Intelligent Cybersecurity Ontology Framework for Internet of Medical Things -Enabled Remote Patient Monitoring

In recent years, the Internet of Medical Things (IoMT) has evolved in Remote Patient Monitoring (RPM) through a digitally connected ecosystem of medical devices, medical sensors, and cloud platforms which enabling mechanism for continuous collection, exchange, and analysis of health data. Existing IoMT ontology-based method provide a defined and orderly representation of the threats and vulnerabilities but remain limited due to their static nature, with the inability to adapt and account for new attacks, and offer no automatic defense capabilities. To overcome these challenges, this research proposes an Intelligent Cybersecurity Ontology Framework (ICOF) that employs ontology-driven representation of knowledge representation with semantic reasoning based on description logic to infer device risks associated with each vulnerability. After that, the ICOF framework incorporates graph-based learning techniques, enabling the discovery of complex attack patterns and hidden relationships across IoMT networks. This integration supports proactive mitigation, semantic interoperability, and resilient cybersecurity in IoMT-enabled RPM environments. Experimental results demonstrate ICOF model provide an average accuracy of 98.69% for digital temperature sensor readings and 98.43% for pulse sensor readings across 5 users when compared with Blockchain-based IoT for real-time secured medical management.