Autors: Mfondoum, R. B., Gotseva N., Vlahov, A. G., Ivanov, A. S., Koleva, P. H., Poulkov, V. K., Manolova, A. H.
Title: Mask Inflation Encoder and Quasi-Dynamic Thresholding Outlier Detection in Cellular Networks
Keywords: autoencoder, cellular networks, encoder masking, outlier detection, streaming data

Abstract: Mobile networks have advanced significantly, providing high-throughput voice, video, and integrated data access to support connectivity through various services to facilitate high user density. This traffic growth has also increased the complexity of outlier detection (OD) for fraudster identification, fault detection, and protecting network infrastructure and its users against cybersecurity threats. Autoencoder (AE) models are widely used for outlier detection (OD) on unlabeled and temporal data; however, they rely on fixed anomaly thresholds and anomaly-free training data, which are both difficult to obtain in practice. This paper introduces statistical masking in the encoder to enhance learning from nearly normal data by flagging potential outliers. It also proposes a quasidynamic threshold mechanism that adapts to reconstruction errors, improving detection by up to 3% median area under the receiver operating characteristic (AUROC) compared to the standard 95% threshold used in base AE models. Extensive experiments on the Milan Human Telecommunications Interaction (HTA) dataset validate the performance of the proposed methods. Combined, these two techniques yield a 31% improvement in AUROC and a 34% lower computational complexity when compared to baseline AE, long short-term memory AE (LSTM-AE), and seasonal auto-regressive integrated moving average (SARIMA), enabling efficient OD in modern cellular networks.

References

  1. Giordani M. Polese M. Mezzavilla M. Rangan S. Zorzi M. Toward 6G networks: Use cases and technologies IEEE Commun. Mag. 2020 58 55 61 10.1109/MCOM.001.1900411
  2. Edozie E. Shuaibu A.N. Sadiq B.O. John U.K. Artificial intelligence advances in anomaly detection for telecom networks Artif. Intell. Rev. 2025 58 100 10.1007/s10462-025-11108-x
  3. Aziz Z. Bestak R. Modeling Voice Traffic Patterns for Anomaly Detection and Prediction in Cellular Networks based on CDR Data IEEE Trans. Mob. Comput. 2024 23 13131 13143 10.1109/TMC.2024.3430032
  4. Mahrez Z. Driss M.B. Sabir E. Saad W. Driouch E. Benchmarking of anomaly detection techniques in o-ran for handover optimization Proceedings of the 2023 International Wireless Communications and Mobile Computing (IWCMC) Marrakesh, Morocco 19–23 June 2023 119 125
  5. Mfondoum R. Ivanov A. Koleva P. Poulkov V. Manolova A. Outlier Detection in Streaming Data for Telecommunications and Industrial Applications: A Survey Electronics 2024 13 3339 10.3390/electronics13163339
  6. Rassam M.A. Autoencoder-Based Neural Network Model for Anomaly Detection in Wireless Body Area Networks IoT 2024 5 852 870 10.3390/iot5040039
  7. Owoh N. Riley J. Ashawa M. Hosseinzadeh S. Philip A. Osamor J. An Adaptive Temporal Convolutional Network Autoencoder for Malicious Data Detection in Mobile Crowd Sensing Sensors 2024 24 2353 10.3390/s24072353 38610563
  8. Hua X. Zhu L. Zhang S. Li Z. Wang S. Deng C. Feng J. Zhang Z. Wu W. GenAD: General unsupervised anomaly detection using multivariate time series for large-scale wireless base stations Electron. Lett. 2023 59 e12683 10.1049/ell2.12683
  9. Aziz Z. Bestak R. Insight into Anomaly Detection and Prediction and Mobile Network Security Enhancement Leveraging K-Means Clustering on Call Detail Records Sensors 2024 24 1716 10.3390/s24061716 38543979
  10. Rafique S.H. Abdallah A. Musa N.S. Murugan T. Machine learning and deep learning techniques for internet of things network anomaly detection—Current research trends Sensors 2024 24 1968 10.3390/s24061968 38544231
  11. Kim J. Kang H. Kang P. Time-series anomaly detection with stacked Transformer representations and 1D convolutional network Eng. Appl. Artif. Intell. 2023 120 105964 10.1016/j.engappai.2023.105964
  12. Mo Y. Fu H. Bai S. Deng C. Tang T. Lang J. Zhou F. InfoFlow: A Transformer-based Time Series Anomaly Detection Model with Information Bottleneck and Normalizing Flows arXiv 2024 2402.00000
  13. Zhang Y. Hu J. Wen D. Deng W. Unsupervised evaluation for out-of-distribution detection Pattern Recognition 2024 160 111212 10.1016/j.patcog.2024.111212
  14. Sultan K. Ali H. Zhang Z. Call detail records driven anomaly detection and traffic prediction in mobile cellular networks IEEE Access 2018 6 41728 41737 10.1109/ACCESS.2018.2859756
  15. Priyadarshini I. Alkhayyat A. Gehlot A. Kumar R. Time series analysis and anomaly detection for trustworthy smart homes Comput. Electr. Eng. 2022 102 108193 10.1016/j.compeleceng.2022.108193
  16. Chebyshev P. Des valeurs moyennes J. Math. Pures Appl. 1867 12 177 184
  17. Stellato B. Van Parys B. Goulart P. Multivariate Chebyshev inequality with estimated mean and variance Am. Stat. 2017 71 123 127 10.1080/00031305.2016.1186559
  18. Zhou H. Li J. Zhang S. Zhang S. Yan M. Xiong H. Expanding the prediction capacity in long sequence time-series forecasting Artif. Intell. 2023 318 103886 10.1016/j.artint.2023.103886
  19. Barlacchi G. De Nadai M. Larcher R. Casella A. Chitic C. Torrisi G. Antonelli F. Vespignani A. Pentland A. Lepri B. A multi-source dataset of urban life in the city of Milan and the Province of Trentino Sci. Data 2015 2 150055 10.1038/sdata.2015.55 26528394
  20. Hung C.F. Tseng C.H. Cheng S.M. Anomaly Detection for Mitigating xApp and E2 Interface Threats in O-RAN Near-RT RIC IEEE Open J. Commun. Soc. 2025 6 1682 1694 10.1109/OJCOMS.2025.3546760

Issue

Telecom, vol. 6, 2025, Switzerland, https://doi.org/10.3390/telecom6040084

Copyright Multidisciplinary Digital Publishing Institute (MDPI)

Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus и Web of Science