Avocado Ripeness Classification Using Graph Neural Network

Abstract

In this study, the Graph Neural Network is a new deep learning algorithm, just like Convolutional Neural Network. This study aims to classify the ripeness of avocado using Graph Neural Network and its yield and benefit to farmers, consumers, vendors, and other researchers who will use the Graph Neural Network. Avocado Ripeness Classification with Graph Neural Network is a system that must classify the ripeness of avocados, whether they are unripe or ripe. Graph Neural Network uses node classification to classify the avocado by setting labels or classes for the nodes. For the training part, there is no available dataset image of avocado. It needs to manually create an image dataset of avocados by downloading at least 200 avocados per class and a total of 400 photos of avocados taken on Google Image. The study was successfully conducted to classify the avocado ripeness using Graph Neural Network to train and check the avocado ripeness. A total of 400 avocados were used in the study to classify ripeness, and it has an overall accuracy of 97.75% in detecting avocado ripeness.