AN IMPROVED MULTI-LABEL CLASSIFICATION METHOD BASED ON SVM WITH DELICATE DECISION BOUNDARY

Multi-label classification problem is an extension of traditional multi-class classification problem in which the classes are not mutually exclusive and each sample may belong to several classes simultaneously. Such problems occur in many important applications. Some researches indicate that the performance of classifier can be improved by introducing the information of multi-label training samples into learning procedure effectively. In this paper, we propose a novel method based on SVM with delicate decision boundary. For the basic overlapping problem of two labels, characteristics of double-label samples are utilized to obtain the range of overlapping sample space decided by two binary SVM classifier separating surfaces. And a bias model with delicate decision boundary is built for samples in overlapping sample space to improve the classification accuracy. Experimental results on the benchmark datasets of Yeast and Scene show that our proposed method improves the classification accuracy efficiently, compared with the basic binary SVM method and some existing well-known methods.