A Novice Approach for Web Document Clustering Using FP Growth Based Fuzzy Particle Swarm Optimization

Abstract

The success of any Information Retrieval system relies upon extracting relevant pages of similar knowledge matching the requirements of the user. The traditional best of all statistical methodologies fails in conquering the issues of relevancy and redundancy of web pages retrieved. In this paper we propose a novel architecture, FP Growth based Fuzzy Particle swarm optimization which captures the dynamicity and fuzziness of web documents. With FPGrowth we attain a much lesser but frequent sets recurring repeatedly. Indirectly the FPGrowth reduce the redundancy of the search space. These reduced frequent sets are optimized efficiently with evolutionary nature inspired PSO algorithm. This scenario of divide and conquer strategy of FP Growth to reduce the list of transactions to frequent items and being optimised using FuzzyPSO is extended to web document clustering. The major contribution in this paper is the generation of number of clusters and frequent item sets(particles) achieved via FP Growth which in rest of all algorithms are user given and better optimized accuracy in retrieval using FuzzyPSO avoiding the limitation of local minima of FCM completely with the global and local search mechanism. The evaluation reveals an optimised results for the proposed hybrid approach.