Sensory stability of pistachio nut (Pistacia vera L.) varieties during storage using descriptive analysis combined with chemometrics

Sensory evaluation involves the measurement and examination of the sensory properties of foods. This paper deals with the use of some chemometrics techniques for sensory recognition and stability of four Iranian pistachio nut varieties (Kale-Ghouchi, Akbari, Ohadi, and Momtaz) during storage. For this purpose, nine sensory attributes (bitterness, firmness, sweetness, rancidity, crunchiness, salty, sour, glossy, roasted) were evaluated by a professional trained human sensory panel to examine the changes during 8 months of storage. Several chemometrics techniques were employed for this aim. Linear techniques as principal component analysis (PCA) and Linear Discriminant Analysis (LDA) were performed over the data that partial overlapping were seen for all treatments of pistachio nut varieties. Moreover, artificial neural networks such as Probabilistic Neural Networks (PNN) with Radial Basis Functions (RBF) and FeedForward Networks with Backpropagation (BP) learning method were then used. The methods have proved a good capability to recognize and classify the stored pistachio nuts satisfactorily in such a way, for whole varieties, high classification accuracies were obtained. The highest success rate was found for Kale-Ghouchi variety (D) as 100%. It was revealed the classification accuracies were better using BP compared with PNN. The achievements of this study can be of great interest to pistachio nut producers for the management of storage length and more particularly export circumstances. The results obtained can be used as a reference data for electronic nose and electronic tongue experiments in future studies.