Hybrid ANN–XGBoost Framework for Intelligent Intrusion Detection in Internet of Medical Things Networks

The rapid expansion of the Internet of Medical Things (IoMT) connects diverse medical devices and healthcare systems, significantly increasing the cybersecurity attack surface. To address these vulnerabilities, this research presents a hybrid Artificial Neural Network (ANN) and Extreme Gradient Boosting (XGBoost) framework designed for intelligent intrusion detection in IoMT environments. The methodology integrates the nonlinear representation capabilities of an ANN with the robust ensemble learning performance of XGBoost using a weighted probability averaging mechanism. The development workflow spans data acquisition, preprocessing, feature engineering, and model integration. In comparative evaluations reported in the paper, the hybrid ANN-XGBoost model achieved an accuracy of 98.6%, a precision of 0.983, a recall of 0.989,

and an F1-score of 0.986, outperforming standalone models such as Logistic Regression (95.4%), Random Forest (97.6%), standalone ANN (97.1%), and standalone XGBoost (97.8%). Additionally, the hybrid framework demonstrated a ROC-AUC of 0.99. This methodology-oriented framework provides a strong foundation for M.Tech researchers seeking to implement and evaluate advanced ensemble techniques for securing sensitive healthcare networks against evolving cyber threats.

Message: Hi FE, I need help with “Hybrid ANN–XGBoost Framework for Intelligent Intrusion Detection in Internet of Medical Things Networks” in “Electronics & Communication Engineering”