Title :
Climate model by SVM based on experienced knowledge in tobacco region division
Author :
Deji, Wang ; Bo, Xu ; Guangcai, Li ; Guoqun, Chen ; Bingyu, Sui
Author_Institution :
Training Centre of Nat. Tobacco Monopoly Bur., Zhengzhou, China
Abstract :
Tobacco region division is vital to improve the quality of the tobacco. And the climate model is the most important factor for the division. However, the climate variable, which was strongly corrupted by noises or fluctuations, can not be reconstructed by common method. In order to improve the performance of regression, the experienced knowledge about climate variable is incorporated in the training of SVM. The experimental results demonstrate the effectiveness and efficiency of our approach.
Keywords :
support vector machines; tobacco industry; climate model; experienced knowledge based SVM; experienced knowledge based support vector machines; tobacco region division; Biological system modeling; Cities and towns; Kernel; Meteorology; Monopoly; Neural networks; Pipelines; Research and development; Support vector machine classification; Support vector machines; Climate Model; Experienced Knowledge; SVM; Tobacco Region Division;
Conference_Titel :
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location :
Guilin
Print_ISBN :
978-1-4244-2722-2
Electronic_ISBN :
978-1-4244-2723-9
DOI :
10.1109/CCDC.2009.5192581
