Title :
Sample reduction based on kernel squared Mahalanobis distance for support vector machines
Author :
Zou, Xiao-Lin ; Liu, Xiao-Zhang
Author_Institution :
Fac. of Math. & Inf. Sci., Zhaoqing Univ., Zhaoqing, China
Abstract :
This paper presents a sample reduction algorithm based on kernel squared Mahalanobis distance, as a sampling preprocessing for SVM training to improve the scalability. Experimental results show that, the proposed algorithm is effective for reducing training samples for nonlinear SVMs.
Keywords :
sampling methods; support vector machines; kernel squared Mahalanobis distance; nonlinear SVM; sample reduction algorithm; sampling preprocessing; support vector machine; Computer applications; Covariance matrix; Kernel; Modeling; Support vector machines; Symmetric matrices; Training;
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
DOI :
10.1109/ICCASM.2010.5623208
