Enhanced threat detection in health care systems with random coupled bootstrapped ensemble classifier

Area of Science:

• Cybersecurity
• Health Informatics
• Machine Learning

Background:

• Modern healthcare faces significant patient data protection challenges due to the integration of Internet of Things (IoT) technologies.
• Existing cybersecurity measures struggle to effectively detect sophisticated cyberattacks in interconnected healthcare environments.
• Ensuring patient confidentiality and system integrity is paramount in the evolving landscape of digital health.

Purpose of the Study:

• To introduce an advanced intrusion detection framework, the Random Coupled Bootstrapped Ensemble Classifier (RCBEC), for smart healthcare environments.
• To optimize the RCBEC model for enhanced accuracy, computational efficiency, and precision in identifying cyber threats.
• To bolster the security of IoT-enabled healthcare systems and safeguard sensitive patient information.

Main Methods:

• Employed Decimal Score Max Normalization for data preprocessing, including transformation, duplicate removal, and imputation of missing values.
• Utilized K-Best Kernel Discriminant Analysis (K-BKDA) for feature extraction and the Hunter Canis Algorithm (HCA) for feature selection and optimization.
• Implemented the RCBEC model within a Python-based ECU-IoHT environment for intrusion detection.

Main Results:

• The RCBEC model achieved a high accuracy and F1-score of 99.6%, outperforming existing intrusion detection methods.
• Demonstrated rapid computational performance combined with robust threat identification capabilities.
• Showcased superior generalization and adaptability across diverse datasets in comparative analyses.

Conclusions:

• The RCBEC model provides a resilient and intelligent mechanism for detecting and mitigating cybersecurity threats in healthcare networks.
• Machine learning-driven intrusion detection significantly strengthens patient data protection, operational reliability, and trust in next-generation healthcare systems.
• The proposed framework represents a significant advancement in securing IoT-enabled healthcare infrastructure against cyberattacks.