Visual/Near-Infrared Spectroscopy Combined with Linear Discriminant Analysis and Machine Learning for Classification of Apple Damage

This study investigated the combined application of visible/near-infrared (Vis-NIR) spectroscopy with linear discriminant analysis (LDA) and machine learning (ML) for the classification of apples with different degrees of damage. The Vis-NIR spectral data of apples with different degrees of damage were collected, and the effect of different spectral preprocessing methods on the support vector machine (SVM) classification model was analyzed. LDA was used to reduce the dimensionality of the preprocessed spectral data, and five machine learning models including SVM, random forest (RF), K-nearest neighbor (KNN), decision tree (DT) and extreme gradient boosting (XGBoost) were constructed and compared for the classification of apple damage. The results showed that the SVM model based on preprocessed spectra with Savitzky-Golay (SG) smoothing had the best classification performance, with an accuracy of 87.3%. After dimensionality reduction using LDA, the classification accuracy of all the models was significantly improved, with the highest increase of 16% being observed in the DT model. The KNN model showed the best classification performance, with an accuracy of 96.0% and a precision of 96.4%. This study provides a basis for efficient and accurate assessment of the degree of mechanical damage in apples.