The Adaptive Waste Management Assistant (AWMA) An IO and IoT-Based Intelligent System for Urban Waste Management

¹ Dept of IT, St. Joseph’s College of Engineering, Chennai, India
² Dept of IT, St. Joseph’s College of Engineering, Chennai, India
³ Dept of IT, St. Joseph’s College of Engineering, Chennai, India
⁴ Dept of IT, St. Joseph’s College of Engineering, Chennai, India

This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Smart city garbage collection Adaptive Waste Management Assistant (AWMA) is a garbage collection, management service application that integrates the principle of Artificial Intelligence (AI) and Internet of Things (IoT) to contribute to the efficiency, precision, and sustainability of the garbage collection procedures. The solutions of the projects address the major issues that the municipalities are experiencing which include the missed garbage collection, incorrect route planning, and improper waste separation and overflowing of garbage bins. The proposed system is based on smart bins with AI assistance in that the devices installed on the bins will have sensors and cameras that will either determine the fill levels, contamination, and sort waste into plastic, paper, metal, and organic materials. Once a bin has reached a specific level, then automatic request of collection is generated and transmitted to a centralized cloud server. The server processes this information and applies the optimal routing algorithms to the close waste collection vehicle to minimize manual labor, prevent overflowing, and have a timely collection process. Real-time monitoring and analytics on data used can assist AWMA in reducing manual labor, preventing overflowing, and ensuring a timely collection process. In addition, the obtained information might be valuable to the municipal government and enable it to forecast, more effectively distribute the resources and work out superior recycling policies. Figma based interface designs and no-code apps were utilised during the prototype stage to serve as a simulation of system functionality. The future developments to the AWMA system include introduction of more advanced machine learning models and a potential of predictive filling patterns, which will demonstrate that the system will shift off of the traditional reactive approach of waste collection and towards a more proactive and automated system. Its architecture is scalable and modular and can be deployed in future in smart cities, college campuses, residential and in business districts. The smart solution based on technology assists in making cities cleaner, reducing costs of operations and improving the citizens in terms of heal.