URBAN GROWTH MODELLING USING CELLULAR AUTOMATA BASED CLASSIFIER

Urban cities are like complex systems. In order to test various policies urban models are used. A cellular automaton is used to simulate complex systems. The data used for urban planning is huge and complex because it is based on various factors like the growth in population, economy etc. So an accurate classifier is required. This paper proposes a cellular automata model, called Scalable Cellular Automata-based Classifier (SCAC), which has the capability to deal with non-conforming patterns in the binary features. It is developed on a Decision Support Elementary Cellular Automata (DS-ECA). The classifying capability of DS-ECA is accurate since it can describe very complicated decision rule in high dimension problems with less complexity. SCAC has double rule vectors and a scalable algorithm with decision function, the structure of which has two layers; the first layer is employed to evolve an input pattern into feature space using Apache Spark and the other interprets the patterns in feature space as binary answer through the decision function which is also scaled in a cluster. The algorithm proposed is a Cloud based Cluster computing model which is based on Cellular Automata.