IOT Based Train Accident Detection System and the Loco-Pilot Health Issue Monitoring Using Yolo Model

Aim: The Present research focus on developing IoT-based Train Accident Detection and Loco Pilot Health Monitoring System based on the YOLOv5 model with real-time object detection and wearable IoT sensors for day-to-day health monitoring by Cameras and sensors. Materials and Methods: This Research is based upon two groups. Group 1: Existing method for accident detection and loco-pilot health monitoring relies mainly on Mask R-CNN monitoring systems and manual reporting systems. Group 2 The proposed IoT-based train accident detection system and loco-pilot health monitoring using the YOLOv5 model provide a more advanced automated solution. Result: The proposed YOLOv5 system had a mean accuracy of 95%, whereas the current Mask R-CNN model had 89%, which is less. The independent samples test validated that this increase in accuracy was statistically significant at 0.036. Conclusion: The research illustrates that the system based on YOLOv5 guarantees real-time detection and better performance with timely alerts to avoid accidents and increase loco pilot safety