Keywords
online anomaly detection
micro-clustering
Abstract
IoT sensor networks generate continuous data streams from temperature, humidity, vibration, pressure, current, and device-status signals. These streams often contain gradual drift, repeated short-term fluctuations, and rare abnormal events, making conventional clustering-based anomaly detection prone to adaptation fatigue and missed anomalies. This study proposes a habituation-resistant micro-cluster updating method for online anomaly detection in IoT sensor streams. The proposed method maintains compact micro-clusters for normal patterns and introduces a response-decay control mechanism to prevent frequently repeated but suspicious deviations from being absorbed too quickly into normal clusters. A temporal density adjustment module is further used to distinguish persistent concept drift from abrupt abnormal behavior. Experiments are conducted on an IoT monitoring dataset containing 1,260 sensor nodes, 38 streaming variables, and 5-second observations collected over 84 days. The dataset includes 42.7 million streaming records and 1,940 annotated abnormal segments, including sensor freezing, abnormal vibration bursts, battery instability, communication delay, and device overheating. The proposed method reduces median detection delay from 46 seconds to 14 seconds compared with a standard DenStream baseline. False alarms decrease to 2.3 events per sensor-week, while the Matthews correlation coefficient reaches 0.908 under mixed drift and burst-anomaly conditions. The online update module processes 31,000 records per second with a memory footprint of 620 MB. Cluster stability analysis shows that the average normal-cluster displacement remains below 0.18 standard units during gradual environmental drift. These results indicate that habituation-resistant clustering can improve real-time anomaly detection in large-scale IoT data streams.
References
1. Zhang, Z., Gao, Y., & Tong, Y. (2026). Semantic-Temporal Graph Learning for Demand Forecasting and Resource Allocation in Public Information Systems. Available at SSRN 6792279.
2. Kumar, A., Kumar, A., Raja, R., Dewangan, A. K., Kumar, M., Soni, A., ... & Saudagar, A. K. J. (2025). Revolutionising anomaly detection: a hybrid framework for anomaly detection integrating isolation forest, autoencoder, and Conv. LSTM. Knowledge and Information Systems, 67(12), 11903-11953.
3. Qi, C., & Qiao, X. (2026, May). From Traditional Machine Learning to Large Language Models: The Evolution of Infrastructure from an Engineering Perspective. In 2026 6th International Symposium on Computer Technology and Information Science (ISCTIS) (pp. 503-506). IEEE.
4. Kabir, T. (2026). Intelligent Condition Monitoring and Fault Diagnosis of Electrical Power and Control Systems Using Machine Learning–Based Predictive Analytics. American Journal of Interdisciplinary Studies, 7(01), 177-222.
5. Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
6. Trirat, P., Shin, Y., Kang, J., Nam, Y., Na, J., Bae, M., ... & Lee, J. G. (2024). Universal time-series representation learning: A survey. arXiv preprint arXiv:2401.03717.
7. Su, D., & Zhang, H. Developing a Data-Driven Computational Framework for Scalable Special Education Practices for Autism and Intellectual Disabilities in the US Public School System.
8. Ma, Y. (2026). Industrial Financial Risk Prediction Model Based on Graph Neural Network and Knowledge Graph Inference. Journal of Circuits, Systems and Computers, 35(16), 2650103.
9. Bian, J., Al Arafat, A., Xiong, H., Li, J., Li, L., Chen, H., ... & Guo, Z. (2022). Machine learning in real-time Internet of Things (IoT) systems: A survey. IEEE Internet of Things Journal, 9(11), 8364-8386.
10. Gao, G., Gao, R., Gao, R., Zhou, H., & Lu, C. (2026, March). Performance Study of Enterprise SMS Communication Scheduling Mechanisms in Triple-Play Convergence Environments. In 2026 IEEE 8th International Conference on Communications, Information System and Computer Engineering (CISCE) (pp. 82-86). IEEE.
11. Li, Y., & Liu, S. (2026, May). A Study on Dynamic Optimization of Alerting Policies and Multi-Agent Decision-Making Mechanisms in Cloud Environments. In 2026 7th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) (pp. 703-706). IEEE.
12. Musababa, M. A., & Fachrie, M. (2025). Data Streaming Pipeline Model Using DBSTREAM-Based Online Machine Learning for E-Commerce User Segmentation. Journal of Applied Informatics and Computing, 9(6), 3346-3355.
13. Xu, T., Zhu, W., & Zhang, J. (2026). Stability and Consistency of Explainable Deep Learning Methods in Credit Risk Assessment. Available at SSRN 6893938.
14. Zhou, Y., & Jia, R. (2025). Research on Driving Behavior Risk Identification and Safety Assessment Methods Based on Artificial Intelligence. Artificial Intelligence and Machine Learning Review, 6(2), 1-15.
15. Behura, A., Kumar, A., & Jain, P. K. (2025). A multi-objective approach for secure cluster based routing & attack classification in VANETs. Peer-to-Peer Networking and Applications, 18(3), 119.
16. Andreica, M., & Andreica, A. M. (2025). Vibration-induced failures in industrial ventilation systems: A predictive maintenance approach. Journal of Vibration and Control, 10775463251366352.
17. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning. arXiv preprint arXiv:2606.29354.
18. Gui, H., Wang, B., Lu, Y., & Fu, Y. (2025). Computational Modeling-Based Estimation of Residual Stress and Fatigue Life of Medical Welded Structures.
19. Mannapur, S. B. (2025). Understanding data drift and concept drift in machine learning systems. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 11(1), 318-330.
20. Chen, H., Ning, P., Li, J., & Mao, Y. (2025). Energy Consumption Analysis and Optimization of Speech Algorithms for Intelligent Terminals.
21. Yang, M., Wu, J., Tong, L., & Shi, J. (2025). Design of Advertisement Creative Optimization and Performance Enhancement System Based on Multimodal Deep Learning.
22. Lara-Gutierrez, A., Fernandez-Gago, C., & Onieva, J. A. (2025). A Framework for Drift Detection and Adaptation in AI-driven Anomaly and Threat Detection Systems: A. Lara-Gutierrez et al. International Journal of Information Security, 24(5), 199.
23. Wu, C., & Chen, H. (2025). Research on system service convergence architecture for AR/VR system.
24. Jiao, Y., Wang, A., Zhao, B., & Shi, T. (2026). The Impact of Visual Language Strategies in Public Art Creation on Community Spatial Perception and Public Behavior.
25. Sharma, A., Kumar, V. K., & Poojari, A. (2025). Prioritize threat alerts based on false positives qualifiers provided by multiple AI models using evolutionary computation and reinforcement learning. Journal of The Institution of Engineers (India): Series B, 106(4), 1305-1322.
26. Yin, J., Huang, Y., & Rao, H. (2026). A Study on User Behavior Signal-Driven Predictive Models for Digital Platform Consumption Trends. Available at SSRN 6607298.
27. Tran, Q. T., Le-Khac, N. A., & Bertolotto, M. (2026). Concept drift detection in image data stream: a survey on current literature, limitations and future directions. Artificial Intelligence Review, 59(1), 33.
28. Yang, J. (2026). Stage‐Coupled Computational Framework for Stratified Accessibility and Equity Analysis in Community‐Based Elderly Care Services.
29. Bushehri, A. S., Amirnia, A., Belkhiri, A., Keivanpour, S., de Magalhães, F. G., & Nicolescu, G. (2023). Deep learning-driven anomaly detection for green IoT edge networks. IEEE Transactions on Green Communications and Networking, 8(1), 498-513.
30. Zhang, Z. (2026). A Study on Return Optimization in E-commerce for Complex Consumer Goods Driven by Installation Information Quality. Available at SSRN 6734720.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Wei Jie Tan, Li Xin Chong, Hannah Mei Lin Lim (Author)