Title: Intrusion detection using a SV-SMOTE method in IoMT

Authors: Yonglai Zhang

Addresses: North University of China, Shanxi, 030051, China

Abstract: Intrusion detection for the internet of medical things (IoMT) is particularly important as the problem of network attacks. Network security has become more serious during the COVID-19 pandemic. To address the problem that edge servers in IoMT are vulnerable to network traffic attacks, we propose a SV-SMOTE oversampling algorithm, and construct an IoMT intrusion detection model with machine learning algorithms as the main body. Using a benchmark dataset of network attacks, the random forest, oversampling and XGBoost algorithms are used in the proposed model for intrusion detection comparison experiments, respectively. This study makes a significant research contribution by proposing a new methodological approach to unbalanced data sets, which can lead to improved performance of classification models. The experimental results show that the proposed method can effectively detect network traffic attacks.

Keywords: SV-SMOTE; random forest; XGBoost; internet of medical things; IoMT; intrusion detection.

DOI: 10.1504/IJMIC.2024.139090

International Journal of Modelling, Identification and Control, 2024 Vol.44 No.4, pp.294 - 302

Received: 20 Dec 2022
Accepted: 17 Feb 2023
Published online: 13 Jun 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article