Advanced ENF Region Classification Using UniTS-SinSpec: A Novel Approach Integrating Sinusoidal Activation Function and Spectral Attention
Source abstract
Abstract
The electric network frequency (ENF), often referred to as the industrial heartbeat, plays a crucial role in the power system. In recent years, it has found applications in multimedia evidence identification for court proceedings and audio–visual temporal source identification. This paper introduces an ENF region classification model named UniTS-SinSpec within the UniTS framework. The model integrates the sinusoidal activation function and spectral attention mechanism while also redesigning the model framework. Training is conducted using a public dataset on the open science framework (OSF) platform, with final experimental results demonstrating that, after parameter optimization, the UniTS-SinSpec model achieves an average validation accuracy of 97.47%, surpassing current state-of-the-art and baseline models. Accurate classification can significantly aid in ENF temporal source identification. Future research will focus on expanding dataset coverage and diversity to verify the model’s generality and robustness across different regions, time spans, and data sources. Additionally, it aims to explore the extensive application potential of ENF region classification in preventing crimes such as telecommunications fraud, terrorism, and child pornography.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image and Signal Denoising Methods · Structural Health Monitoring Techniques · Blind Source Separation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Network Security, People’s Public Security University of China, Beijing 100038, China
Funding
Fundamental Research Funds for the Central Universities · People’s Public Security University of China Top-notch innovative talents training funds
References (32)
Show source-provided references
1. Audio Authenticity: Detecting ENF Discontinuity with High Precision Phase Analysis10.1109/TIFS.2010.2051270 ↗
2. National Technical Information Service (2024, September 26). NTIS Homepage, Available online: https://www.ntis.gov/.
3. Application of the Electrical Network Frequency (ENF) Criterion: A case of a digital recording10.1016/j.forsciint.2004.11.015 ↗
4. Using the ENF criterion for determining the time of recording of short digital audio recordings
5. Hajj-Ahmad, R.A., Geradts, Z., and Wu, M. (2012, January 3–6). Instantaneous Frequency Estimation and Localization for ENF Signals. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hollywood, CA, USA.
6. Applications of ENF criterion in forensic audio, video, computer and telecommunication analysis10.1016/j.forsciint.2006.06.033 ↗
7. Application of Power System Frequency for Digital Audio Authentication10.1109/TPWRD.2012.2198892 ↗
8. Garg, R., Hajj-Ahmad, A., and Wu, M. (2013, January 26–31). Geo-Location Estimation from Electrical Network Frequency Signals. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada.10.1109/ICASSP.2013.6638180 ↗
9. Anti-Forensics and Countermeasures of Electrical Network Frequency Analysis10.1109/TIFS.2013.2285515 ↗
10. Chakma, S., and Fattah, S.A. (2018, January 14–16). Location Identification Using Power and Audio Data Based on Temporal Variation of Electric Network Frequency and Its Harmonics. Proceedings of the 2018 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), Chonburi, Thailand.10.1109/WIECON-ECE.2018.8783110 ↗
11. Power Grid Estimation Using Electric Network Frequency Signals10.1155/2019/1982168 ↗
12. Garg, R., Hajj-Ahmad, A., and Wu, M. (2021). Feasibility Study on Intra-Grid Location Estimation Using Power ENF Signals. arXiv.10.36227/techrxiv.14516634.v1 ↗
13. Khairy, I. (2024, June 27). ENF Based Classification and Extraction. IEEE Signal Processing Cup 2016. Available online: https://github.com/ibrahimkhairy/ENF_based_classification_and_extraction.
14. Tzolopoulos, G., Korgialas, C., and Kotropoulos, C. (2024). On Spectrogram Analysis in a Multiple Classifier Fusion Framework for Power Grid Classification Using Electric Network Frequency. arXiv.10.5220/0012418400003654 ↗
15. Gao, S., Koker, T., Queen, O., Hartvigsen, T., Tsiligkaridis, T., and Zitnik, M. (2024). UNITS: A Unified Multi-Task Time Series Model. arXiv.
16. On a Method of Investigating Periodicities in Distributed Series, with special reference to Wolfer’s Sunspot Numbers10.1098/rsta.1927.0007 ↗
17. Kim, Y. (2024). Time Series Analysis for Macroeconomics and Finance, University of Kentucky.
18. Jumar, R., Maaß, H., Schäfer, B., Gorjão, L.R., and Hagenmeyer, V. (2020). Database of Power Grid Frequency Measurements. arXiv.
19. Kruse, T., Vanfretti, L., and Silva, F. (2021). Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models. Electronics, 10.10.3390/electronics10020151 ↗
20. Hendrycks, D., and Gimpel, K. (2016). Gaussian Error Linear Units (GELUs). arXiv.
21. Nair, V., and Hinton, G.E. (2010, January 21–24). Rectified Linear Units Improve Restricted Boltzmann Machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel.
22. Parascandolo, G., and Virtanen, T. (2017, January 24–26). Taming the Waves: Sine as Activation Function in Deep Neural Networks. Proceedings of the ICLR 2017, Toulon, France.
23. Gashler, M.S., and Ashmore, S.C. (2014). Training Deep Fourier Neural Networks to Fit Time-Series Data. arXiv.10.1007/978-3-319-09330-7_7 ↗
24. Implicit Neural Representations with Periodic Activation Functions (SIREN)
25. Zhou, S., and Pan, Y. (2021, January 14–16). Spectrum Attention Mechanism for Time Series Classification. Proceedings of the 2021 Chinese Control and Decision Conference (CCDC), Suzhou, China.10.1109/DDCLS52934.2021.9455697 ↗
26. Tumino, P. (2020). Frequency Control in a Power System, EE Power. Available online: https://eepower.com/technical-articles/frequency-control-in-a-power-system.
27. (2024, June 27). Power Grid Frequency. Available online: https://power-grid-frequency.org/.
28. Non-Gaussian power grid frequency fluctuations characterized by Lévy-stable laws and superstatistics
29. Implications of diurnal and seasonal variations in renewable energy generation for large scale energy storage
30. Hugging Face (2024, June 27). Time Series Transformer Classification. Available online: https://huggingface.co/keras-io/timeseries_transformer_classification/tree/main.
31. Romijnders, R. (2024, June 27). LSTM Time Series Classification. Available online: https://github.com/RobRomijnders/LSTM_.
32. Chakma, S., Chowdhury, D., and Sarkar, M. (2016, January 19–21). Power line data based grid identification using signal processing. Proceedings of the 2016 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), Pune, India.10.1109/WIECON-ECE.2016.8009106 ↗