Autors: Georgieva P., Vlahov, A. G., Mfondoum, R. B., Poulkov, V. K., Zaharis Z.
Title: Informer-Based Anomaly Detection in Mobile Networks Using CDR Time-Series Analysis
Keywords: Anomaly Detection, Call Detail Records (CDR), Informer Model, Machine Learning, Telecom Traffic Analysis

Abstract: This paper introduces an Informer model for anomaly detection in mobile networks. Call detail records, containing mobile internet traffic data are thoroughly processed and feature engineering is applied to improve the model's overall accuracy and efficiency. Moreover, logarithmic transformation is employed onto the data to ensure realistic and precise results. After training the model for the length of 5 epochs and testing with synthetic injected anomalous data patterns an accuracy of 80.69% was achieved.

References

  1. Rep. ITU-R M. 2370-0, 07/2015
  2. Eric Bouillet, Ravi Kothari, Vibhore Kumar, Laurent Mignet, Senthil Nathan, Anand Ranganathan, Deepak S. Turaga, Octavian Udrea, Olivier Verscheure, "Processing 6 billion CDRs/day: From research to production (experience report)", The 6th ACM International Conference on Distributed Event-based system, 20 Aug 2012
  3. A. Siva Kumar, S. Raja, N. Pritha, Havaldar Raviraj, R. Babitha Lincy, J. Jency Rubia, "An adaptive transformer model for anomaly detection in wireless sensor networks in real-time", Measurement: Sensors Volume 25, February 2023, 100625
  4. Telecom Italia, 2015, "Telecommunications-SMS, Call, Internet-MI", https: //doi. org/10. 7910/DVN/EGZHFV, Harvard Dataverse, V
  5. https: //github. com/arunasubbiah/milan-telecom-datamodeling/ blob/master/images/Top_10_geojson. png?raw=true
  6. The Data Says: Mobile Traffic by Day and Time, https: //www. seoclarity. net/blog/mobile-seo-by-day-and-time-11890/
  7. Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, Wancai Zhang, "Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting", Proceedings of the AAAI conference on artificial intelligence, 2021

Issue

60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, 2025, Macedonia, https://doi.org/10.1109/ICEST66328.2025.11098317

Copyright IEEE

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus