Real-Time Anomaly Detection in IoMT Networks Using Stacking Model and a Healthcare- Specific Dataset
Bibliographic record
Abstract
The Internet of Medical Things (IoMT) connects medical devices to enable real-time monitoring and personalized care, significantly enhancing patient health and well-being. However, this connectivity also introduces substantial cybersecurity risks, including various attack types that compromise data integrity and availability, jeopardizing patient safety and healthcare service reliability. This study addresses these challenges by proposing a real-time anomaly detection model based on machine learning (ML) techniques, designed to detect and mitigate diverse cyber threats effectively. This paper proposes a new medical dataset for anomaly detection, inspired by the UNSW-NB15 dataset, and enriched with healthcare-relevant attack types, including falsification and DoS attacks, to reflect real-world IoMT scenarios. The dataset comprises 253,680 records, with 60% anomalous data distributed across multiple attack types, offering a more challenging and realistic environment for evaluating ML models. Seven machine learning algorithms, including Random Forest, XGBoost, and Artificial Neural Networks (ANN), were rigorously tested, leading to the development of a novel stacking ensemble model. This model integrates XGBoost as the meta-learner with Random Forest and ANN as base models, leveraging their strengths to optimize anomaly detection. The proposed model was evaluated on both the UNSW-NB15 and the new medical dataset, achieving significant improvements across key metrics such as accuracy, precision, recall, and F1-score. A real-time prediction analysis further demonstrated its ability to detect anomalies efficiently during live data transmission, validating its suitability for detecting anomalies in real-time scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".