DESIGN AND ANALYSIS OF INTRUSION DETECTION SYSTEM USING MACHINE LEARNING IN SMART HEALTHCARE SYSTEM

Abstract

The integration of the Internet of Things (IoT) in medical applications into healthcare applications has enabled the remote monitoring of patients' information, facilitating timely diagnostics as required. The technology of the Internet of Medical Things (IoMT) empowers doctors to treat patients through real-time monitoring and remote diagnostics. Nevertheless, implementing high-security features that ensure the accuracy and confidentiality of patients' data poses a substantial challenge. IoMT devices have limited processing power and memory, making it impossible to build security technology on them. Methodology: So the proposed work formulates a machine learning-based topology to construct an efficient and precise intrusion detection system using network traffic and patient data. Findings: In this topology, modified Whale optimization topology has been implemented for feature selection, and the intrusion is detected using two ML algorithms namely, Random Forest and SVM. Hence, the proposed method surpasses the current state-of-the-art, achieving an accuracy rate of 99.82%.

Keywords

• intrusion detection system (ids)
• network attacks
• svm
• random forest (rf)