Prediction of moisture dependent some physical properties of wheat using artificial neural network and fuzzy logic

Abstract

Artificial intelligence systems are widely accepted as a technology offering an alternative way to tackle complex and ill-defined problems. They can learn from examples, are fault tolerant in the sense that they are able to handle noisy and incomplete data, are able to deal with non-linear problems, and once trained can perform prediction and generalization at high speed. In this study, the mass, geometric mean diameter and rupture force of wheat seed were measured at different levels of moisture content (9.93-19.01% w.b.). An artificial neural network (ANN), fuzzy logic (FL) and regression models were developed to predict the mass, geometric mean diameter and rupture force of wheat seed. The ANN and FL models had one input parameter and three output parameters. The results obtained with the experimental methods were compared with ANN, FL and regression model results. The results showed that ANN, FL and regression model can be alternative approaches for the predicting of physical properties of wheat seed, but the best results have been obtained with the ANN model.