Title :
Meteorological Prediction Using Support Vector Regression with Genetic Algorithms
Author :
Xue, Shengjun ; Yang, Ming ; Li, Chan ; Nie, Jing
Author_Institution :
Sch. of Comput. & Software, Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Abstract :
The theory of support vector regression (SVR) is introduced in this paper. And genetic algorithms (GAs) are adopted to optimize free parameters of support vector regression. Then we develop an optimal meteorological prediction model based on support vector Regression with genetic algorithms (SVRG). In this study, SVRG is applied to predict meteorology. The experimental results indicate that SVRG model proposed in this paper overcomes some shortcomings of the traditional SVR, and can achieve better forecasting accuracy and performance than traditional SVR and BP neural network (BPNN) prediction models. Consequently, the meteorological prediction model based on SVRG is an effective method.
Keywords :
backpropagation; forecasting theory; neural nets; regression analysis; support vector machines; weather forecasting; BP neural network; genetic algorithms; optimal meteorological prediction model; support vector regression; Atmospheric modeling; Genetic algorithms; Genetic engineering; Information science; Meteorology; Neural networks; Predictive models; Software; Vectors; Weather forecasting;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.735