Research of web data mining based on fuzzy logic and neural networks

Authors:
Limin Ren
Affiliations:
Electronic & Information Engineering Department, Tianjin Institute of Urban Construction, Tianjin, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
Year:
2009

Citing 4
Cited 0

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Latent semantic indexing: a probabilistic analysis

PODS '98 Proceedings of the seventeenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Fast latent semantic indexing of spoken documents by using self-organizing maps

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 04
Research and Realization of Text Mining Algorithm on Web

CISW '07 Proceedings of the 2007 International Conference on Computational Intelligence and Security Workshops

Quantified Score

Hi-index	0.00

Visualization

Abstract

Web document classification and clustering are two crucial sections in Web data mining. The models, algorithms and simulation experiments for both Web document classification and clustering have been studied separately to support for the personalized services and to overcome the deficiencies and shortcomings of the same type's algorithms in the paper. The Web document classification based on fuzzy reasoning with comprehensive weights and Web search result clustering based on fuzzy logic and neural networks are presented for Web data mining to obtain easily understood, robust and low-priced solutions by exploring the greatest possible extents of imprecision, uncertainty, fuzzy reasoning and partial correctness. The experiments have demonstrated that the established intelligent Web information mining system here makes Web document classification and clustering more accurate, more credible and more rapid than the exciting ones.