SVM in the Sand-Dust Storm Forecasting

Author

Lu, Zhi-ying ; Zhang, Qi-meng ; Zhao, Zhi-chao

Author_Institution

Sch. of Electr. Eng. & Autom., Tianjin Univ.

fYear

2006

fDate

13-16 Aug. 2006

Firstpage

3677

Lastpage

3681

Abstract

A novel method of the support vector machine (SVM) is proposed in the sand-dust storm-forecasting model. The development of the model includes pre-treating original data by using principal component analysis (PCA), choosing a kernel function (i.e. the radial basic function (RBF) kernel), defining the search region of (C, sigma²) by analyzing the influence on SVM classifier of the regularization parameter and the kernel parameter, and optimizing the two parameters (C, sigma²) by using grid search in the search region. The result of the experiment shows that this SVM method has better performances than the improved back-propagation neural network (BPNN) method in terms of stability, correct classification and the running speed

Keywords

backpropagation; forecasting theory; neural nets; principal component analysis; support vector machines; SVM classifier; back-propagation neural network method; principal component analysis; radial basic function kernel; regularization parameter; sand-dust storm forecasting model; support vector machine; Automation; Cybernetics; Economic forecasting; Kernel; Machine learning; Neural networks; Predictive models; Principal component analysis; Stability; Storms; Support vector machine classification; Support vector machines; BPNN; PCA; SVM; sand-dust storm forecast;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2006 International Conference on

Conference_Location

Dalian, China

Print_ISBN

1-4244-0061-9

Type

conf

DOI

10.1109/ICMLC.2006.258625

Filename

4028709