基于模糊VSM和RBF网络的文本分类方法  

Document classification method based on fuzzy vector space model and RBF neural network

作　　者：许少华[1] 李小红[1] 潘俊辉[1] 

机构地区：[1]大庆石油学院计算机科学与工程学院,黑龙江大庆163318

出　　处：《计算机工程与设计》2007年第1期145-148,共4页Computer Engineering and Design

摘　　要：针对文本自动分类问题,提出了一种基于模糊向量空间模型和径向基函数网络的分类方法。网络由输入层、隐层和输出层组成。输入层完成分类样本的输入,隐层提取输入样本所隐含的模式特征,将分类结果在输出层表现出来。该方法在特征提取时充分考虑了特征项在文档中的位置信息,构造出模糊特征向量,使自动分类更接近手工分类方法。以中国期刊网全文数据库部分文档数据为例验证了该方法的有效性。Aimed at the problems of document automatic classification, a classification method is proposed based on fuzzy vector space model and RBF network. The network is constituted of input layer, hidden layer and output layer. The input layer performs classification samples provided, hidden layer extracts the implicit pattern characters of input samples. Give classification results at output layer. The information of its locality in the text is considered while the features are extracted and the fuzzy characteristic vector is constructed, as a result, the automatic categorization principle is close to the manual categorization method. Finally the availability of the model and algorithms is proved by the documents of china periodical document database.

关 键 词：数据挖掘 特征提取 神经网络 文本分类 模糊特征向量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]