Shelf-life Quality Monitor of Postharvest Tomato Based on Visible/Near Infrared Spectroscopy

Visible and near infrared (Vis/NIR) spectroscopy combined with chemometrics was investigated for the fast determination of soluble solids content (SSC), pH and firmness of postharvest tomatoes during shelf-life. A total of 630 tomato fruit samples from 5 cultivars and 9 days shelf-life was selected for the analysis, 450 samples (90 for each variety and 50 for each day shelf-life) were selected as calibration set, whereas 180 samples (36 for each varietyand 20 for each dayshelf-life) for the validation set, Partial least squares (PLS) analysis was implemented for calibration of models with spectra preprocessed by Savitzky-Golay smoothing, Optimal factors were used as the inputs of least squares-support vector machine (LS-SVM) models with grid search technique and RBF kernel. All LS-SVM models outperformed PLS models. The correlation coefficient (r), RMSEP and bias in validation set by LS-SVM were 0.8676, 0.1192 and 0.0610 for SSC, 0.8587, 0.5067 and 0.0653 for pH, 0.8515, 1.0867 and 0.0516for firmness, respectively. The results indicated that Vis/NIR spectroscopy combined with LS-SVM could be successfully applied for the determination of SSC, pH and firmnessof postharvest tomatoes in shelf life. The results will be helpful for further analysis of using Vis/NIR spectroscopy to monitor horticultural product quality in shelf-life.