An Automated Smart Waste Management Systems using Support Vector Machine

Through reducing air pollution, maintaining the aquatic environment, and improving human health, environmental problems caused by improper waste disposal can be resolved in smart cities. However, the technologies, methods, and systems used for waste management today remain centralized and manual. Because of this, both manipulation and the problem of single points of failure can affect them. a smart city's building requires efficient waste management, and the IoT is a significant player in this process. The term "IoT" describes how commonplace devices and devices are connected to one another so they may exchange data and communicate. Self-waste management was the most important factor. People should have visited every street each day to pick up waste from the community. Waste collection trucks and their drivers are part of the regular waste management system. They follow a predefined route without checking the level of the containers. Because of this system's inability to detect container levels, half-filled containers may be emptied. Furthermore, the system's collection routes result in time waste, increased fuel consumption, and excessive resource use when trucks pick up empty bins. Therefore, to overcome these issues, this system is introduced. In this system ML technique (Support Vector Machine) is used for Smart Waste Management System. The objective of this proposed system is to classify dustbins as either filled or empty for efficient waste management. The methodology involves several stages like input dataset will be pre-processed to remove noise and to remove unwanted. Then relevant features are extracted and selected for classification. The trained SVM classifier predicts the dustbin status. Therefore, this system demonstrates the accurate feature selection to enhances the prediction performance like reduce labour costs, to optimize waste collection operations, and contribute to cleaner urban environments by enabling proactive management of waste bins. So, by using this system, dust bin can predict each and every area by taking last data as input values (such as weight of dustbin and time taken to fill the dustbin) and trained with machine learning technique.