Detection of pumpkin puree adulteration in tomato paste using a gas sensor array

Tomato is the second most important crop in the world, which is often consumed freshly. One of the most importance tomato products is paste that considered being the stuffing ingredient in Iranian foods. Therefore, the safety of tomato paste is so important. The aim of this study was diagnosis adulteration in tomato paste. For this purpose, olfactory machine system based on five gas sensors (TGS2600, TGS2620, MQ3, TGS880, TGS2610) was constructed and its potential was evaluated in determining the different levels of pumpkin adulteration in tomato paste (0, 5, 10, 15 and 20%). Pure tomato paste detection from adulteration samples was based on the samples smell in the head space and the receipt of smell by sensors. The principal component analysis (PCA), linear discriminant analysis (LDA), support vector machine (SVM) and partial least squares (PLS) were used to classify and analyze the extracted features of the sensor response. Results of PCA and PLS indicated that 99 and 94 percent of data variance was covered by two main components. TGS2610 and MQ-3 sensors and TGS880 sensor had the highest and lowest application in detection of tomato paste adulteration. The accuracy of the classification by the LDA method was 79.7%. The polynomial function with accuracy of 77.78% of the training and 76.66% validation in the C-SVM method and the radial base function with a precision of 98.8% of the training and 88.14% of Validation in the Nu-SVM method had the highest classification accuracy. In total, the olfactory machine system had acceptable performance in separation of different levels of adulteration.