A new approach of adaptive Neuro Fuzzy Inference System (ANFIS) modeling for yield prediction in the supply chain of Jatropha

Abstract

Jatropha seed yield prediction is one of the most important factors for developing a supply chain modeling of Jatropha seed. The seeds of Jatropha curcas are generally used for the making of oil. Jatropha happens to be one of the most easily cultivable biofuel crops having a high degree of yield. The extract from its seeds, jatropha oil, is processed to obtain biofuel and biodiesel. The uncultivable wastelands are planned to utilize for cultivating jatropha seed is the main focus in this study. The effectiveness of prediction affects the functional characteristics of supply chain network design. The jatropha yield prediction has two important roles includes, (i) The identification of external parameters which affects the yield and (ii) Detection of internal attributes which changes the growth characteristics of jatropha plant. The development of Fuzzy Inference System characterized by a large number of input variables. This paper analyses the quantitative evidence that the yield of different regions on different attributes which are largely determined by only few attributes. Therefore, a new approach was ventured, where GUI was developed using MATLAB integrating ANFIS variables to model the Jatropha yield phenomenon, in which the numeric and graphical output can be easily printed to interpret the results. To investigate ANFIS variables' characteristic and effect, error was analyzed via Root Mean Square Error (RMSE) The RMSE values were then compared among various trained variables and settings to finalize best ANFIS predictive model.