Drift-Aware Resilient Ensemble Deep Learning-based Anomaly Detection Model in Internet of Medical Things
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 January 2026
,
Page 1-8
https://doi.org/10.22037/ijmtfm.v16.52740
Abstract
Background: The rapid advancement of the Internet of Medical Things (IoMT) has facilitated continuous health monitoring and real-time physiological data collection. Artificial intelligence, particularly machine learning and deep learning techniques, has become widely employed for anomaly detection.
Methods: This research proposes a novel Drift-Aware Resilient Ensemble Deep Learning-based Anomaly Detection Model in Internet of Medical Things Environments (DREAM-IoMT). The proposed method employs a hybrid feature selection strategy integrating Gini-index, recursive feature elimination, and SelectFromModel. For anomaly detection and classification, the proposed DREAM-IoMT model employs a weighted-voting ensemble of a graph convolutional network, a bidirectional temporal convolutional network, and an improved conditional variational autoencoder. This ensemble approach enhances accuracy by accounting for each classifier’s prediction confidence. The ensemble classification model is further optimized using AdamW.
Results: The DREAM-IoMT model achieved an accuracy of 98.74%, demonstrating superior anomaly detection performance compared with existing methodologies.
Conclusion: The proposed DREAM-IoMT effectively combines feature selection and weighted ensemble deep learning for reliable anomaly detection in IoMT environments.
- Internet of Medical Things
- Anomaly Detection
- Hybrid Feature Selection
- Ensemble Classifier
- Hyperparameter Tuning
How to Cite
References
[1] Li X, Xie C, Zhao Z, Wang C, Yu H. Anomaly detection algorithm of industrial internet of things data platform based on deep learning. IEEE Transactions on Green Communications and Networking. 2024;8(3):1037-48. [DOI: 10.1109/TGCN.2024.3403102]
[2] Zeng GQ, Yang YW, Lu KD, Geng GG, Weng J. Evolutionary adversarial autoencoder for unsupervised anomaly detection of industrial internet of things. IEEE Transactions on Reliability. 2025;74(3):3454-68. [DOI: 10.1109/TR.2025.3528256]
[3] Rodríguez M, Tobón DP, Múnera D. A framework for anomaly classification in Industrial Internet of Things systems. Internet of Things. 2025;29:101446. [DOI: 10.1016/j.iot.2024.101446]
[4] Chen Z, Li Z, Huang J, Liu S, Long H. An effective method for anomaly detection in industrial Internet of Things using XGBoost and LSTM. Sci Rep. 2024;14(1):23969. [DOI: 10.1038/s41598-024-74822-6]
[5] Abudurexiti Y, Han G, Zhang F, Liu L. An explainable unsupervised anomaly detection framework for Industrial Internet of Things. Comput Secur. 2025;148:104130. [DOI: 10.1016/j.cose.2024.104130]
[6] Riaz R, Han G, Shaukat K, Khan NU, Zhu H, Wang L. A novel ensemble Wasserstein GAN framework for effective anomaly detection in industrial internet of things environments. Sci Rep. 2025;15(1):26786. [DOI: 10.1038/s41598-025-07533-1]
[7] Luo S, Zeng P, Ma C, Wei Y. Anomaly detection for industrial Internet of Things devices based on self-adaptive blockchain sharding and federated learning. Journal of Communications and Networks. 2025;27(2):92-102. [DOI: 10.23919/JCN.2025.000019]
[8] Wang R, Qiu H, Cheng X, Liu X. Anomaly detection with a container-based stream processing framework for industrial internet of things. Journal of Industrial Information Integration. 2023;35:100507. [DOI: 10.1016/j.jii.2023.100507]
[9] Tang L, Xue C, Zhao Y, Chen Q. Anomaly detection of service function chain based on distributed knowledge distillation framework in cloud-edge industrial internet of things scenarios. IEEE Internet Things J. 2023;11(6):10843-55. [DOI: 10.1109/JIOT.2023.3327795]
[10] De Vita F, Nocera G, Bruneo D, Das SK. A novel echo state network autoencoder for anomaly detection in industrial IoT systems. IEEE Transactions on Industrial Informatics. 2022;19(8):8985-94. [DOI: 10.1109/TII.2022.3224981]
[11] Prasad DV, Saraswathi S. The role of anomaly detection in industry 4.0: a survey of techniques and applications. Journal of Trends in Computer Science and Smart Technology. 2024;6(2):125-38. [DOI: 10.36548/jtcsst.2024.2.003]
[12] Bouke MA, Abdullah A, Frnda J, Cengiz K, Salah B. BukaGini: a stability-aware Gini index feature selection algorithm for robust model performance. IEEE Access. 2023;11:59386-96. [DOI: 10.1109/ACCESS.2023.3284975]
[13] Toor MS, Shahbaz H, Yasin M, Ali A, Fitriyani NL, Kim C, Syafrudin M. An optimized weighted-voting-based ensemble learning approach for fake news classification. Mathematics. 2025;13(3):449. [DOI: 10.3390/math13030449]
[14] Kingma DP, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR); 2015 May 7-9; San Diego, CA. [DOI: 10.48550/arXiv.1412.6980]
[15] Hua J, Li C. Distributed robust Bayesian filtering for state estimation. IEEE Transactions on Signal and Information Processing over Networks. 2018;5(3):428-41. [DOI: 10.1109/TSIPN.2018.2889579]
[16] Annamalai U. WUSTL-IIOT-2021 dataset [dataset]. Kaggle. [Link]
[17] Dataset Engineer. Cybertec IIoT malware dataset (CIMD 2024) [dataset]. Kaggle. [Link]
[18] Zia S, Bibi N, Alhazmi S, Muhammad N, Alhazmi A. Enhanced anomaly detection in iot through transformer-based adversarial perturbations model. Electronics. 2025;14(6):1094. [DOI: 10.3390/electronics14061094]
[19] Zakariah M, Almazyad AS. Anomaly detection for IoT systems using active learning. Appl Sci. 2023;13(21):12029. [DOI: 10.3390/app132112029]
[20] Rhachi H, Balboul Y, Bouayad A. Enhanced anomaly detection in IoT networks using deep autoencoders with feature selection techniques. Sensors. 2025;25(10):3150. [DOI: 10.3390/s25103150]
- Abstract Viewed: 0 times
- PDF Downloaded: 0 times