Title :
Application of Improved SVR Model in Ecological Economy Prediction
Author :
Yan Li;Yuening Long
Author_Institution :
Sch. of life Sci., Yunnan Univ., Kunming, China
Abstract :
Principle of support vector regression method is investigated. Genetic algorithm is adopted to search the optimal SVR parameters to improve the generalization performance of SVR. Then an improved SVR method based on intelligent computing is put forward. At last, the proposed method is used in the prediction of ecological tourism economy. Different kernel functions are used for training data, and the performance of the prediction is compared. The predictive effect of RBF kernel function is significantly better than that of the polynomial kernel function. The proposed method can provide important reference for the development of ecological tourism economy.
Keywords :
"Support vector machines","Kernel","Genetic algorithms","Prediction algorithms","Biological system modeling","Testing","Urban areas"
Conference_Titel :
Intelligent Systems Design and Engineering Applications (ISDEA), 2015 Sixth International Conference on
DOI :
10.1109/ISDEA.2015.48