<![CDATA[This research aims to develop a classification model using Convolutional Neural Networks (CNN) to determine the ripeness and quality of Cavendish bananas. The model classifies bananas into four categories: good quality unripe (MHBS), poor quality unripe (MHBK), good quality ripe (MGBS), and poor quality ripe (MGBK), using a total of 1,000 images. In this study, the classification process of the ripeness and quality of Cavendish bananas was carried out based on automatic feature extraction using CNN,after which an evaluation was carried out using a confusion matrix to assess model performance. The research developed 36 models with variations in parameters such as the number of epochs, batch size, and dataset split. The analysis results indicate that the number of epochs significantly affects the model's accuracy, with an increase in the number of epochs leading to higher accuracy. However, the dataset split scenario and batch size do not have a significant impact on the model's overall accuracy. Evaluation shows that the highest accuracy of 95% was achieved by the model with a 90:10 dataset split, a batch size of 16, and 20 epochs.]]>
Copyrights © 2024
