〔摘要〕首先提出一种基于模糊向量空间模型和径向基函数网络的文本自动分类方法,该网络由输入层、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 ；其次，构造更详细的算法推导及实施方案 ；最后，以中国期刊网全文数据库部分文档数据为例，对该方法的有效性进行验证，结果表明该方法分类效果较好。
〔关键词〕数据挖掘 特征提取 神经网络 文本分类
Research and Implementation of Text Classification Method Based on Fuzzy Vector Space Model and RBF Neural Network
Daqing Petroleum Institute Library, Daqing 163318
〔Abstract〕A classification method based on fuzzy vector space model and radial basis function network is presented in this paper. The network includes input layer, hidden layer and output layer. Input layer performs import of samples, hidden layer extracts model characters of samples and output layer presents classification results. The information of its locality in the document is considered while the keywords of model characters are extracted. The classification results of this method are more precise than that of general method because fuzzy eigenvectors are applied. Finally the availability of model and algorithms is proved by the classification of some documents in China periodical document database.
〔Keywords〕data mining characters extraction neural network document classification ......