Title :
New smooth support vector machine for regression
Author_Institution :
Coll. of Sci., China Jiliang Univ., Hangzhou, China
Abstract :
Researching smooth support vector machine for regression (SSVR) is an active field in data mining. In this study, a new method that multiple knot spline function is used to make smooth the model of support vector machine for regression is presented. A Multiple Knot Spline SSVR (MKS-SSVR) is obtained. Moreover, by analyzing the function precision, MKS-SSVR is better than SSVR and PSSVR.
Keywords :
data mining; regression analysis; splines (mathematics); support vector machines; MKS-SSVR; data mining; function precision; multiple knot spline function; smooth support vector machine for regression; Abstracts; Convergence; Kernel; Regression; Smoothing; Support vector machine;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2012 International Conference on
Conference_Location :
Xian
Print_ISBN :
978-1-4673-1484-8
DOI :
10.1109/ICMLC.2012.6358931
