Domain density description for multiclass pattern classification with reduced computational load

作     者：Kang, Woo-Sung Choi, JinYung 

作者机构：Seoul Natl Univ Sch Elect & Comp Engn Kwanak Ku Seoul 151744 South Korea Seoul Natl Univ Seoul 151600 South Korea 

出 版 物：《PATTERN RECOGNITION》 (图形识别)

年 卷 期：2008年第41卷第6期

页      面：1997-2009页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：multiclass pattern classification computational load reduction support vector learning 

摘      要：We propose a novel classification method that can reduce the computational cost of training and testing for multiclass problems. The proposed method uses the distance in feature space between a test sample and high-density region or domain that can be described by support vector learning. The proposed method shows faster training speed and has ability to represent the nonlinearity of data structure using a smaller percentage of available data sample than the existing methods for multiclass problems. To demonstrate the potential usefulness of the proposed approach, we evaluate the performance about artificial and actual data. Experimental results show that the proposed method has better accuracy and efficiency than the existing methods. (C) 2007 Elsevier Ltd. All rights reserved.