| Form of studies |
Bachelor |
| Title of the study programm |
Computer Systems |
| Title in original language |
IoT ierīču integrācija un drošības pārvaldība veselības aprūpē. |
| Title in English |
Integration and Security Management of IoT Devices in Healthcare. |
| Department |
Faculty Of Computer Science Information Tehnology And Energy |
| Scientific advisor |
Imants Gorbāns |
| Reviewer |
Aigars Riekstiņš |
| Abstract |
This bachelor thesis addresses the critical cybersecurity and integration challenges posed by the Internet of Medical Things (IoMT) in modern healthcare systems. As medical facilities increasingly rely on interconnected devices—ranging from smart infusion pumps to implantable pacemakers—the attack surface grows, exposing both patients and systems to unprecedented digital threats. Through a comprehensive analysis of architectural models, threat vectors, and regulatory frameworks (HIPAA, GDPR, and NIS2), this research highlights the unique vulnerabilities of IoMT environments, including outdated firmware, weak encryption, and flawed access control.
To address these challenges, the thesis proposes and implements an IoMT Security Framework that combines real-time anomaly detection using a decentralized neural network trained via Swarm Learning, with immutable attack logging powered by Hyperledger Fabric. The solution ensures high detection accuracy without compromising patient privacy, in alignment with Zero Trust principles. Practical deployment scenarios in ICU networks and smart medical devices demonstrate the framework's effectiveness in identifying anomalies and providing verifiable security logs. The results confirm the framework’s feasibility for real-time use in clinical settings and its contribution to regulatory compliance, operational resilience, and patient safety. |
| Keywords |
IoT, Datortīkls,Kiberdrošība,Datu konfidencialitāte,AI |
| Keywords in English |
IoT, Networks,Cybersecurity,Data Privacy,AI |
| Language |
eng |
| Year |
2025 |
| Date and time of uploading |
27.05.2025 23:35:35 |
