计算机技术与发展Issue(10)：80-82,86,4.DOI:10.3969/j.issn.1673-629X.2013.10.020
基于优化的多核学习方法的Web文本分类的研究
Research of Web Document Classification Based on Optimized Multiple Kernel Learning Method
摘要
Abstract
Web document classification has been considered as an important research field in data mining,it's necessary to improve the performance of technique of Web document classification for quickly retrieving the documents from the massive information spread all o-ver the network. Multiple-kernel learning is a focus in current machine learning community,which is able to develop the capability of classification and learning extension,while kernel method is one of effective approaches for solving high dimension and non-linear pattern analysis. By using the advantage of multiple kernel can boost interpretability of decision function and obtain better performance. In this paper,propose a Web document classification based on multiple kernel learning after a research of a SVM based on multiple kernel learn-ing. According to the result of the experiment,this approach presented in this paper has high efficiency and more accurate rate compared with simple consistent combination multiple kernel learning method.关键词
支持向量机/数据挖掘/多核学习/Web文本分类Key words
SVM/data mining/multiple kernel learning/Web document classification分类
信息技术与安全科学引用本文复制引用
江伟,潘昊..基于优化的多核学习方法的Web文本分类的研究[J].计算机技术与发展,2013,(10):80-82,86,4.基金项目
湖北省自然科学基金(2011CDB257) （2011CDB257）
