Automated Assessment of Hospital Waste Bin Fill Ratios: A Novel AI-Driven Approach for Enhanced Waste Management and Infection Control

Medical waste management has become a very serious problem due to population growth and the use of disposable medical instruments. Traditional sensors (capacitive, optical, infrared, etc.) can have multiple limitations, medical waste being very varied, some categories having a high degree of risk. The purpose of this work is to implement a versatile and efficient system, by using as a level sensor an ESP32-CAM camera and by implementing a linear regression model, preceded by image processing operations to detect the level of waste bins in hospitals. The Mean Squared Error (MSE) and the Regression Correlation Coefficient (R2) were used to quantify the accuracy of the predictions obtained by the algorithm.