CLASSIFICATION OF STAR FRUIT HEALTH LEVEL USING KNN AND SVM ALGORITHMS

Abstract

Starfruit, scientifically known as Averrhoa Carambola, is a horticultural commodity whose health quality must be maintained to ensure it is suitable for consumption and has a good selling value. Manual starfruit health assessment still relies on human visual observation, potentially leading to subjectivity and inconsistency. Therefore, this study aims to classify starfruit health using machine learning approaches, namely the K-Nearest Neighbor (KNN) algorithm and the Support Vector Machine (SVM).

The results showed that the SVM algorithm provided better classification performance than KNN in determining star fruit health. Therefore, the application of the KNN and SVM algorithms can be an alternative solution for an automatic and objective star fruit health classification system.