Abstract:
This study developed an IoT-enabled system integrated with machine learning for real-time ambulance tracking and patient health monitoring, emphasizing data security. The system continuously captures vital signs such as temperature, heart rate, and oxygen saturation, improving care coordination between ambulances and hospitals. Due to ethical and logistical constraints, the machine learning model was trained using secondary data from patients transported in ambulances And Testing was performed with normal individuals in private cars instead of real-time ambulance data. However, the alternative approach using this secondary data and private car testing has proven effective. The Isolation Forest Algorithm was employed for anomaly detection, and the system provides real-time alerts via buzzer, and on-screen notifications. Patient data is transmitted from sensors to a server and displayed on dashboards developed with Python’s framework Flask and SQL Server Database. The system successfully demonstrated its ability to track ambulances and monitor patient conditions. The prototype and dashboards confirmed the system’s effectiveness in enhancing emergency care through real-time in-ambulance patient health monitoring.
