Title :
Feature selection based on the feature space class separability criterion
Author :
Liang, Siyang ; Li, Ming ; Liang, Guanhui ; Gao, Qing
Author_Institution :
Beijing Inst. of Technol., Beijing, China
Abstract :
Aimed at the imbalance of training samples, isolated points, and the importance degree of class samples of different three questions, this paper put forward a improvement weighted support vector machine (SVM), and give the method of determine the integrated weights, the simulation results show the effectiveness of the method.
Keywords :
feature extraction; pattern classification; support vector machines; training; SVM; feature selection; feature space class separability criterion; integrated weights method; isolated points; support vector machine; training samples; Accuracy; Optimization; Simulation; Support vector machine classification; Training; Vectors; class separability criterion; feature space; joint optimization; support vector machine;
Conference_Titel :
Systems and Informatics (ICSAI), 2012 International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4673-0198-5
DOI :
10.1109/ICSAI.2012.6223093
