Hybrid PSO and GA Models for Document Clustering

This paper presents Hybrid Particle Swarm Optimization (PSO) Genetic Algorithm (GA) approaches for the document clustering problem. To obtain an optimal solution using Genetic Algorithm, operation such as selection, reproduction, and mutation procedures are used to generate for the next generations. In this case, it is possible to obtain local solution because chromosomes or individuals which have only a close similarity can converge. In standard PSO the non-oscillatory route can quickly cause a particle to stagnate and also it may prematurely converge on suboptimal solutions that are not even guaranteed to local optimal solution. This work proposes hybrid models that enhance the search process by applying GA operations on stagnated particles and chromosomes. GA will be combined with PSO for improving the diversity, and the convergence toward the preferred solution for the document clustering problem. The approach efficiency is verified and tested using a set of document corpus. Our results indicate that the approaches are feasible alternative to solve document clustering problems.