Ripeness assessment and quality control of mango gold susu using an e-nose system

In this paper, the development and implementation of an electronic nose (e-nose) system utilizing the MQ sensor series from MOS-type gas sensors to classify mango gold susu ripeness is presented. The system's performance was enhanced through machine learning techniques, including Principal Component Analysis (PCA) for data dimensionality reduction and Support Vector Machine (SVM) for classification. The SVM classifier demonstrated high accuracy, particularly in identifying unripe and overripe mangoes, with accuracy scores of 1.00 and 0.99, respectively. A comprehensive database of volatile organic compound (VOC) profiles was established, leading to a precise prediction model for assessing the different stages of ripeness based on the mango’s VOC profile.