Enhanced Intrusion Detection System for IoMT Devices Using Improved Human Evolutionary Optimization Algorithm and Tabular Transformers

The Internet of Medical Things (IoMT) has revolutionized healthcare by enabling real-time monitoring, intelligent diagnostics, and remote patient care. However, the widespread adoption of IoMT devices has introduced significant cybersecurity challenges. An Intrusion Detection System (IDS) is an essential tool designed to overcome these cybersecurity threats. This research presents a novel Intrusion Detection System (IDS) framework namely IHEOA-Tab that combines Improved Human Evolutionary Optimization Algorithm (IHEOA) for feature selection and Tabular Transformers for classification. First, healthcare intrusion detection system dataset namely CIC-IoMT2024 has been selected. Second, an improvement to the existing Human Evolutionary algorithm has been proposed. Besides, this IHEOA is used for selecting the crucial features from the dataset. Third, Tabular Transformers with self-attention mechanisms is employed for building the model and test it. The proposed model is evaluated using various performance measures such as accuracy, precision, recall and F1-score and confusion matrix in both binary and multiclass classification. The model achieved near-perfect classification performance, with minimal misclassifications.