Classification of aromatic and non-aromatic rice using electronic nose and artificial neural network

Abstract

Classification of rice is carried out by human experts in the industry and apart from other attributes like grain size, elongation ratio, aroma plays a significant role in the classification process. On the basis of aroma, the rice samples are manually categorized as strongly aromatic, moderately aromatic, slightly aromatic and non aromatic. Instrumental evaluation of aroma of rice is much needed in the industry and in this paper, we describe an electronic nose instrument, that has been developed for aroma characterization of rice. Artificial neural network is used for the pattern classification on data obtained from the sensor array of the electronic nose. With unknown rice samples, aroma based classification accuracy has been observed to be more than 80%.