Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On Spectrogram Analysis in a Multiple Classifier Fusion Framework for Power Grid Classification Using Electric Network Frequency (2403.18402v1)

Published 27 Mar 2024 in cs.LG

Abstract: The Electric Network Frequency (ENF) serves as a unique signature inherent to power distribution systems. Here, a novel approach for power grid classification is developed, leveraging ENF. Spectrograms are generated from audio and power recordings across different grids, revealing distinctive ENF patterns that aid in grid classification through a fusion of classifiers. Four traditional machine learning classifiers plus a Convolutional Neural Network (CNN), optimized using Neural Architecture Search, are developed for One-vs-All classification. This process generates numerous predictions per sample, which are then compiled and used to train a shallow multi-label neural network specifically designed to model the fusion process, ultimately leading to the conclusive class prediction for each sample. Experimental findings reveal that both validation and testing accuracy outperform those of current state-of-the-art classifiers, underlining the effectiveness and robustness of the proposed methodology.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM International Conference on Knowledge Discovery & Data Mining, pages 2623–2631.
  2. Alamir, M. A. (2021). A novel acoustic scene classification model using the late fusion of convolutional neural networks and different ensemble classifiers. Applied Acoustics, 175:107829.
  3. Breiman, L. (1996). Bagging predictors. Machine Learning, 24:123–140.
  4. Bykhovsky, D. (2020). Recording device identification by ENF harmonics power analysis. Forensic Science International, 307:110100.
  5. Multi-harmonic histogram comparison. Technical report, Purdue University. Signal Processing Cup.
  6. Cooper, A. J. (2009). An automated approach to the electric network frequency (ENF) criterion: Theory and practice. International Journal of Speech, Language & the Law, 16(2):193–218.
  7. Exploring power signatures for location forensics of media recordings. Technical report, University of Novi Sad, Serbia. Signal Processing Cup.
  8. A novel ENF extraction approach for region-of-recording identification of media recordings. In Proceedings of the Computer Science & Information Technology, page 97–108. CSCP.
  9. New forensic ENF reference database for media recording authentication based on harmony search technique using GIS and wide area frequency measurements. IEEE Transactions on Information Forensics and Security, 9(4):633–644.
  10. Geo-location estimation from electrical network frequency signals. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 2862–2866. IEEE.
  11. Feasibility study on intra-grid location estimation using power ENF signals. arXiv preprint arXiv:2105.00668.
  12. “Seeing” ENF: Power-signature-based timestamp for digital multimedia via optical sensing and signal processing. IEEE Transactions on Information Forensics and Security, 8(9):1417–1432.
  13. Grigoras, C. (2005). Digital audio recording analysis–the electric network frequency criterion. International Journal of Speech Language and the Law, 12(1):63–76.
  14. Grigoras, C. (2007). Applications of ENF criterion in forensic audio, video, computer and telecommunication analysis. Forensic Science International, 167(2-3):136–145.
  15. Hajj-Ahmad, A. (2016). ENF power frequency data for location forensics. https://dx.doi.org/10.21227/H2159S. Signal Processing Cup.
  16. Exploiting power signatures for camera forensics. IEEE Signal Processing Letters, 23(5):713–717.
  17. ENF based location classification of sensor recordings. In Proceedings of the 2013 IEEE International Workshop on Information Forensics and Security, pages 138–143. IEEE.
  18. ENF-based region-of-recording identification for media signals. IEEE Transactions on Information Forensics and Security, 10(6):1125–1136.
  19. A dynamic matching algorithm for audio timestamp identification using the ENF criterion. IEEE Transactions on Information Forensics and Security, 9(7):1045–1055.
  20. Acoustic scene classification using ensembles of convolutional neural networks and spectrogram decompositions. In Mandel, M., Salamon, J., and Ellis, D. P. W., editors, Proceedings of the 2019 Challenge on Detection and Classification of Acoustic Scenes and Events, pages 45–49. New York University, NY, USA.
  21. Location tracking technique for regional ENF classification using ARIMA. In Proceedings of the 2020 International Conference on Information and Communication Technology Convergence, pages 1321–1324. IEEE.
  22. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  23. Using transfer learning, svm, and ensemble classification to classify baby cries based on their spectrogram images. In Proceedings of the 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops, pages 106–110. IEEE.
  24. A survey of ensemble learning: Concepts, algorithms, applications, and prospects. IEEE Access, 10:99129–99149.
  25. Ensemble of convolutional neural networks to improve animal audio classification. EURASIP Journal on Audio, Speech, and Music Processing, 2020(1):1–14.
  26. ENF based digital multimedia forensics: Survey, application, challenges and future work. IEEE Access, 11:101241–101272.
  27. Exploiting the rolling shutter read-out time for ENF-based camera identification. Applied Sciences, 13(8):5039.
  28. ENF based grid classification system: Identifying the region of origin of digital recordings. Criterion, 3(4):5.
  29. Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 12:2825–2830.
  30. Self-paced ensemble learning for speech and audio classification. arXiv preprint arXiv:2103.11988.
  31. Improving location of recording classification using electric network frequency (ENF) analysis. In Proceedings of the 2016 IEEE International Symposium on Intelligent Systems and Informatics, pages 51–56. IEEE.
  32. Application of electrical network frequency of digital recordings for location-stamp verification. Applied Sciences, 9(15):3135.
  33. Exploring power signatures for location forensics of media recordings. Technical report, University of Patras, Greece. Signal Processing Cup.
  34. Frequency sensitivity and electromechanical propagation simulation study in large power systems. IEEE Transactions on Circuits and Systems I: Regular Papers, 54(8):1819–1828.
  35. ENF based robust media time-stamping. IEEE Signal Processing Letters, 29:1963–1967.
  36. Location signatures that you don’t see: Highlights from the IEEE signal processing cup 2016 student competition. IEEE Signal Processing Magazine, 33(5):149–156.
  37. Source location identification of distribution-level electric network frequency signals at multiple geographic scales. IEEE Access, 5:11166–11175.
  38. Geographic location estimation from ENF signals with high accuracy. Technical report, University of Science and Technology of China. Signal Processing Cup.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets