<![CDATA[Waste management in Indonesia, particularly the limited ability to distinguish and sort organic and inorganic waste from an early age, poses a challenge to achieving sustainable development goals. This study aims to develop a web-based learning system that integrates a Convolutional Neural Network (CNN) model with a transfer learning approach using the MobileNetV2 architecture to classify images of organic and inorganic waste as an interactive educational medium for elementary school students aged 6–12 years. A dataset comprising 3,000 images (1,500 organic and 1,500 inorganic) was obtained from publicly available sources and divided into training, validation, and testing sets at a ratio of 70:15:15. The preprocessing stage included data augmentation, normalization, and image resizing to 224 × 224 pixels. The model was trained for 20 epochs using the Adam optimizer and Binary Crossentropy loss function. The evaluation results demonstrated a test accuracy of 92%, with precision, recall, and F1-score values of 0.92 for both classes. The model was subsequently integrated into a Flask-based website featuring image upload functionality, educational articles, and interactive quizzes. The main contribution of this study lies in integrating a lightweight CNN-based image classification model into a child-oriented educational web platform, thereby supporting efforts to improve waste-sorting awareness from an early age among elementary school students in Denpasar City.]]>
Copyrights © 2026
