Optimizing convolutional neural networks-based ensemble learning for effective herbal leaf disease detection

Abstrak

This study aims to optimize convolutional neural networks (CNN)-based ensemble learning models to enhance accuracy and stability in detecting herbal leaf diseases. The dataset used in this study is sourced from the “Lontar Taru Pramana” collection, which includes various images of herbal leaves affected by different diseases such as Ancak Bacterial Spot, Dapdap Mosaic Virus, and Kelor Powdery Mildew. Several CNN models, including VGG16, AlexNet, ResNet50, DenseNet121, MobileNetV2, and InceptionV2, were evaluated. Among these, the ensemble models combining VGG16, DenseNet121, and MobileNetV2 were selected due to their superior performance. The ensemble model achieved precision scores of 0.81 for class 1, 0.76 for class 2, and 0.78 for class 3, with corresponding recall scores of 0.8167, 0.74, and 0.7633, and F1-scores of 0.8133, 0.75, and 0.7717 respectively. These results indicate significant improvements in model performance and robustness.