ARCHIVES

The intensive implementation of Medical Internet of Things tools has enhanced the efficiency of patient monitoring but has also exposed the system to more cyber threats likely to compromise data integrity and reliability of the devices. The given paper introduces a real time cybersecurity monitoring system, which is developed according to a simulated medical IoT environment. The architecture consists of data simulation, anomaly detection, and rule based risk assessment integrated into an interactive monitoring dashboard proposed. It is completely implemented in Python and Streamlit, and it allows seeing the behavior of the devices without using external storage systems. Artificial medical device data in terms of heart rate, temperature, blood pressure and battery condition is produced to simulate normal and attack conditions. The abnormal behavioral patterns are detected in real-time with the help of a machine learning model that is based on unsupervised anomaly detection. Simultaneously, a rule based engine tests various security conditions such as abnormal vital range, validation of device identity, consistency of timestamps and reliability of signals. To enhance its interpretability and reliability, outputs of both the detection layers are used to generate alerts. The dashboard has real time charts, alerts and mitigation recommendations like device blocking or quarantine. The system shows the effectiveness of hybrid-based methods in an effective medical IoT security monitoring interface. The present work illuminates that it is possible to apply lightweight analytics and visualization tools to enable proactive cyber risk awareness in healthcare-linked devices.