Facemask Detection for Passengers’ Safety Using Green Technology by Fine Tuning on Object Detection Model in IoT

This study presents a green approach for recognizing face masks, a vital public transportation security measure in Internet of Things (IoT) systems. Fine-tuning an object recognition algorithm to accurately recognize persons wearing face masks utilizing green methods is offered. The research analyzes a large accident and vehicle dataset utilizing fine tuning and cutting-edge data analysis and visualization methods. The research focuses on IoT accident characteristics such as mortality rates, vehicle movements, driver gender, travel aims, road types, and day of the week. To understand the dataset, bar charts and pie charts are created. These visuals show the investigation's key findings. The study also evaluates the relationship between accidents and automobile manufacturers to identify possible causes. This research uses green methods to handle and manipulate vast amounts of data and fine-tune characteristics. Analysis of the dataset for trends and correlations aids public transport safety standards. Face mask detection is a key component of IoT for passenger safety, especially in preventing dangerous illnesses. The object detection model must be refined to recognize mask-wearers. This study involves training the model with relevant datasets and optimizing its performance to recognize masks accurately. Integrating relevant technology simplifies green object detection. The study's findings illuminate passenger face mask usage, accident causes, and face mask regulatory effectiveness. The results may assist transportation authorities and decision-makers in designing passenger-safe rules and legislation. This study presents a face mask identification approach to improve public transportation safety. The recommended method fine-tunes an object recognition model utilizing green IoT approaches to recognize persons wearing face masks. The research analyzes accident and vehicle data utilizing IoT data analysis and visualization. The research examines accident characteristics such as deaths, vehicle movements, driver gender, trip goals, road types, and day of the week. Bar and pie charts are used to display the results. The research also examines automaker– accident links. The project aims to improve IoT safety by analyzing accident trends and promoting passenger face mask usage.