A New Regression Method Based on SVM Classification
SVM (Support Vector Machines) is a novel algorithm of machine learning which is based on SLT (Statistical Learning Theory). It can solve the problem characterized by nonlinear, high dimension, small sample and local minimizing perfectly. For non-linear problem, the forecasting technique of FCTR (First classification, then regression) was proposed, based on the classification approach of SVM and has carried on the simulation experiment. The experiment shows that the fitting value which obtains using the return to first would be more precise than directly. Using this method to food production forecast, its accuracy is superior to other production forecasting methods.
support vector machines (SVM) first classification then regression (FCTR) forecast
DONG Yi CHENG Wei LI Shengfeng
Institute of Applied Mathematics, Bengbu College,Bengbu, China School of Management, Hefei Univ. of Key Lab. of Intelligent Computing & Signal Processing,Anhui University, Hefei, China Anhui Vocationa Institute of Applied Mathematics, Bengbu College, Bengbu, China
国际会议
上海
英文
796-799
2011-07-26（万方平台首次上网日期，不代表论文的发表时间）