Abstract

DATA PREDICTION FROM A SET OF SAMPLED DATA USING ARTIFICIAL NEURAL NETWORK IN MATLAB SIMULINK

*Md. Shohel Rana and Shakila Zahan

Abstract

Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. Classical statistical and econometric models used to predict efficiently handle uncertainty nature of data analysis. Prediction of the data from a set of sampled data is a difficult problem from both theoretical and practical point of view because the collections of data are influenced by many economic and natural factors. During the time, many statistical and econometric models have been developed by researchers for the purpose of prediction of data analysis but this problem remains one of the major challenges in the field of prediction and forecasting methods. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for prediction of the desired data and tried to see the implementation and comparison of the performance for foreign exchange rate prediction and finally to select the best method between this two feed forward of that keep the greater influence than the other in the field of prediction.

Keywords: Artificial Neural Network, MATlab Simulation, Data Prediction.