Palm Fruit Ripeness Detection System Using Convolutional Neural Network (CNN) Algorithm
Palm Fruit Ripeness Detection System Using Convolutional Neural Network (CNN) Algorithm
Josua Nainggolan,Debi Yandra Niska,2 Authors,Kana Saputra S
TLDR
In this study, CNN was used with the MobileNetV2 algorithm and the training accuracy results reached a peak of 98.20%, while the validation accuracy remained high at 95.00%.
Abstract
Oil Palm Fruit is a valuable natural resource crop in the plantation sector in Indonesia, with promising future growth prospects. To produce the best oil palm fruit, good sorting is needed. With good oil palm fruit, adequate technology is needed to assist in sorting oil palm fruit. Therefore, this study aims to help companies sort oil palm fruit bunches. In this study, CNN was used with the MobileNetV2 algorithm and the training accuracy results reached a peak of 98.20%, while the validation accuracy remained high at 95.00%. This proves that this model is very good and very feasible for further research. This method has proven to be the best choice for achieving high accuracy and low loss, but also minimizing errors in prediction.