Measuring of Paddy mass flow using capacitive sensor and modeling with using multiple regression, ANN, and ANFIS models

Measuring the mass flow of agricultural products by using capacitive sensors as inexpensive and rapid method has been developed. But predicted mass flow due dependence of sensor response to various factors and complexity effect of these factors is difficult. So in this study the potential of Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Multiple Regression (MR) techniques to predict paddy mass flow by using capacitive sensor was evaluated. Frequency, Moisture content and output voltage were employed as input variables and mass flow was considered as output in the developed models. Results showed that ANN gave the best correlation between predicted and actual values (R2 = 0.927); ANFIS gave the correlation between predicted and actual values, with correlation coefficient (R2) of 0.909. These results indicate that the ANN and ANFIS techniques can potentially be used to predict mass flow of agricultural products.