A hybrid method of prediction based on Soft Computing Techniques

Abstract In Soft Computing Techniques based prediction various methods have been developed to establish the hybrid model for forecasting the future values, the present paper proposes a hybrid method of soft computing i.e; the combination of artificial neural networks and fuzzy set theory techniques. The study uses the fuzzy set theory Zadeh(1965) and fuzzy time series models introduced by Song and Chissom(1993) and Chess(1993). The prediction has also been obtained by developing an Artificial Neural Network model using back propagation algorithm. The study is aimed to find the forecast for primary education literate population of Lucknow district for a lead year by using a fuzzy time series model and back propagation algorithm. The success of the proposed model has been examined by comparing the result of proposed model with actual primary educated population of Lucknow district.