Forest Fire Disaster Area Prediction Based on Genetic Algorithm and Support Vector Machine

被引:6
作者
Xiao, Fang [1 ]
机构
[1] NE Forestry Univ, Sch Forestry, Harbin 150040, Peoples R China
来源
TRENDS IN CIVIL ENGINEERING, PTS 1-4 | 2012年 / 446-449卷
关键词
support vector machine; parameter optimization; time series; forest fire disaster area;
D O I
10.4028/www.scientific.net/AMR.446-449.3037
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Forest fire disaster area prediction based on genetic algorithm and support vector machine is presented in the paper. Genetic algorithm is used to select appropriate parameters of support vector machine. Genetic algorithm can obtain the optimal solution by a series of iterative computations. The forest fire disaster area data in Jiangxi Province from 1970 to 1997 are used as our research data. The comparison of the forest fire disaster area forecasting results between the proposed GA-SVM model and the SVM model is given,which indicates that the proposed GA-SVM model has more excellent forest fire disaster area forecasting results than the SVM model.
引用
收藏
页码:3037 / 3041
页数:5
相关论文
共 4 条
[1]   Development of a genetic algorithm for component placement sequence optimization in printed circuit board assembly [J].
Hardas, Chinmaya S. ;
Doolen, Toni L. ;
Jensen, Dean H. .
COMPUTERS & INDUSTRIAL ENGINEERING, 2008, 55 (01) :165-182
[2]  
Katayama K, 2003, MATH COMPUT MODEL, V38, P1275, DOI 10.1016/S0895-7177(03)00340-6
[3]   Optimal reduction of solutions for support vector machines [J].
Lin, Hwei-Jen ;
Yeh, Jih Pin .
APPLIED MATHEMATICS AND COMPUTATION, 2009, 214 (02) :329-335
[4]   A parallel solver for large quadratic programs in training support vector machines [J].
Zanghirati, G ;
Zanni, L .
PARALLEL COMPUTING, 2003, 29 (04) :535-551