Akilli algoritmalara dayali nesnelerin interneti için dayanikli İdS tasarimi

The vulnerabilities of the Internet of Things (IoTs) in general and the Internet of Mobility Things (IoMTs) in particular motivate researchers to equip them with security systems against intruders and attacks. The integration of anomaly detection with intrusion detection for IoMTs has not been addressed adequately. This study tackles this issue through building a Kalman and Cauchy clustering for anomaly detection and using it for authentication nodes within IoMTs using the Extreme Learning Machine (ELM) classifier. The algorithm is composed of various components; firstly, the Kalman filter-based model for estimating the trajectory of pedestrians within an indoor environment based on fusing WiFi with IMU data. Secondly, trustworthiness assessment for detecting anomaly behaviour in IoMT based on the estimated trajectory using the Kalman filter. Thirdly, the trust IDS model for IoMT systems by integrating anomaly detection with online learning for attacks identification using an Online Sequential Extreme learning machine(OSELM). The OSELM algorithm has been implemented and evaluated using TamperU dataset for WiFi fingerprinting and KDD99 for intrusion detection. Furthermore, a comparison with benchmarks for intrusion detection and anomaly detection proves the superiority of the proposed approach in terms of all the considered classification metrics. The developed algorithm was compared with two existing models for anomaly detection, namely, a multi-density clustering algorithm for evolving data stream (MUDI) and fully online clustering of evolving data streams into arbitrarily shaped clusters (CEDAS). The results proved the superiority of the developed algorithm in this work in terms of anomaly and intrusion detection under three different scenarios that include different percentages of added anomalies, different numbers of pedestrians, and different average speeds of pedestrians.