ML Based Rank Attack Detection for Smart Hospital Infrastructure
37
Fig. 7. Power tracking per each mote
Fig. 8. Evolution of anomaly detection rate
6 Conclusion
In this paper, we propose an intrusion detection system “IDS” for smart hospital infrastructure data protection. The chosen IDS is centralized and anomaly
based using a machine learning algorithm OSVM. Simulation results show the
efficiency of the approach by a high detection accuracy which is more precise
when the number of malicious nodes increases. As future work, we are interested
in developing a machine learning based IDS for more RPL attacks detection. Furthermore, we aim to extend this solution to anomaly detection in IoT systems
composed not only of WSN networks but also of cloud-based services.
37
Fig. 7. Power tracking per each mote
Fig. 8. Evolution of anomaly detection rate
6 Conclusion
In this paper, we propose an intrusion detection system “IDS” for smart hospital infrastructure data protection. The chosen IDS is centralized and anomaly
based using a machine learning algorithm OSVM. Simulation results show the
efficiency of the approach by a high detection accuracy which is more precise
when the number of malicious nodes increases. As future work, we are interested
in developing a machine learning based IDS for more RPL attacks detection. Furthermore, we aim to extend this solution to anomaly detection in IoT systems
composed not only of WSN networks but also of cloud-based services.