Intrusion Detection for Internet of Medical Things (IoMT) using Extreme Learning Machine

The proliferation of Internet of Medical Things (IoMT) devices in healthcare requires robust intrusion detection systems to safeguard sensitive data and ensure patient safety. This study presents a novel approach utilizing Extreme Learning Machine (ELM) architectures for intrusion detection in IoMT environments, leveraging the WUSTL-EHMS-2020 dataset. Addressing the prevalent issue of class imbalance, we compare the impact of Synthetic Minority Over-sampling Technique (SMOTE), weighted loss functions, and a hybrid over- and under-sampling strategy to enhance detection accuracy. Our research implements and evaluates multiple ELM architectures, comparing their performance in terms of accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). The results demonstrate that the weighted loss function method significantly improves the detection capabilities of ELMs, providing an effective solution for real-time intrusion detection in healthcare IoMT systems.