Optimal Biclustering using Hybrid Swarm Intelligence for Web usage Mining
Kavitha
Kavitha, School of Computer Science and Applications, REVA University, Bangalore, India.
Manuscript received on 03 March 2019 | Revised Manuscript received on 08 March 2019 | Manuscript published on 30 July 2019 | PP: 6392-6395 | Volume-8 Issue-2, July 2019 | Retrieval Number: B2215078219/19©BEIESP | DOI: 10.35940/ijrte.B2215.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Web usage mining is used to analyze the user browsing behavior among the web pages which can be further utilized in other applications like recommender system, personalized web pages, providing insight for better business functionality. Since this type of mining does not only depends on the user or web pages, conventional clustering techniques may not suit very well for the analysis. Biclustering techniques are used to discover the subset in the form of submatrices as objects and attributes of objects are considered symmetrically. Finding optimal biclusters is a critical research issue. This research proposes a hybrid swarm intelligence-based method having Particle Swarm Optimization combined with Leader Clustering method along with Uniform Crossover operator. The experimental study shows that the proposed method performs well than traditional biclustering techniques in terms of evaluation metrics.
Index Terms: Biclustering, Web Usage Mining, Particle Swarm Optimization, Leader Clustering, Hybrid Swarm Intelligence.
Scope of the Article: Discrete Optimization