DYNAMICAL CLUSTERING OF STREAMING DATA WITH A GROWING NEURAL GAS NETWORK

Abstract

One of characteristic feature of contemporary data bases is their growing dynamics. The number of registered entities as well as their group structure tends to dynamically grow. In order to effectively determine the rapidly changing number and structure of clusters, appropriate methods of cluster analysis have to be applied. The paper presents the results of simulation research concerning the possibility of applying self-learning GNG neural networks in clustering data from data streams.