October 2016 Issue Vol.6 No.10
M.Phil Research Scholar, PG & Research Department of Computer Science,Chikkanna Government Arts College, Tirupur, Tamil Nadu, India
Assistant Professor, PG & Research Department of Computer Science, Chikkanna Govt. Arts College, Tirupur, Tamil Nadu, India
Abstract: Climate prediction is an ever tough place of research for scientists. The Adaptive Neuro-Fuzzy Inference System (ANFIS) has been widely used for modeling one-of-a-kind forms of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference systems (ANFIS) combines the talents of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to remedy different sorts of troubles, particularly green in rainfall prediction and also wind speed prediction. In this paper the utility of synthetic neural networks to predict the climate of Delhi town has been proposed the use of information base inside the Neuro-Fuzzy Inference gadget. The weather parameters like minimum temperature, maximum temperature, relative humidity, sea stage strain, rainfall, wind speed, wind route and sun shine etc. has been used for prediction. When appearing weather predictive model the key standards are usually accuracy. We’re seeking to be expecting future weather circumstance based upon above parameters by way of artificial neural community. The version performance is contrasted with multi layered perceptron community. The proposed network train with actual records of the 5 years (2010 to 2015) of South station, Coimbatore and tested which comes from meteorological department. The Multilayer Perceptron (MLP) used with Fuzzy good judgment. The Extreme Learning Machine (ELM) as an emerging mastering approach affords green unified answers to generalized feed-ahead net-works including but not limited to (both single- and multi-hidden-layer) neural networks, radial basis characteristic (RBF) networks, and kernel mastering.
Keywords:ANFIS, NN, Fuzzy Logic, Neuro Fuzzy, BPA.