Services of prediction for visiting path based on improved matrix clustering

Autor:	Tie-Jun Li, Tao Lin, Mei-Na Chen, Yu-qing Peng
Rok vydání:	2005
Předmět:	Matrix (mathematics) Data stream clustering Computer science CURE data clustering algorithm Correlation clustering Path (graph theory) Canopy clustering algorithm Data mining Cluster analysis computer.software_genre computer Computer Science::Databases k-medians clustering
Zdroj:	Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).
DOI:	10.1109/icmlc.2004.1382053
Popis:	According to the analysis of Web log files, matrix clustering algorithm not only can be optimized, but also mining results can be applied to predicting users' visiting path and classify new users. The data-preprocessing phase has been discussed in detail. Then, Web log mining algorithms and pattern analysis and appliance phase are presented, including the optimized matrix clustering algorithm and the basic idea and realization of the prediction algorithm. Experiments show that the algorithm is effective and feasible.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::353671038ce520ecc3784731c0d4fa26 https://doi.org/10.1109/icmlc.2004.1382053 Zobrazit plný text záznamu