<![CDATA[The increase in solid wastes floating on surface of rivers has become a big problem in the urban environment, such as floods and diseases. The goal of this research is to build an object detection model using Convolutional Neural Network (CNN) with YOLOv8 (You Only Look Once v8) algorithm, and to implement that model to detect floating wastes on the surface of Ciliwung River. The model used in this research is YOLOv8, because of its high speed and accuracy. The data used are obtained from online sources (Google Images and YouTube), and directly from Ciliwung River obtained with smartphone camera. The best epoch is the 177th epoch. The Precision value is 84.02%, the Recall value is 91.03%, the Accuracy value is 77.6%, and the F1-Score is 87.38%. The conclusion is that the model built with YOLOv8 algorithm can be used to detect floating wastes on the surface of Ciliwung River.]]>
Copyrights © 2024
