A tree classifier based network intrusion detection model for Internet of Medical Things. (September 2022)

• Record Type: Journal Article
• Authors: Gupta, Karan; Sharma, Deepak Kumar; Datta Gupta, Koyel; Kumar, Anil
• Is Part Of: Computers & electrical engineering. Volume 102(2022)
• Publication Date: 2022-09
• Subjects: Internet of Medical Things -- Intrusion detection -- Tree classifier -- Security -- Estimator; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108158
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Healthcare is one of the key areas of prospect for the Internet of Things (IoT). To facilitate better medical services, enormous growth in the field of the Internet of Medical Things (IoMT) is observed recently. Despite the numerous benefits, the cyber threats on connected healthcare devices can compromise privacy and can also cause damage to the health of the concerned patient. The massive demand for IoMT devices with seamless and effective medical facilities for the large-scale population requires a robust secured model to ensure the privacy and safety of patients in this network. However, designing security models for IoMT networks is very challenging. An effort has been made in this work, to design a tree classifier-based network intrusion detection model for IoMT networks. The proposed system effectively reduces the dimension of the input data to speed up the anomaly detection procedure while maintaining a very high accuracy of 94.23%. Graphical abstract: Highlights: Protect the sensor's biometric and network data from cyber-attacks. Ensure the privacy and safety of the patients in both wired and wireless networks. Use of robust scaling with the random forest under hyperparameter tuning. Data Augmentation significantly improved in benchmarking the result. Increase accuracy by 4.19% in classification results.