Analysis Of The Accuracy Of The Naive Bayes Algorithm In Classifying The Quality Of Malang Manalagi Apples

Abstract

Apples are one of the most popular fruits in Indonesia and around the world. Manalagi apples, originating from the city of Malang in East Java, are renowned for their unique taste and quality. In the fruit distribution and trade channels, determining apple quality quickly and accurately is crucial, especially to ensure the quality of the product received by consumers. However, the current apple quality assessment method is still manual and relies on visual observation by individuals, making it susceptible to subjectivity, fatigue, and errors in assessment. thus prone to subjectivity and inconsistency. To overcome this, this study developed a naive Bayes algorithm accuracy analysis system in classifying the quality of Malang Manalagi apples. The system was built on the MATLAB platform with an interactive graphical interface, and utilizes color feature extraction (Rmean, Gmean, Bmean), texture (GLCM), and image statistical features such as entropy, smoothness, skewness, and intensity. This method enables automatic and accurate classification of fresh and rotten apples. This research is expected to be a supporting solution in the process of assessing fruit quality more efficiently and objectively, and applicable to the needs of the agricultural industry.