H-RADIS: An Adaptive Edge-Centric Lightweight Framework for Real-Time Multi-Stream Anomaly Detection in Smart Building IoT Systems
DOI:
https://doi.org/10.53560/PPASA(63-3)720Keywords:
IoT, Streaming Data, Edge Computing, HST, Incremental Learning, Real-Time Anomaly DetectionAbstract
The rapid adoption of smart, real-time, QoS-aware IoT applications generates a massive amount of multi-stream data collected from heterogeneous interconnected devices. Extracting valuable and immediate insights from this data requires real-time processing and analytics. Real-time anomaly detection enhances these insights by identifying deviations in data as they occur, ensuring operational reliability, energy efficiency, and resilience against faults. Detecting anomalies in such streams involves analyzing individual streams and identifying complex interrelationships among multiple streams, where irregular patterns may emerge collectively or over time. Therefore, this paper proposes H-RADIS, an adaptive Half-Space Trees (HST) based framework specifically designed for real-time, multi-stream anomaly detection on edge devices. It effectively detects point and combined anomalies and employs Complex Event Processing (CEP) to detect collective anomalies. The framework integrates a sliding window-based dynamic threshold with adaptive parameter tuning, enabling the H-RADIS to cope with varying situations in real time more effectively. The performance of H-RADIS is evaluated against RIVER-based online machine learning algorithms, Local Outlier Factor (LOF), and OneClassSVM (OCSVM) across two different datasets by augmenting them with synthetic anomalies. The experimental results indicate that H-RADIS consistently improves anomaly detection performance over the collective LOF–OCSVM baseline, with relative gains in F1-score (26.08%), Recall (23.88%), Precision (22.22%), and ROC-AUC (17.69%). In terms of computational efficiency, H-RADIS achieves a relative 48.65% increase in throughput, together with relative reductions of 34.71% in processing time, 34.69% in energy consumption, and 0.21% in memory usage, while maintaining comparable CPU utilization. Overall, the comparative results indicate that, under the evaluated experimental conditions, H-RADIS is a resource-efficient approach for real-time anomaly detection in smart-building IoT environments.
References
1. A. Alawad and V. Marttin. Internet of Things (IoT) and Smart Applications. In: Pioneer and Innovative Studies in Computer Sciences and Engineering. A. Alaybeyoğlu (Ed.). All Sciences Academy, Konya, Turkey pp. 126-141 (2024).
2. N.M. Quy, L.A. Ngoc, N.T. Ban, N.V. Hau, and V.K. Quy. Edge computing for real-time internet of things applications: Future internet revolution. Wireless Personal Communications 132(2): 1423-1452 (2023). https://doi.org/10.1007/s11277-023-10669-w
3. C. Hu, Z. Sun, C. Li, Y. Zhang, and C. Xing. Survey of Time Series Data Generation in IoT. Sensors 23(15): 6976 (2023). https://doi.org/10.3390/s23156976
4. K.-D. Kang. A Review of Efficient Real-Time Decision Making in the Internet of Things. Technologies 10(1): 12 (2022). https://doi.org/10.3390/technologies10010012
5. W. Yu, F. Liang, X. He, W. G. Hatcher, C. Lu, J. Lin, and X. Yang. A Survey on the Edge Computing for the Internet of Things. IEEE Access 6: 6900–6919 (2018). https://doi.org/10.1109/ACCESS.2017.2778504
6. M. J. C. S. Reis and C. Serôdio. Edge AI for Real-Time Anomaly Detection in Smart Homes. Future Internet 17(4): 179 (2025). https://doi.org/10.3390/fi17040179
7. L. Erhan, M. Ndubuaku, M. Di Mauro, W. Song, M. Chen, G. Fortino, O. Bagdasar, and A. Liotta. Smart anomaly detection in sensor systems: A multi-perspective review. Information Fusion 67: 64-79 (2020). https://doi.org/10.1016/j.inffus.2020.10.001
8. T. Lu, L. Wang, and X. Zhao. Review of anomaly detection algorithms for data streams. Applied Sciences 13(10): 6353 (2023). https://doi.org/10.3390/app13106353
9. Y. Zhang, C. Jiang, B. Yue, J. Wan, and M. Guizani. Information fusion for edge intelligence: A survey. Information Fusion 81: 171-186 (2022). https://doi.org/10.1016/j.inffus.2021.11.018
10. A. Verdone, S. Scardapane, and M. Panella. A data attribution approach for unsupervised anomaly detection on multivariate time series. Expert Systems with Applications 297: 129285 (2026). https://doi.org/10.1016/j.eswa.2025.129285
11. Z. Zhong, Z. Yu, Y. Yang, W. Wang, K. Yang, and C. Chen. PatchAD: A lightweight patch-based MLP-mixer for time series anomaly detection. IEEE Transactions on Big Data 11(6): 3460-3473 (2025). https://doi.org/10.1109/TBDATA.2025.3596745
12. A. Ayad, M. El-Gayar, N. Hikal, and N. Sakr. Efficient real-time anomaly detection in IoT networks using one-class autoencoder and deep neural network. Electronics 14(1): 104 (2025). https://doi.org/10.3390/electronics14010104
13. X. Wang, Z. Tang, J. Guo, T. Meng, C. Wang, T. Wang, and W. Jia. Empowering edge intelligence: A comprehensive survey on on-device AI models. ACM Computing Surveys 57(9): 228 (2025). https://doi.org/10.1145/3724420
14. V. Prakash, O. Odedina, A. Kumar, L. Garg, and S. Bawa. A secure framework for the Internet of Things anomalies using machine learning. Discover Internet of Things 4(1): 33 (2024). https://doi.org/10.1007/s43926-024-00088-z
15. U. Islam, M. Alatawi, A. Alqazzaz, S. Alamro, B. Shah, and F. Moreira. A hybrid fog-edge computing architecture for real-time health monitoring in IoMT systems with optimized latency and threat resilience. Scientific Reports 15(1): 25655 (2025). https://doi.org/10.1038/s41598-025-09696-3
16. C. Ni, J. Wu, and H. Wang. Energy-aware edge computing optimization for real-time anomaly detection in IoT networks. Applied and Computational Engineering 139: 42-53 (2025). https://doi.org/10.54254/2755-2721/2025.22280
17. Z. Chen, M. Wang, J. Li, G. Li, and X. Wu. Unsupervised anomaly detection methods for in situ observation data: A comparative study. IEEE Access 13: 187347-187360 (2025). https://doi.org/10.1109/ACCESS.2025.3626371
18. N. Watanabe, T. Yamazaki, T. Miyoshi, R. Yamamoto, M. Nakahara, N. Okui, and A. Kubota. Self-adaptive traffic anomaly detection system for IoT smart home environments. IEICE Transactions on Communications 108(3): 230-242 (2025). https://doi.org/10.23919/transcom.2024EBT0002
19. J. Montiel, M. Halford, S.M. Mastelini, G. Bolmier, R. Sourty, and et al. RIVER: Machine learning for streaming data in Python. Journal of Machine Learning Research 22: 1-8 (2021).
http://jmlr.org/papers/v22/20-1380.html
20. S. Tan, K. Ting, and T. Liu. Fast anomaly detection for streaming data. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI) pp. 1511-1516 (2011). https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-254
21. Z. Cheng, C. Zou, and J. Dong. Outlier Detection using Isolation Forest and Local Outlier Factor. Conference on Research in Adaptive and Convergent Systems (RACS ’19), (24th - 27th September 2019), Chongqing, China, pp. 161-168 (2019). https://doi.org/10.1145/3338840.3355641
22. K. Yang, S. Kpotufe, and N. Feamster. An efficient one-class SVM for anomaly detection in the Internet of Things. arXiv preprint arXiv:2104.11146 (2021). https://doi.org/10.48550/arXiv.2104.11146
23. S.K. Ray and S. Susan. Performance analysis of online machine learning frameworks for anomaly detection in IoT data streams. 15th International Conference on Computing, Communication and Networking Technologies (ICCCNT), (24th -28th June 2024), Kamand, India, (2024). https://doi.org/10.1109/ICCCNT61001.2024.10724326
24. U. Erol, F. Raimondo, J. Pope, S. Gunner, V. Kumar, and et al. Multi-sensor, multi-device smart building indoor environmental dataset. Data in Brief 49: 109392 (2023). https://doi.org/10.1016/j.dib.2023.109392
25. H. Kim and I. Joe. Enhancing anomaly detection in maritime operational IoT time-series data with synthetic outliers. Electronics 13(19): 3912 (2024). https://doi.org/10.3390/electronics13193912
26. S. Schmidl, P. Wenig, and T. Papenbrock. Anomaly detection in time series: A comprehensive evaluation. Proceedings of the VLDB Endowment 15(9): 1779-1797 (2022). https://doi.org/10.14778/3538598.3538602
27. N. Mejri, L. Lopez-Fuentes, K. Roy, P. Chernakov, E. Ghorbel, and D. Aouada. Unsupervised anomaly detection in time-series: An extensive evaluation and analysis of state-of-the-art methods. Expert Systems with Applications 256: 124922 (2024). https://doi.org/10.1016/j.eswa.2024.124922
28. W. Fernandes Jr., K.S. Komati, and K.A.S. Gazolli. Anomaly detection in oil-producing wells: A comparative study of one-class classifiers in a multivariate time series dataset. Journal of Petroleum Exploration and Production Technology 14: 343-363 (2024). https://doi.org/10.1007/s13202-023-01710-6
