A data fusion approach for nondestructive tracking of the ripening process and quality attributes of green Hayward kiwifruit using artificial olfaction and proximal hyperspectral imaging techniques

A data fusion strategy based on hyperspectral imaging (HSI) and electronic nose (e-nose) systems was developed in this study to inspect the postharvest ripening process of Hayward kiwifruit. The extracted features from e-nose HSI techniques, single or combined mode, were used develop machine learning algorithms. Performance evaluations proved that olfactory reflectance improves performance discriminative predictive Accordingly, with high classification accuracies 100% 94.44% calibration test stages, fusion-based support vector (SVM) outperformed partial least square discriminant analysis (PLSDA) for discriminating kiwifruit samples into eight classes storage time. Moreover, regression (SVR) a better predictor than squares (PLSR) firmness, soluble solids content (SSC), titratable acidity (TA) measures. prediction R2 RMSE criteria SVR algorithm 0.962 0.408 0.964 0.337 SSC, 0.955 0.039 TA, respectively. It concluded hybrid coupled SVM delivers an effective tool accurate nondestructive monitoring quality during storage.