Journal of Smart Computing ISSN 2979-8752 · Biannual
Register Log in
Research Article · Vol. 2, No. 1 (2026)

Lightweight Deep Learning for Real-Time Anomaly Detection on Intelligent Edge Devices

Joanna Oleskow Szłapka* , Francesco Facchini

Poznan University of Technology; Poznan, Poland · Department of Mechanical Engineering, Polytechnic University of Bari, Bari, Italy

* Corresponding author: joanna.oleskow-szlapka@put.poznan.pl

Abstract The proliferation of Internet-of-Things sensors has created a need to detect anomalies where data are generated, yet deep anomaly detectors are typically too large and power-hungry for microcontroller-class devices at the network edge. Streaming raw data to the cloud incurs latency, bandwidth costs, and privacy risks, so on-device inference is increasingly preferred, but it demands models that fit within kilobytes of memory and run within tight energy budgets. This paper presents LiteAD, a lightweight deep learning framework for real-time anomaly detection on intelligent edge devices. The approach combines a depthwise-separable convolutional autoencoder trained only on normal data with structured pruning and integer quantization, scoring anomalies by reconstruction error against an adaptive threshold. The framework is described formally and as pseudocode, covering offline compression and on-device inference. Using an illustrative synthetic time-series benchmark, LiteAD is compared against four baselines on detection quality, latency, memory, and energy. The synthetic results indicate that the compressed model retains detection accuracy close to a full-precision autoencoder while reducing model size and inference latency by roughly an order of magnitude. These findings support lightweight deep learning as a practical approach to always-on anomaly detection at the edge.

Keywords: Anomaly detection, Edge computing, Lightweight deep learning, Model compression, TinyML

DOI
10.5281/zenodo.23265837
Pages
33-42
Published
4 Mar 2026
Download PDF

To cite this article: Szłapka, J.O., & Facchini, F. (2026). Lightweight Deep Learning for Real-Time Anomaly Detection on Intelligent Edge Devices. Journal of Smart Computing , 2(1) , 33-42. https://doi.org/10.5281/zenodo.23265837

References

  1. Ahmad, S., Lavin, A., Purdy, S., & Agha, Z. (2017). Unsupervised real-time anomaly detection for streaming data. Neurocomputing, 262, 134–147. https://doi.org/10.1016/j.neucom.2017.04.070
  2. Al-Otum, H. M. (2024). Classification of anomalies in electroluminescence images of solar PV modules using CNN-based deep learning. Solar Energy, 278, Article 112803. https://doi.org/10.1016/j.solener.2024.112803
  3. David, R., Duke, J., Jain, A., Janapa Reddi, V., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., Regev, S., Rhodes, R., Wang, T., & Warden, P. (2021). TensorFlow Lite Micro: Embedded machine learning for TinyML systems. Proceedings of Machine Learning and Systems, 3, 800–811.
  4. Fan, L., Gong, X., Huang, L., & Ou, Y. (2026). Dual-branch decoupling framework for medical one-class classification. Pattern Recognition, 180, Article 114266. https://doi.org/10.1016/j.patcog.2026.114266
  5. Fang, L., Yu, X., Cai, J., Chen, Y., Wu, S., Liu, Z., Yang, Z., Lu, H., Gong, X., Liu, Y., Ma, T., Ruan, W., Abbasi, A., Zhang, J., Wang, T., Latif, E., Liu, W., Zhang, W., Kolouri, S., . . . Ma, P. (2026). Knowledge distillation and dataset distillation of large language models: Emerging trends, challenges, and future directions. Artificial Intelligence Review, 59(1), Article 17. https://doi.org/10.1007/s10462-025-11423-3
  6. Han, S., Mao, H., & Dally, W. J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In International Conference on Learning Representations.
  7. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). IEEE. https://doi.org/10.1109/cvpr.2016.90
  8. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
  9. Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2704–2713). IEEE. https://doi.org/10.1109/cvpr.2018.00286
  10. Kumar, R., Reddy, R. D., Babu, T. N., & Pandiyan, M. (2026). Dual-stream 1D mobile-net with channel attention fusion for rolling element fault diagnosis. Scientific Reports. Advance online publication. https://doi.org/10.1038/s41598-026-64845-6
  11. Li, Q., Lin, J., Qi, R., & Chi, Y. (2026). An assembly defection diagnostic method for alkaline water electrolyzer awared by ohmic resistance based on physical-informed statistical analytics. International Journal of Hydrogen Energy, 220, Article 153952. https://doi.org/10.1016/j.ijhydene.2026.153952
  12. Lin, J., Chen, W.-M., Lin, Y., Cohn, J., Gan, C., & Han, S. (2020). MCUNet: Tiny deep learning on IoT devices. In Advances in Neural Information Processing Systems (Vol. 33, pp. 11711–11722).
  13. Lindemann, B., Maschler, B., Sahlab, N., & Weyrich, M. (2021). A survey on anomaly detection for technical systems using LSTM networks. Computers in Industry, 131, Article 103498. https://doi.org/10.1016/j.compind.2021.103498
  14. Moon, A.-S., Lee, J. K., & Lee, J. (2026). Three-dimensional convolutional neural network with channel compression module for efficient diagnosis of thyroid-associated orbitopathy. Multimedia Tools and Applications, 85, Article 609. https://doi.org/10.1007/s11042-026-21771-z
  15. Pang, G., Shen, C., Cao, L., & van den Hengel, A. (2021). Deep learning for anomaly detection: A review. ACM Computing Surveys, 54(2), Article 38. https://doi.org/10.1145/3439950
  16. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510–4520). IEEE. https://doi.org/10.1109/cvpr.2018.00474
  17. Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762. https://doi.org/10.1109/jproc.2019.2918951
CC BY Creative Commons Attribution 4.0
Creative Commons Attribution 4.0 International CC BY 4.0

This work is licensed under a Creative Commons Attribution 4.0 International License.

Read the full CC BY 4.0 license →