Key points are not available for this paper at this time.
This study focuses on developing an efficient urban waste management system using deep learning algorithms and Internet of Things (IoT) technology. The goal is to improve waste management in Ikot Ekpene municipality by enabling quick disposal responses to prevent environmental pollution. The researchers employed an Object-Oriented Analysis and Design (OOAD) methodology to develop a software system that integrates mobile GIS techniques and IoT sensors to monitor and manage waste. The system was trained using a dataset of 510 images of six classes of waste-related scenarios, with an 84% training set and 16% validation set. The results showed that the garbage bin half-full class had the highest F1 score (above 80%) at a confidence score of 0.4, indicating accurate detection. The average F1 score for all classes was 0.45 at a confidence score of 0.238. The system’s API was designed using Python, supporting both web-based and Android-based applications. The integration of IoT sensors and mobile GIS techniques enables real-time monitoring and efficient waste management. This study demonstrates the potential of deep learning algorithms and IoT technology in improving waste management services, contributing to a cleaner and healthier environment. The system’s effectiveness in detecting waste levels and triggering timely disposal responses can help prevent environmental pollution and enhance the well-being of citizens.
James et al. (Mon,) studied this question.