CLUSTERING DATA PENCEMARAN UDARA SEKTOR INDUSTRI DI JAWA TENGAH DENGAN KOHONEN NEURAL NETWORK

Abstract

Industrial clustering in Central Java based on polutan yielded to be intended in order to obtaine an industrial group as information in development wisdom specially at Central Java Province. The method that is selected in industrial clustering is Kohonen Artificial Neural Network. An Artificial Neural Network is configured for a specific application, such as pattern recognition or data classification, through a learning process. Kohonen Neural Network can be used in data clustering through unsupervised learning. This network will divide the input pattern into some cluster, based on trained weight. Then this weight will be updated until it can classified itself into the class needed. This paper will present the result of the air contamination data clustering at industrial sector in Central Java at the year 2006 using Kohonen Neural Network. The result of this clustering is industrial clustering, based on polutan yielded, become three clusters.