Real-Time Mapping of Epidemic Spread and Public Alert System Using Machine Learning

The paper presents a prototype web application for real-time epidemic monitoring, visualization, and alerting. The system integrates a CSV-backed case dataset, an optional machine-learning symptom classifier, server-side simulation of case updates, interactive geospatial visualization using Folium, and SMTP-based email alerts triggered by configurable thresholds. Real-time updates are broadcast to connected clients using Flask-SocketIO. This prototype is implemented in Python (Flask) and demonstrates a lightweight, deployable architecture suitable for rapid public-health dashboards, community reporting, and early-warning alerts. Results from the prototype show how streaming updates, map visualizations, and automated email notifications can be combined to provide situational awareness for regional epidemic spread. We discuss design choices, limitations, and directions for future work including robust data ingestion, multi-process deployment, and model-driven predictions.