Evaluating the Adulteration of Sodium Benzoate and Potassium Sorbate in Tomato Paste on the Physicochemical Properties of the Tomato Paste Using an Olfactory Machine and Artificial Intelligence

Tomato is a major horticultural crop consumed globally. As a widely used ingredient in foods, tomato paste’s quality and safety are highly important. This study investigates adulteration in tomato paste using an electronic nose (E‐nose) system equipped with 10 gas sensors to detect sodium benzoate and potassium sorbate at concentrations of 0%, 0.05%, and 0.1%. The effects of these preservatives on physicochemical properties, including pH, total soluble solids (TSSs), precipitate weight ratio (PPT), and total acidity (TA), were also evaluated. Results showed that both preservatives significantly affected all physicochemical parameters at the 1% significance level ( p < 0.01) across 50 tested samples. Linear discriminant analysis (LDA) achieved 100% accuracy in detecting preservative levels, while principal component analysis (PCA) and support vector machine (C‐SVM) effectively identified samples with 0.05% and 0.1% preservatives. The loading chart highlighted TGS2620, MQ135, and TGS2602 as the most sensitive sensors for detecting adulterated samples. Principal component regression (PCR) and multiple linear regression (MLR) were the most effective models for predicting TA and TSS, PPT, and pH, respectively. The E‐nose proved to be an efficient tool for detecting adulteration in tomato paste.