Scholarlink

<p>The Internet of Medical Things (IoMT) is becoming increasingly crucial as it revolutionizes healthcare through remote patient monitoring. The constant monitoring of patient’s health data is facilitated by IoMT devices, which enable the identification of new illnesses or health risks. The Internet enables IoMT devices to connect and share data in real-time. However, the interconnected nature of IoMT devices makes them vulnerable to various security threats. Therefore, security in IoMT is essential to protect patient privacy, ensure device availability, and mitigate the risk of cyber attacks. Motivated by this fact, this paper presents a novel Grey Wolf Optimizer (GWO) based Intrusion Detection System framework for IoMT architecture. A GWO is employed to extract the optimal set of features. The K-Nearest Neighbour classifier is used to detect malicious activities in IoMT architecture. The proposed IDS framework is evaluated over WUSTL-EHMS-2020 dataset. The proposed framework significantly decreases the input data’s dimensionality while maintaining a minimum false alarm rate. Theexperimental results show that the proposed framework outperforms the existing methods with an increase in accuracy and AUC scores by 3.11% and 4.53%, respectively.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel Grey Wolf optimizer-based IDS framework in IoMT

  • 期刊论文

  • 发表日期：

    2026年2月20日

查看全文
  • Yogendra Kumar,
  • Vijay Kumar

摘要

The Internet of Medical Things (IoMT) is becoming increasingly crucial as it revolutionizes healthcare through remote patient monitoring. The constant monitoring of patient’s health data is facilitated by IoMT devices, which enable the identification of new illnesses or health risks. The Internet enables IoMT devices to connect and share data in real-time. However, the interconnected nature of IoMT devices makes them vulnerable to various security threats. Therefore, security in IoMT is essential to protect patient privacy, ensure device availability, and mitigate the risk of cyber attacks. Motivated by this fact, this paper presents a novel Grey Wolf Optimizer (GWO) based Intrusion Detection System framework for IoMT architecture. A GWO is employed to extract the optimal set of features. The K-Nearest Neighbour classifier is used to detect malicious activities in IoMT architecture. The proposed IDS framework is evaluated over WUSTL-EHMS-2020 dataset. The proposed framework significantly decreases the input data’s dimensionality while maintaining a minimum false alarm rate. Theexperimental results show that the proposed framework outperforms the existing methods with an increase in accuracy and AUC scores by 3.11% and 4.53%, respectively.