A Secure IoT-Based Biomedical Monitoring System Using Machine Learning–Driven Intrusion Detection and Data Encryption

Abstract

IoT enables continuous patient monitoring and immediate response to healthcare needs by creating a connected environment where healthcare services can interact seamlessly and continuously with one another. However, IoT-based healthcare systems represent an attractive target for cybercriminals, as they hold sensitive medical information on individuals. An IoT-based healthcare platform can be compromised through data manipulation, unauthorized access, and denial-of-service (DoS) attacks. To keep this issue from occurring, this paper describes a secure solution for the continuous monitoring of patient health through the use of IoT technology. The Secure IoT-based Biomedical Monitoring Framework (SIBMF) will utilize lightweight encryption techniques and the Machine Learning-based Intrusion Detection System (MLIDS) to enhance security for IoT users. Physiological signals from patients’ bodies (ECG, heart rate, and temperature) will be captured by IoT sensors and transmitted in an encrypted format to a cloud-based server. IoT sensors will utilize a cryptographic algorithm to encrypt their biomedical data prior to sending it to a cloud-based server, ensuring the confidentiality of patient data. MLIDS will detect unauthorized suspect access to the IoT network by analyzing the features of the traffic created by the IoT devices. A prototype of the SIBMF was built in MATLAB, and various performance metrics (i.e., accuracy, detection rate, false positive rate, data encryption time, and latency) were assessed. The experimental results demonstrate that this approach significantly improves data security and will provide superior accuracy for monitoring patients’ health and has minimal computational requirements.