| Data Mining is a new information technology that has been developed with the technology of Database and Artificial Intelligence, which integrates of Database, AI and Statistics and etc.It tries to extract the unknown, effective and useful knowledge from database. Web Mining is the traditional Data Mining technology application used in web, which can extract user's browse pattern and find the relative web pages from data (such as web log, web page content) on eb. Web Usage Mining mainly processes and analyses the web log data which is generally redundancy. Moreover the relations among the web pages are fuzzy and uncertain.Rough Sets theory is a soft computing tool dealing with vague, imprecise, uncertain and incomplete data. And Fuzzy Clustering Analysis is an analysis method of object through establishing fuzzy analogical relations based on the character, distance and similarity among objects. Web Usage Mining can get the interesting pattern from the log of websites, and apprehend the user's browse interest behavior, so as to improve the website's structure and provide individual services for the users.So the research into "Rough Sets Theory and Fuzzy Clustering Algorithm" is a research of theoretical significance and realistic value.Firstly, principle theories and methods of Data Mining, Web Data Mining, Rough Sets and Fuzzy Clustering Algorithm theory are introduced. Then method of Web Usage Mining and model of Web Log data are established through actual Web Log data. The page-user clustering's general model based on Fuzzy Clustering Algorithm is put forward as well. Furthermore, based on the educational administration's website of our university, the primal Web Log data is pretreated through the above theories. And reduction of the web pages are gained, which doesn't affect the analysis. Finally, the result which is got through fuzzy equivalence matrix and fuzzy clustering method of graph is analyzed and research in futher depth. The Algorithm is realized in Java Language. |
PDF Full Text Request