This paper proposes a WD-GA-LSSVM model for predicting the displacement of a deepseated landslide triggered by seasonal rainfall,in which wavelet denoising(WD)is used in displacement time series of landslide to elimin...This paper proposes a WD-GA-LSSVM model for predicting the displacement of a deepseated landslide triggered by seasonal rainfall,in which wavelet denoising(WD)is used in displacement time series of landslide to eliminate the GPS observation noise in the original data,and genetic algorithm(GA)is applied to obtain optimal parameters of least squares support vector machines(LSSVM)model.The model is first trained and then evaluated by using data from a gentle dipping(~2°-5°)landslide triggered by seasonal rainfall in the southwest of China.Performance comparisons of WD-GA-LSSVM model with Back Propagation Neural Network(BPNN)model and LSSVM are presented,individually.The results indicate that the adoption of WD-GA-LSSVM model significantly improves the robustness and accuracy of the displacement prediction and it provides a powerful technique for predicting the displacement of a rainfall-triggered landslide.展开更多
The authors present an algorithm which is a modilication of the Nguyen-Stenle greedy reduction algorithm due to Nguyen and Stehle in 2009. This algorithm can be used to compute the Minkowski reduced lattice bases for ...The authors present an algorithm which is a modilication of the Nguyen-Stenle greedy reduction algorithm due to Nguyen and Stehle in 2009. This algorithm can be used to compute the Minkowski reduced lattice bases for arbitrary rank lattices with quadratic bit complexity on the size of the input vectors. The total bit complexity of the algorithm is O（n^2·（4n!）^n·（n!/2^n）^n/2·（4/3）^n（n-1）/2）.log^2 A）where n is the rank of the lattice and A is maximal norm of the input base vectors. This is an O（log^2 A） algorithm which can be used to compute Minkowski reduced bases for the fixed rank lattices. A time complexity n!. 3n（log A）^O（1） algorithm which can be used to compute the successive minima with the help of the dual Hermite-Korkin-Zolotarev base was given by Blomer in 2000 and improved to the time complexity n!- （log A）^O（1） by Micciancio in 2008. The algorithm in this paper is more suitable for computing the Minkowski reduced bases of low rank lattices with very large base vector sizes.展开更多
基金supported by the Chinese National Natural Science Foundation (Grant No. 41502293)the National Basic Research Program (973 Program) (Grant No. 2014CB744703)the Funds for Creative Research Groups of China (Grant No. 41521002)
文摘This paper proposes a WD-GA-LSSVM model for predicting the displacement of a deepseated landslide triggered by seasonal rainfall,in which wavelet denoising(WD)is used in displacement time series of landslide to eliminate the GPS observation noise in the original data,and genetic algorithm(GA)is applied to obtain optimal parameters of least squares support vector machines(LSSVM)model.The model is first trained and then evaluated by using data from a gentle dipping(~2°-5°)landslide triggered by seasonal rainfall in the southwest of China.Performance comparisons of WD-GA-LSSVM model with Back Propagation Neural Network(BPNN)model and LSSVM are presented,individually.The results indicate that the adoption of WD-GA-LSSVM model significantly improves the robustness and accuracy of the displacement prediction and it provides a powerful technique for predicting the displacement of a rainfall-triggered landslide.
基金supported by the National Natural Science Foundation of China (No.10871068)the Danish National Research Foundation and National Natural Science Foundation of China Joint Grant (No.11061130539)
文摘The authors present an algorithm which is a modilication of the Nguyen-Stenle greedy reduction algorithm due to Nguyen and Stehle in 2009. This algorithm can be used to compute the Minkowski reduced lattice bases for arbitrary rank lattices with quadratic bit complexity on the size of the input vectors. The total bit complexity of the algorithm is O（n^2·（4n!）^n·（n!/2^n）^n/2·（4/3）^n（n-1）/2）.log^2 A）where n is the rank of the lattice and A is maximal norm of the input base vectors. This is an O（log^2 A） algorithm which can be used to compute Minkowski reduced bases for the fixed rank lattices. A time complexity n!. 3n（log A）^O（1） algorithm which can be used to compute the successive minima with the help of the dual Hermite-Korkin-Zolotarev base was given by Blomer in 2000 and improved to the time complexity n!- （log A）^O（1） by Micciancio in 2008. The algorithm in this paper is more suitable for computing the Minkowski reduced bases of low rank lattices with very large base vector sizes.
