Differentiation of Yeast-Inoculated and Uninoculated Tomatoes Using Fluorescence Spectroscopy Combined with Machine Learning

Artificial-intelligence-based analysis methods can provide objective and accurate results. This study aimed to evaluate the performance of machine learning algorithms classify yeast-inoculated uninoculated tomato samples using fluorescent spectroscopic data. For this purpose, three different types were used: ‘local dwarf’, ‘Picador’, ‘Ideal’. Discrimination was applied with six (ML) algorithms. Confusion matrices, average accuracies, F-Measure, Precision, ROC (receiver operating characteristic) Area, MCC (Matthews Correlation Coefficient), precision-recall area values obtained as a result application ML compared. Based on fluorescence data, showed that first two classified 100% accuracy last type 95% accuracy. The results show spectroscopy data are strongly representative species. fed these high-performance discrimination.