Comparative study of artificial neural network model (ANN) And Adaptive Neural Fuzzy Inference System (ANFIS) in order to forecasting of the Construction permit application (Case study: Zabol's municipality)

Notice of the amount of the claim in the context of license of building in each course is one of the fundamental issues that municipals for answer to client needs. The lack of information in this area caused problems such as a waste of time and energy، reducing efficiency and dissatisfaction with clientele and ultimately causes of the lack of planning. With regard to process of non-liner and pendulous individuals motivated to building and more crafting of construction permits from municipalities and variable affecting it، non – liner models special Artificial Neural Network (ANN) and Adaptive Neural Fuzzy Inference System (ANFIS) would have more success. To this end، consider a combination of the most essential parameters as the external and internal part that are impact on the decision of people making to building، inclusive city''s population and its grows rate، average of the household costs and revenue، the impact of the season`s and temperature، the rate of gross domestic product (macro level)، inflation، and Exchange rate fluctuations (as the external parameters) and factors such as land and its price، building density، and the rate of imposition of construction (as the internal parameters). in continue to compare their ability to both، utilize from evaluation criteria to performance models such as the coefficient of determination (R2)، middle absolute deviations (MAD) and root middle square errors (RMSE). Finally ANFIS excel to ANN due to reliance to combination of ANN ventilations power and logical function of fuzzy inference system with amount of R=­­ (0. 9899، 0. 9656)، RMSE= (0. 0064، 0. 0026)، and AMD= (0. 0061، 0. 0018) for training and testing system.