Extreme learning machine and bayesian optimization-driven intelligent framework for IoMT cyber-attack detection.

Area of Science:

• Computer Science
• Biomedical Engineering
• Healthcare Technology

Background:

• The Internet of Medical Things (IoMT) integrates medical devices for enhanced healthcare services, enabling data communication and personalized care.
• Ubiquitous IoMT devices present significant security and data privacy risks due to connectivity and resource limitations.
• Vulnerabilities in IoMT systems can lead to unauthorized access of sensitive health data and potential patient harm.

Purpose of the Study:

• To propose a novel IoMT framework to address critical security and data privacy concerns.
• To enhance the protection of IoMT devices and sensitive patient information.
• To improve the accuracy and effectiveness of decision-making processes in IoMT security.

Main Methods:

• A hybrid framework combining Bayesian optimization and Extreme Learning Machine (ELM) was developed.
• The proposed model was evaluated for its performance in securing IoMT devices and data.
• Comparative analysis against existing state-of-the-art methods was conducted.

Main Results:

• The proposed IoMT framework demonstrated encouraging performance.
• Enhanced accuracy in the decision-making process was achieved compared to existing methods.
• The model effectively addresses security vulnerabilities and enhances data privacy.

Conclusions:

• The hybridized Bayesian optimization and ELM model offers a robust solution for IoMT security and data privacy.
• This framework improves the reliability and safety of connected healthcare systems.
• The proposed approach represents a significant advancement in securing the Internet of Medical Things.