Evaluation of Electronic Nose System Based on Metal Oxide Semiconductor (MOS) Sensors to Detect the Purity of Peppermint Ssential Oil

The essential oils of medicinal plants are evaluated and used in the pharmaceutical and food industry based on the amount of active ingredients in them. One of the effective methods for identifying and evaluating essential oils is the electronic nose, which has fewer weaknesses than conventional methods. In this study, an electronic nose system consisting of 8 metal oxide semiconductor sensors was designed to determine the purity of peppermint essential oil. The PCA method was used to reduce the size of the data and identify effective sensors, and the artificial neural network method was used to calculate the accuracy of data classification. Based on the results, the principal component analysis method with two main components PC1 and PC2 was able to explain 82% of the variance of the data. Sensors that had a greater impact on the separation of essential oil purity classes were also identified. The accuracy of data classification in the training and testing stages in the artificial neural network method was 81% and 70%, respectively. Therefore, the proposed electronic nose system based on the mentioned algorithm is a reliable and low-cost tool for qualitative grading of different samples of purity of peppermint essential oil from each other.