In this article the performance of the genetic algorithm for solving some clustering problem is investigated through a simulation experiment. If the number of cluster is known in advance, our results show that the genetic algorithm is able to find the right partition, almost irrespective of the genetic parameters selection. Also, the genetic algorithm always performs favourably with respect to K-means algorithm. In the case the number of clusters is unknown, four different genetic algorithms proposed in literature are compared, and their performances are found not to differ significantly.
Some Insight into Genetic Algorithm as Clustering Technique / Baragona, Roberto; Bocci, Laura; C. M., Medaglia. - STAMPA. - (2003), pp. 175-180. (Intervento presentato al convegno Applied Simulation and Modelling tenutosi a Marbella, Spain nel September 3-5, 2003).
Some Insight into Genetic Algorithm as Clustering Technique
BARAGONA, Roberto;BOCCI, Laura;
2003
Abstract
In this article the performance of the genetic algorithm for solving some clustering problem is investigated through a simulation experiment. If the number of cluster is known in advance, our results show that the genetic algorithm is able to find the right partition, almost irrespective of the genetic parameters selection. Also, the genetic algorithm always performs favourably with respect to K-means algorithm. In the case the number of clusters is unknown, four different genetic algorithms proposed in literature are compared, and their performances are found not to differ significantly.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
