Predicting Moisture Content of Pistachio Nuts (Akbari Variety) with Artificial Neural Network

In order to predict moisture content of pistachio nuts (Akbari variety) using artificial neural network (ANN) method, experiments were performed at five drying air temperatures (ranging 40 to 80 oC) and four input air flow velocities (ranging from 0.5 to 2 m/s) with triplicates in a thin layer dryer. Initial moisture content of all samples were held at bout 30 % d.b. The data obtained from the experiments were transferred to artificial neural network(ANN) medium. In order to develop neural network firstly experimental data were randomly divided into three sets of training (70%), validating (10%) and testing 20% models. In order to develop ANN models, we used multilayer perception (MLP) with back-propagation with momentum algorithm. MLP models trained as two, three and four layers. The highest coefficient of determination (R2) and lowest mean squared error (MSE) were considered as the criterion for selecting the best network. The network having three layers with a topology of 3-8-5-1 had the best results in predicting the moisture content of pistachio nuts. This network has two hidden layers with 8 neurons in the first hidden layer and 5 neurons in the second hidden layer. For this network, R2 and MSE were 0.9989 and 4.2E-6, respectively. The methodology and results of this research can used/adapted for design the industrial dryer.