Adaptation of Multilayer Perceptron Neural Network to unsupervised Clustering using a developed version of k-means algorithm

摘要

Cluster analysis plays a very important role in different fields and can be mandatory in others. This fact is due to the huge amount of web services, products and information created and provided on the internet and in addition the need of representation, visualization and reduction of large vectors. So in order to facilitate the treatment of information and reducing the research space, data must be classified. In other words, the needless of having a good technique of clustering is continually growing. There exist many clustering algorithms (supervised and unsupervised) in the literature: hierarchical and non hierarchical clustering methods, k-means, artificial neural networks (RNAs).... All of these methods suffer from some drawbacks related to initialization issues, supervision or running time. For instance, the classes' number, initial code vectors and the choice of the best learning set in k-means and Multi Layer Perceptron (MLP) affect seriously the clustering results. To deal with these problems, we develop a new approach of unsupervised clustering. This later consists of using a developed version of k-means algorithm which determines the number of clusters and the best learning set in order to train the MLP in an unsupervised way. The effectiveness of this approach is tested on well-known data sets and compared to other classifiers proposed by recent researches.