Classification of Tangerines on Fruit Ripening Levels Using K-Nearest Neighbor Algorithm

Irfan Rasyid (Universitas Muhammadiyah Magelang)
Imam Saputra (Universitas Muhammadiyah Magelang)
Raden Kartika Satya Suryanegara (Universitas Muhammadiyah Magelang)
Muhammad Resa Arif Yudianto (Universitas Muhammadiyah Magelang)
M Maimunah (Universitas Muhammadiyah Magelang)

Prosiding University Research Colloquium
Proceeding of The 15th University Research Colloquium 2022: Mahasiswa (Student Paper Presentation) B

This journal reviews the classification of the maturity level of tangerines based on HSV using the K-Nearest Neighbor (KNN) method. This study aims to make it easier for the public to distinguish ripe and unripe when choosing citrus fruits and also to avoid fruit shops selling unripe oranges so as not to harm sellers or buyers. We take the data sources used in this study ourselves. In this study, we use the K-Nearest Neighbors (KNN) method. This method is used in the image classification process by relying on the results of feature extraction that have previously been trained. This method selects the nearest neighbor from the training dataset, then determines the closest distance value or the smallest distance value that will produce the classification output. The results of the accuracy in using this method have reached 93% with a value of k=7.