【摘要】 Web挖掘技术在商业上有广泛的应用前景,但现有的Web挖掘技术存在计算量大,精度不高等问题。论文提出的LSIWAC算法,首先运用潜在语义标引技术将Web页面词空间压缩到低维的特征空间;然后,在得到的特征空间上运用最优聚类将样本集合分为若干簇;对得到的每簇鉴别特征再利用最佳鉴别变换进行压缩和特征抽取,并用最终得到的特征矢量进行分类。该方法克服了样本高维效应,有效提高分类准确率,降低计算量。实验结果验证所提方法的有效性。更多还原

【Abstract】 Thought Web Mining has numerous commercial applications,there are many problems in it,for example,enor-mous computation and low precision etc.A new method,Web document automatic classification algorithm based on La-tent Semantic Indexing(LSIWAC),is present in this paper.First,LSIWAC uses the LSI based on Singular Value Decom-position(SVD)to compress the document vector space to lower dimensional space.Second,using the optimal clustering,LSIWAC cluster part of Web documents.Then,LSIWAC using the optimal discriminate transform,to get feature vector from every clustering’s discriminate features.Finally,uses the conception classification algorithm to classify the rest docu-ments.LSIWAC algorithm solves the high dimension problem and improves the precision of Web classification.Experiment results show that the novel method is effective.更多还原