Paper Title
Biomedical Waste Management Through Segregation Using CNN and YOLO

Abstract
To protect the public's health and safety, biological waste must be properly separated. In this study, the segregation of biological waste is automated using computer vision techniques. The device makes use of a camera module that takes pictures of the biological waste and uses machine learning techniques to process them. A variety of categories, including infected, non-infectious, recyclable, and non-recyclable garbage, are created by the algorithm for classifying waste. Any waste produced during medical procedures, such as the diagnosis, treatment, or immunization of people or animals, is referred to as biomedical waste. It consists of abandoned medical items such bandages, gloves, syringes, needles, and syringes. The spread of viruses and diseases as a result of inadequate biomedical waste disposal might constitute a serious hazard to public health. In comparison to the human segregation procedure, the employment of computer vision algorithms in biological waste segregation offers a substantial advantage. The method decreases the possibility of contamination and gets rid of human mistakes. The technology is also scalable and capable of quickly handling massive amounts of garbage. The project's goal is to offer a dependable and effective system for segregating biological waste that will enhance public health and safety. Keywords - Biomedical waste, Segregation, Health care, Convolutional Neural Network, Machine learning, Waste management, Environmental Protection