Vis/NIR and FTIR spectroscopy supported by machine learning techniques to distinguish pure from impure Iranian rice varieties

. Rice is an annual plant from the family of Oryzeae, provides the main food for about 2.5 billion people. The quality of this product is under the influence of various factors. Quality control and adulteration detection are among the main issues in the rice industry for which, various methods have been developed. Some of these methods are costly or with low accuracy. Therefore, this study aimed to investigate and detect adulteration with spectroscopic devices and chemometric methods as well as neural network approach. The results of this study indicated the highest accuracy (100%) in the detection of authentic rice for Fourier-transform infrared combined with C-support vector machine (linear and polynomial functions) and visible–near–infrared device with quadratic discriminant analysis, multivariate discriminant analysis, Bayesian, and Decision Tree. The lowest accuracy was also related to support vector machine method with Sigmoid function for both devices. Principal component analysis method also provided very high accuracy for both devices (accuracy of 100% for visible–near–infrared and 99% for Fourier-transform infrared).