首页    期刊浏览 2024年11月10日 星期日
登录注册

文章基本信息

  • 标题:Improved Correlation Preserved Indexing For Text Mining
  • 本地全文:下载
  • 作者:Vinnarasi Tharania. I ; M.Kanchana ; V.Kavitha
  • 期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
  • 印刷版ISSN:2320-9798
  • 电子版ISSN:2320-9801
  • 出版年度:2014
  • 卷号:2
  • 期号:1
  • 出版社:S&S Publications
  • 摘要:Data mining is an excellent domain to work where new concepts are implemented. Theknowledge extraction and knowledge discovery is a major task of engineering organization. Therefore a newfield of study, Knowledge Discovery in Database (KDD), and data mining is explored. And many applicationsare been developed. In this paper a discussion about field of data mining is also placed. Document clustering is afield where we are implementing a concept of grouping of similar objects. Some groups are formed and thedocuments are placed under those groups. The main motive of this paper is comparison of various algorithmsand giving the best result of the clustering. A new algorithm has been proposed in this paper is ICPI (Improvedcorrelation preserving indexing) which is performed by the correlation similarity measure space. ICPI cansuccessfully find out the essential structures rooted in high dimensional document space. The proposed work isto provide an efficient text mining algorithm to perform mining in the document.ICPI can successfully find outessential structures rooted in high dimensional document space.
  • 关键词:K-means; Latent Semantic Indexing (LSI); Locality Preserving Indexing (LPI); Correlation;Preserving Indexing (CPI); Improved Correlation Preserving Indexing (ICPI); Knowledge Discovery in;Database (KDD).
国家哲学社会科学文献中心版权所有