This paper presentes a new hybrid classifier based on the combination of rough set theory and RBF neural network. Experimental results show that the algorithm Rough-RBF is effective for the texts classification, and has the better performance in classification precision, stability and fault-tolerance comparing with the traditional classification methods, Bayesian classifiers SVM and kNN, especially for the complex classification problems with many feature vectors.
白如江 . 基于粗糙集和RBF神经网络的文本自动分类方法[J]. 现代图书情报技术, 2006, 1(6): 47-51.
Bai Rujiang . A Hybrid Classifier Based on the Rough Sets and RBF Neural Networks. New Technology of Library and Information Service, 2006, 1(6): 47-51.
1施洁斌.基于概率神经网络的文本自动分类研究.情报学报,2004 ,23(2) :147-151
2Pawalk Z. Rough sets . International Journal of Computer and Information Science ,1982 ,11(5) : 341-356
3Pawalk Z. Rough sets : theoretical aspects of reasoning about data. Norwell: Kluwer Academic Publishers ,1991
4Skowron A. Rough Sets and Boolean Reasoning. New York : PhysicalVerlag ,2001. 95-124
5Ziako W. Rough sets : trends , challenges , and prospects. Rough Sets and Current Trends in Computing .Berlin : Springer Verlag ,2001. 1-7
6赵群,保铮. 径向基函数神经网络的分类机理. 通信学报,1996 ,17 (2) :31234
7李斗,李弼程.一种神经网络文本分类器的设计与实现.计算机工程与应用,2005(17):107-109
8郝占刚,王正欧.基于潜在语义索引和遗传算法的文本特征提取方法.情报科学,2006(1):104-107
9Ahn B S , Cho S S , Kim C. The integrated methodology of rough set theory and artificial neural network for business failure prediction. Expert Systems with Applications , 2000 ,18 (2) :65 - 74
10张建宝,慈林林,赵宗涛. RBF 网络分类器的实现及应用. 计算机工程与科学,2001 ,23 (6) :18-22
11David Hand著,张银奎译.数据挖掘原理.北京:机械工业出版社,2003