Application of olfactory machine system for detection of adulteration in caraway samples

Caraway as one of the most valuable herbs are widely used in pharmaceutical and food industries and due to the high cost and quality difference between different varieties of caraway, adulteration maybe carried out in this product in market that leads to the low satisfactory sense in consumers. In this study, an olfactory machine system based on eight metal oxide semiconductor sensors combined with the pattern recognition method was used to identify the different levels of adulteration in the caraway and its authenticity assessment. The principal component analysis method was used to analyze the extracted data from the sensor response signal. Based on the results, the principal component analysis with the two main components of PC1 and PC2 described %94 of the variance of the data set for the used samples. In the sensor array, MQ4 and FIS sensors revealed the highest loading coefficient values and MQ135, MQ3 and TGS813 sensors devoted the lowest ones. Then, the classification of samples was done using support vector machine (SVM) and decision tree (DT) techniques. SVM with linear kernel function showed the training and validation accuracy values as 100% and 97.5%, respectively. Also, the success rate of the DT method in the distinction and classification samples of adulterated caraway was estimated as 90%.