Hyperspectral Method Integrated with Machine Learning to Predict the Acidity and Soluble Solid Content Values of Kiwi Fruit During the Storage Period

Abstract Non-destructive evaluation is advancing in examining the properties of fruits. Kiwi fruit stands out as one of the popular fruits globally. Due to the influence of various environmental factors and storage conditions, diligent checking and storage of this fruit are essential. Therefore, monitoring changes in its properties during storage in cold storage facilities is crucial. One nondestructive method utilised in recent years to investigate changes in fruit texture is the hyperspectral method. This study uses the support vector machine (SVM) method to assess hyperspectral method‘s effectiveness in examining property changes in four kiwi varieties during storage in addition to predicting the properties such as acidity and soluble solid content. The evaluation of the predictive machine learning model revealed an accuracy of 95% in predicting acidity and soluble solid content (SSC) changes in kiwi fruit during storage. Further, investigations found that the support vector machine method provided relatively lower accuracy and sensitivity in identifying product variety during storage, with an average accuracy ranging from about 91% to 94%. These findings suggest that integrating machine learning methods with outputs from techniques like hyperspectral imaging enhances the non-destructive detection capability of fruits. This integration transforms obtained results into practical outcomes, serving as an interface between software and hardware.