A Deep Ensemble Intrusion Detection System for the Internet of Things Enabled Wearable Computing Systems

Technological advancements are playing a significant role in protecting data from intruders. This paper uses deep learning approaches to propose a robust network Intrusion Detection System (IDS) for the Internet of Things enabled wearable computing systems. The significance of IoT in Wearable Computing Systems used in healthcare is paramount. The types of intrusions we have detected in this work are Distributed Denial of Service (DDoS) and replay attacks. The work was carried out in three stages: (a) node deployment, (b) threat detection modeling, and (c) prevention modeling. An ensemble algorithm has been proposed for detection using Deep Neural Network (DNN) and Support Vector Machine (SVM). SVM is used to identify the suspected route, and DNN is employed to identify the suspected node from the suspected routes. The chosen route ensures that it is prevented from attackers by incorporating the Throughput and Packet Delivery Ratio (PDR). The simulation results are obtained based on accuracy, recall, precision, and F -measure to determine the effectiveness of the proposed approach. The precision, recall, F- measure, and accuracy of correctly identified intruders are <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 8. 1 2 \%, ~} \mathbf{9 8. 0 4 \%, ~} \mathbf{9 4. 8 8 \%}$</tex>, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 8. 6 8 \%}$</tex>, respectively, which is an improvement over the previous studies. The efficacy of the designed model for IoT is compared with the existing state-of-the-art approaches.