• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2024, Volume: 17, Issue: 5, Pages: 386-396

Original Article

Combination of One-Class and Multi-Class Anomaly Detection Using Under-Sampling and Ensemble Technique in IoT Healthcare Data

Received Date:04 July 2023, Accepted Date:02 January 2024, Published Date:23 January 2024


Objectives: This study addresses the concept drift issue in anomaly detection for IoT systems. The objective is to develop a novel approach that effectively handles the dynamic nature of IoT data. Methods: The proposed COMCADSET (Combination of One-Class and Multi-Class Anomaly Detection Using Under-Sampling and Ensemble Technique) addresses the concept drift challenge. It adapts to evolving data distributions, detects anomalies in IoT healthcare data, mitigates class distribution imbalances through under-sampling, and enhances performance with ensemble techniques. The approach involves four phases: multi-class anomaly spotting, one-class anomaly isolation, concept-drift-free dataset creation, and robust anomaly detection using ensembles. Evaluation utilizes the "Heart Failure Prediction" dataset from Kaggle, with comprehensive experiments and three classification algorithms. COMCADSET's innovation merges one-class and multi-class anomaly detection, under-sampling, and ensemble classification. It's compared against gold standards for classification accuracy, concept drift management, and anomaly detection performance. Findings: Conduct comprehensive experiments using a concept drift dataset and three classification algorithms to evaluate the efficacy of the COMCADSET technique. The experimental result shows the proposed COMCADSET technique attains an impressive 98.401% accuracy, decisively enhancing classification accuracy by adeptly addressing concept drift and identifying anomalies in IoT data. Early detection of abnormal behaviour prevents more significant issues and potential security vulnerabilities in IoT systems. Novelty: The novelty of the COMCADSET technique lies in its ability to address the concept drift issue and improve anomaly detection accuracy in IoT systems. By integrating one-class and multi-class anomaly detection, under-sampling, and ensemble techniques, the proposed approach provides a robust solution for handling the dynamic nature of IoT data.

Keywords: Anomaly Detection, Concept Drift, Ensemble Classification, Internet of Things, Under­Sampling


  1. Jiang J, Liu F, Liu Y, Tang Q, Wang B, Zhong G, et al. A dynamic ensemble algorithm for anomaly detection in IoT imbalanced data streams. Computer Communications. 2022;194:250–257. Available from: https://doi.org/10.1016/j.comcom.2022.07.034
  2. Chatterjee A, Ahmed BS. IoT anomaly detection methods and applications: A survey. Internet of Things. 2022;19:1–17. Available from: https://doi.org/10.1016/j.iot.2022.100568
  3. Togbe MU, Chabchoub Y, Boly A, Barry M, Chiky R, Bahri M. Anomalies Detection Using Isolation in Concept-Drifting Data Streams. Computers. 2021;10(1):1–21. Available from: https://doi.org/10.3390/computers10010013
  4. Šabić E, Keeley D, Henderson B, Nannemann S. Healthcare and anomaly detection: using machine learning to predict anomalies in heart rate data. AI & SOCIETY. 2021;36(1):149–158. Available from: https://doi.org/10.1007/s00146-020-00985-1
  5. Abu-Alhaija M, Turab NM. Automated Learning of ECG Streaming Data Through Machine Learning Internet of Things. Intelligent Automation & Soft Computing. 2022;32(1):45–53. Available from: https://doi.org/10.32604/iasc.2022.021426
  6. Wu Y, Dai HNN, Tang H. Graph Neural Networks for Anomaly Detection in Industrial Internet of Things. IEEE Internet of Things Journal. 2022;9(12):9214–9231. Available from: https://doi.org/10.1109/JIOT.2021.3094295
  7. Bhatti MA, Riaz R, Rizvi SS, Shokat S, Riaz F, Kwon SJ. Outlier detection in indoor localization and Internet of Things (IoT) using machine learning. Journal of Communications and Networks. 2020;22(3):236–243. Available from: https://doi.org/10.1109/JCN.2020.000018
  8. Ding C, Zhao J, Sun S. Concept Drift Adaptation for Time Series Anomaly Detection via Transformer. Neural Processing Letters. 2023;55:2081–2101. Available from: https://doi.org/10.1007/s11063-022-11015-0
  9. Razak MSA, Nirmala CR, Aljohani M, Sreenivasa BR. A novel technique for detecting sudden concept drift in healthcare data using multi-linear artificial intelligence techniques. Frontiers in Artificial Intelligence. 2022;5:1–14. Available from: https://doi.org/10.3389/frai.2022.950659
  10. Gemaque RN, Costa AFJ, Giusti R, Santos EMd, . An overview of unsupervised drift detection methods. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2020;10(6):1–18. Available from: https://doi.org/10.1002/widm.1381


© 2024 Subha & Sathiaseelan. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.