IoT-based Efficient Waste Management on University Campus : Enhancing Monitoring and Optimization through Machine Learning

The introduction of an IoT-based smart waste management system is proposed to optimize various aspects of university campus waste recycle management processes, such as garbage collection scheduling, waste type identification, and collection routes. This system utilizes advanced data analytics algorithms, wireless communication protocols, and sensors to measure and document variations in trash levels, enabling real-time monitoring of waste accumulation. Through this IoT-based infrastructure, university administrators and waste management staff gain fine-grained visibility and control over garbage collection processes. The implications for sustainability advocacy and environmental stewardship in academic environments are significant. By fostering a culture of environmental awareness and accountability, universities can instill ideals of conservation and resourcefulness in their student populations and staff. The proposed IoT-enabled waste bin system exemplifies the synergy between technological innovation and environmental responsibility, serving as a model for institutions worldwide. Collaboration among universities can leverage IoT technology to drive positive change, mitigate environmental degradation, and promote sustainable practices beyond campus boundaries. Efficient waste management is crucial for nurturing sustainability on college and university campuses, as evidenced by the urgent need for the collection and recycling of compost, general waste, and recyclables. Our models consistently achieve high performance, with perfect scores (1.000) across all split ratios, indicating flawless classification of waste types. Although the Artificial Neural Network (ANN) demonstrates slightly lower accuracy, ranging from 0.973 to 0.997 depending on data splits, it still performs well. As a result, Naive Bayes produces less accurate results, typically surpassing 0.93 but falling short of Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)’s flawless scores, especially at split ratios of 90:10 and 80:20. ANN and Naive Bayes perform adequately with just little compromises in accuracy and recall, while Random Forest, KNN, and SVM stand out as the top-performing models.