AI-Powered Disaster Survivor Monitoring and Emergency Response System with Real-Time Analytics
Author : Dr. K Kalyani and P Abirami
Abstract :
Natural disasters such as earthquakes, floods, landslides, and cyclones cause large-scale destruction and pose significant challenges to emergency response teams. Rapid identification of survivors and accurate assessment of their medical condition are critical to reducing mortality rates. Traditional disaster response systems rely heavily on manual health inspection, verbal communication, and delayed reporting, which can lead to inefficient prioritization and increased human error. This project presents an AI-Powered Disaster Survivor Monitoring and Emergency Response System that integrates wearable health monitoring, rule-based Artificial Intelligence (AI), and real-time analytics. The system collects vital parameters such as heartbeat, body temperature, and movement status through IoT/LoRa-based devices (simulated in this implementation). Using AI-driven rule-based logic, survivors are automatically classified into three urgency levels: CRITICAL, INJURED, and STABLE. Based on classification results, the system provides automated first-aid recommendations and triggers alerts for critical cases. A web-based dashboard developed using Flask and SQLite displays real-time analytics, including survivor statistics, urgency distribution, and health trends through pie charts, bar graphs, and line charts. Experimental results demonstrate improved response efficiency, accurate classification, and enhanced decision-making support. The proposed system provides an intelligent, scalable, and data-driven solution to optimize disaster response operations and improve survival outcomes.
Keywords :
Disaster Management, Artificial Intelligence, Wearable Health Monitoring, Real-Time Analytics, Emergency Response System.
