Fermentation Level Classification of Cross Cut Cacao Beans Using k-NN Algorithm

Abstract

In chocolate production, post-harvest procedure is one of the most critical factors. Fermentation is a vital procedure to consider since exact generation of acid contemplate to aroma and quality of the final product. This innovative study aims to classify the quality of the cacao beans after the post-harvest procedures. Classified sample beans from partner cacao trader were analyzed and became data sets of the device. Photographs are taken to the subjects and undergo image processing procedure then through k-Nearest Neighbors Algorithm (k-NN). Beans are classified to be well-fermented under fermentation and over-fermentation process. Function test and statistical analysis using confusion matrix revealed 97.22 percent accuracy in analyzing well-fermented beans, 92.59 percent accuracy in under fermented, 75 percent in over-fermented and 80 percent in analyzing unknowns. These results generated 92.50 percent overall accuracy of the device.