; and Xu Jinjun 2)
1)College of Civil Engineering and Urban Construction,Jiujiang University, Jiujiang 3320052)School of Geodesy and Geomatics, Wuhan University, Wuhan 430079
Abstract A novel model based on wavelet analysis and Least Square Support Vector Machine(LSSVM) for landslide deformation prediction is presented. Firstly,in the view of timefrequency analysis,through the wavelet transform,deformation time series is decomposed into components of different frequency and then the reconstructed approximate series and detailed series were predicted respectively by using LSSVM and the results were composed finally. The experimental results indicates that this prediction model has advantage over GM(1,1) ,AR and simple LSSVM as it has higher prediction accuracy and is applicable to predicting landslide deformation.
Li Xiao ,and Xu Jinjun . LANDSLIDE DEFORMATION PREDICTION BASED ON WAVELETANALYSIS AND LEAST SQUARE SUPPORT VECTOR MACHINE[J]. , 2009, 29(4): 127-130.
Li Xiao ,and Xu Jinjun . LANDSLIDE DEFORMATION PREDICTION BASED ON WAVELETANALYSIS AND LEAST SQUARE SUPPORT VECTOR MACHINE[J]. jgg, 2009, 29(4): 127-130.