<![CDATA[River pollution caused by waste remains a serious environmental issue, particularly in urban areas such as the Deli River. The process of monitoring and identifying waste types is still largely performed manually, making it inefficient and ineffective. Therefore, this study aims to develop an image-based classification system for organic and inorganic waste using the Convolutional Neural Network (CNN) method with the MobileNetV2 architecture. The dataset used in this research consists of surface images of the Deli River captured using a drone camera. The images were processed through preprocessing and data augmentation stages, followed by data splitting, model training, and testing. The CNN model was designed to classify two waste categories, namely organic and inorganic waste. Model performance was evaluated using a confusion matrix with accuracy, precision, recall, and F1-score as evaluation metrics. The results indicate that the proposed CNN model is able to classify organic and inorganic waste effectively. The system achieved an accuracy of 94%, a precision of 92%, a recall of 98%, and an F1-score of 95%. These results demonstrate that the model has excellent performance and reliability in identifying waste characteristics based on shape, color, and texture features from river surface images. Therefore, the developed system has the potential to be implemented as an automatic and sustainable tool for monitoring the cleanliness of the Deli River.]]>
Copyrights © 2026
