Application of Web usage mining based on improved genetic algorithm
Jun Peng · Computer Engineering and Applications Journal · 2009
Web usage mining is a hot research direction of Web data mining.In this paper,an improved genetic algorithm is pro-posed to overcome the shortage of early convergence and stagnation in the traditional genetic algorithm,which is based on uncon-vertible rate of crossover operator and mutation operator.Moreover,the user page interest measure threshold is introduced into the association rules mining.Lastly,the improved genetic algorithm is successfully applied to a commerce Web server log mining and the experiment results indicate that the proposed algorithm is an effective method to avoid early convergence.