A Review of the Application of Data Science Methods in Communication Signal Anomaly Detection
Main Article Content
Keywords
communication signals, anomaly detection, machine learning, data science
Abstract
With the large-scale deployment of 5G and industrial Internet of Things devices, the electromagnetic environment has become complex and diverse, and communication signal anomalies caused by jamming interference, spoofing interference, and equipment faults have become increasingly prominent. Traditional threshold and time-frequency analysis methods depend on manual experience, and their performance is limited in practical scenarios with unknown interference, low signal-to-noise ratios, and scarce samples. In recent years, data science technologies represented by few-shot learning, open-set recognition, lightweight deep models, and improved unsupervised frameworks have become research hotspots in communication signal anomaly detection. This study reviews recent domestic and international research results from three dimensions: few-shot optimization under supervised paradigms, architectural improvement of unsupervised reconstruction models, and open semi-supervised models. It compares the advantages and existing shortcomings of different technical routes, analyzes practical challenges related to samples, signal-to-noise ratios, and deployment in real electromagnetic environments, and looks ahead to future development directions.
References
- [1]Zhao, G., Li, G., Qin, Y., Zhang, J., Chai, Z., Wei, X., Lin, L., & Yu, Y. (2024). Exploration and exploitation of unlabeled data for open-set semi-supervised learning. International Journal of Computer Vision, 132, 5888-5904. https://doi.org/10.1007/s11263-024-02155-y
- [2]Elango, A., & Landry, R. J. (2024). XAI GNSS—A Comprehensive Study on Signal Quality Assessment of GNSS Disruptions Using Explainable AI Technique. Sensors, 24(24), 8039. https://doi.org/10.3390/s24248039
- [3]Feng, Y., Han, B., Wang, X., Shen, J., Guan, X., & Ding, H. (2024). Self-supervised transformers for unsupervised SAR complex interference detection using Canny edge detector. Remote Sensing, 16(2), 306. https://doi.org/10.3390/rs16020306
- [4]Elango, A., & Landry, R. J. (2024). XAI GNSS—A Comprehensive Study on Signal Quality Assessment of GNSS Disruptions Using Explainable AI Technique. Sensors, 24(24), 8039. https://doi.org/10.3390/s24248039
- [5]Tu, S., Cheng, Q., Qian, F., Hui, P., & Guan, L. (2022). Composite interference signals recognition based on YOLOv5. In 2022 IEEE 21st International Conference on Ubiquitous Computing and Communications (IUCC/CIT/DSCI/SmartCNS) (pp. 210-215). IEEE. https://doi.org/10.1109/IUCC-CIT-DSCI-SmartCNS57392.2022.00042
- [6]Chen, G., Wang, J., Liu, W., Lin, Y., & Xu, F. (2023). The concept, model, and practical inspiration of meta-learning: A study based on spatio-temporal theory. Chinese Journal of Management Science,1-17. https://doi.org/10.16381/j.cnki.issn1003-207x.2023.0498.
- [7]Huang, X., Fu, C., & Zeng, Q. (2026). Research on few-shot intrusion detection based on a Meta-SGD+ANIL meta-learning framework.12(8),712-720.
- [8]Yiding Wang. (2025). Evolution and Breakthroughs of Generative Adversarial Network Technology. ITM Web of Conferences (ITM WoC), 80(11): 01023. https://doi.org/10.1051/itmconf/20258001023.
- [9]Wang, H., Liu, H., & Li, M. (2024). Lightweight communication signal recognition network for embedded deployment. Journal of Electronics & Information Technology, 46(3), 912-920.
- [10]Yu, Y., & Zhang, J. (2024). Unsupervised communication signal anomaly detection method based on memory-enhanced autoencoder. Journal on Communications, 45(6), 182-193.
- [11]Jin, Z., & Liu, C. (2023). Communication weak interference detection algorithm based on time-frequency channel attention. Journal of Signal Processing, 39(2), 345-354.
- [12]Wang, H., & Li, M. (2024). Unsupervised signal anomaly screening framework for large-scale base-station monitoring. Journal of Electronics & Information Technology, 46(8), 2761-2769.
- [13]Mehr, A., & Dovis, F. (2023). Limitations of reconstruction-based unsupervised models for GNSS spoofing detection. IEEE Transactions on Aerospace and Electronic Systems, 59(4), 4123-4136.
- [14]Li, J., Pan, J., Tan, V.Y., Toh, K., & Zhou, P. (2024). Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning. ArXiv, abs/2410.11206.
- [15]Feng, Q., Fang, S., Lin, T., & Xie, L. (2024). BaCon: Boosting imbalanced semi-supervised learning via balanced feature-level contrastive learning. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.48448/wxgy-7s45
- [16]Filipiak, D., Tempczyk, P., & Cygan, M. (2026). n-CPS: Generalising cross pseudo supervision to n networks. IEEE Access, 14, 101774-101789. https://doi.org/10.1109/ACCESS.2026.3704899
- [17]Xie, S., Wang, H., Niu, Z., Sun, H., Ouyang, S., Chen, Y.-W., & Lin, L. (2024). SemSim: Revisiting weak-to-strong consistency from a semantic similarity perspective for semi-supervised medical image segmentation. arXiv. https://arxiv.org/abs/2410.13486
- [18]Ding, D., Wang, L., Zhu, L., Gedeon, T., & Koniusz, P. (2024). Learnable expansion of graph operators for multi-modal feature fusion. arXiv. https://arxiv.org/abs/2410.01506
- [19]Ding, D., Wang, L., Zhu, L., Gedeon, T., & Koniusz, P. (2025). Learnable expansion of graph operators for multi-modal feature fusion. International Conference on Learning Representations. arXiv. https://doi.org/10.48550/arXiv.2410.01506
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.