DETERMINATION OF OIL PALM FRUIT MATURITY USING A PORTABLE INSTRUMENT BASED ON UV-VIS-NIR SENSOR
PENENTUAN KEMATANGAN BUAH KELAPA SAWIT MENGGUNAKAN INSTRUMEN PORTABEL BERBASIS SENSOR UV-VIS-NIR
DOI : https://doi.org/10.35633/inmateh-76-49
Authors
Abstract
This study developed a portable instrument using the AS7265x sensor (410–940 nm) for non-destructive oil palm maturity evaluation. Reflectance from 250 oil palm fruits at 10 maturity stages was measured by the instrument and processed with some spectra pre-treatments, then classified into three levels of maturity using principal component analysis (PCA). PCA with SNV pre-treatment explained 97% variance using PC1 and PC2. Classification was validated using support vector machines (SVM), random forest (RF), and K-nearest neighbors (KNN), with KNN achieving 100% accuracy. This approach enables a non-destructive and accurate classification of oil palm fruit maturity.
Abstract in Indonesian