<![CDATA[Indonesia is recognized as one of the world's biodiversity hotspots, with around 30,000 of the 40,000 global medicinal plant species found in its territory. This biological wealth is a strategic asset for health innovation and digital preservation. In areas with limited access to healthcare services, medicinal plants are the primary source of treatment, but their use is still hampered by the lack of a technology-based identification and documentation system. This study aims to develop and test a classification model for medicinal plants using a Convolutional Neural Network with Inception V3 architecture. The study uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework, which ensures systematic stages of business understanding, data preparation, modeling, and evaluation. The dataset used consists of 2,750 leaf images in 25 classes, compiled from previous research and independent collections. The data was divided into 1,921 images for training and 823 images for testing using a 70:30 ratio. The model was evaluated using accuracy, precision, recall, and F1 score. The results showed that the Inception V3-based CNN achieved a training accuracy of 96%, which increased to 97% with optimized weights, while maintaining strong precision, recall, and F1 scores. This proves that the Inception V3-based approach is capable of providing high and stable classification performance for the identification of Indonesian medicinal plants. These findings highlight the effectiveness of the model in identifying Indonesian medicinal plants from leaf images, providing a promising foundation for the development of knowledge and potential real-world applications]]>
Copyrights © 2025
