Title :
A Modified Self-Training Semi-supervised SVM Algorithm
Author :
Jin, Yun ; Ma, Yong ; Zhao, Li
Author_Institution :
Sch. of Phys. & Electron. Eng., Xuzhou Normal Univ., Xuzhou, China
Abstract :
In this paper, we present a modified self-training semi-supervised SVM algorithm. In order to demonstrate its validity and effectiveness, we carry out some experiments which prove that our method is better than the former algorithm. Using our modified self-training semi-supervised SVM algorithm, we can save much time for labeling the unlabelled data.
Keywords :
data handling; learning (artificial intelligence); pattern classification; support vector machines; SVM algorithm; modified self-training semi-supervised learning; support vector machine; unlabelled data; Classification algorithms; Convergence; Data models; Iris recognition; Optimization; Support vector machines; Training; SVM; UCI; self-training; semi-supervised learning;
Conference_Titel :
Communication Systems and Network Technologies (CSNT), 2012 International Conference on
Conference_Location :
Rajkot
Print_ISBN :
978-1-4673-1538-8
DOI :
10.1109/CSNT.2012.56
