<![CDATA[Detection of Arabica coffee leaf diseases is crucial for improving the quality and yield of coffee crops. This study aims to apply the DenseNet121 Convolutional Neural Network model to identify three types of diseases on Arabica coffee leaves, namely Rust, Phoma, and Miner. The data used consists of images of Arabica coffee leaves, which are divided into training, validation, and test sets. The model was trained using the Adamax optimizer with hyperparameters such as a maximum of 30 epochs and a batch size of 32. During training, the model achieved a validation accuracy of 98.86% before being stopped by the early stopping callback at epoch 28 to prevent overfitting. Model evaluation using a confusion matrix resulted in 97% accuracy on the test data, with excellent precision, recall, and F1-score values for most categories, particularly for the Healthy, Miner, and Phoma classes. The Rust class showed lower recall due to data imbalance in the test set. The results of this study demonstrate that the DenseNet121 model is reliable for detecting diseases on Arabica coffee leaves with high accuracy and provides an important contribution to the technology of plant health monitoring, which can assist farmers in early detection and improve coffee crop productivity.]]>
Copyrights © 2025
