一种基于邻域粗糙集的多标记加权分类算法  

A MULTI- LABEL WEIGHTED CLASSIFICATION ALGORITHM BASED ON NEIGHBORHOOD ROUGH SETS

作　　者：马文[1,2] 计华[1,2] 

机构地区：[1]山东师范大学信息科学与工程学院,济南250014 [2]山东省分布式计算机软件新技术重点实验室,济南250014

出　　处：《山东师范大学学报（自然科学版）》2015年第4期30-33,共4页Journal of Shandong Normal University(Natural Science)

基　　金：国家自然科学基金资助项目（61170145）;教育部高等学校博士点专项基金资助项目（20113704110001）;山东省自然科学基金资助项目（ZR2010FM021）;山东省科技攻关计划项目（2013GGX10125）.

摘　　要：多标记分类问题在文本分类、图像标注和基因功能组学习等领域都有很好的应用前景．考虑到多标记分类问题中的不确定性和相关性问题，引入了邻域粗糙集模型来构造一种新的框架MLRS．但该方法忽略了邻域中样例与测试样例之间的局部相关性，针对该问题，提出一种新的加权多标记分类算法WMLRS．实验表明，本文提出的方法拥有比其他常用的多标记分类算法更优的分类性能．Multi -label classification problems have a good application prospect in the areas such as text classification, image annotation and gene functional group learning, etc. Neighborhood rough set model can be introduced to construct a new framework called MLRS by considering the uncertainty and correlation questions in multi -label classification problems. But this algorithm ignored the local correlation between the labels of the test examples and their k - nearest neighbors. To cover this defect, this paper proposed a new algorithm called WMLRS algorithm. Experimental results show that the proposed approach WMLRS works better than other commonly used multi - label algorithms.

关 键 词：多标记分类 邻域粗糙集 不确定性 K近邻 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]