Scholarlink

The Internet of Things is progressively becoming prevalent in different industries, including medicine and healthcare. Implementing the Internet of Medical Things (IoMT) offers substantial advantages in diagnosis and treatment. Nonetheless, the IoMT-based healthcare system encounters security concerns that adversely impact the quality of therapy and directly jeopardize patient health. Many studies have employed Machine Learning to detect network intrusion on IoMT systems; however, most utilize supervised learning techniques. This research presents a detection method employing unsupervised machine learning algorithms to identify potential future attack techniques. The proposed approach incorporates the concept of Explainable AI to identify significant elements that enhance prediction accuracy. We evaluated three distinct algorithms: Kmeans, One Class SVM, and Autoencoder. The One-Class SVM model demonstrated superior performance, with an accuracy of 99.87%, a false positive rate of below 2.6%, a true positive rate of 99.98% on the CIC-IoMT2024 dataset.

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

An Efficient Explainable Unsupervised Machine Learning Approach for Network Intrusion Detection in IoMT

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Van Le,
  • Hai Minh Tran,
  • Quang Minh Tran,
  • Tung Bui

摘要

The Internet of Things is progressively becoming prevalent in different industries, including medicine and healthcare. Implementing the Internet of Medical Things (IoMT) offers substantial advantages in diagnosis and treatment. Nonetheless, the IoMT-based healthcare system encounters security concerns that adversely impact the quality of therapy and directly jeopardize patient health. Many studies have employed Machine Learning to detect network intrusion on IoMT systems; however, most utilize supervised learning techniques. This research presents a detection method employing unsupervised machine learning algorithms to identify potential future attack techniques. The proposed approach incorporates the concept of Explainable AI to identify significant elements that enhance prediction accuracy. We evaluated three distinct algorithms: Kmeans, One Class SVM, and Autoencoder. The One-Class SVM model demonstrated superior performance, with an accuracy of 99.87%, a false positive rate of below 2.6%, a true positive rate of 99.98% on the CIC-IoMT2024 dataset.