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

Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data (2402.09466v2)

Published 9 Feb 2024 in eess.SP, cs.CV, and eess.IV

Abstract: Jamming devices pose a significant threat by disrupting signals from the global navigation satellite system (GNSS), compromising the robustness of accurate positioning. Detecting anomalies in frequency snapshots is crucial to counteract these interferences effectively. The ability to adapt to diverse, unseen interference characteristics is essential for ensuring the reliability of GNSS in real-world applications. In this paper, we propose a few-shot learning (FSL) approach to adapt to new interference classes. Our method employs quadruplet selection for the model to learn representations using various positive and negative interference classes. Furthermore, our quadruplet variant selects pairs based on the aleatoric and epistemic uncertainty to differentiate between similar classes. We recorded a dataset at a motorway with eight interference classes on which our FSL method with quadruplet loss outperforms other FSL techniques in jammer classification accuracy with 97.66%. Dataset available at: https://gitlab.cc-asp.fraunhofer.de/darcy_gnss/FIOT_highway

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. A. B. Nassif, M. A. Talib, Q. Nasir, and F. M. Dakalbab, “Machine Learning for Anomaly Detection: A Systemic Review,” in IEEE Access, vol. 9, May 2021, pp. 78 658–78 700.
  2. Y. Dou, Z. Liu, L. Sun, Y. Deng, H. Peng, and P. S. Yu, “Enhancing Graph Neural Network-based Fraud Detectors Against Camouflaged Fraudsters,” in CIKM, Oct. 2020, pp. 315–324.
  3. T. Schlegl, P. Seeböck, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs, “Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery,” in IPMI, May 2017.
  4. N. L. Raichur, T. Brieger, D. Jdidi, T. Feigl, J. R. van der Merwe, B. Ghimire, F. Ott, A. Rügamer, and W. Felber, “Machine Learning-assisted GNSS Interference Monitoring Through Crowdsourcing,” in ION GNSS+, Denver, CO, Sep. 2022, pp. 1151–1175.
  5. J. R. van der Merwe, D. C. Franco, J. Hansen, T. Brieger, T. Feigl, F. Ott, D. Jdidi, A. Rügamer, and W. Felber, “Low-Cost COTS GNSS Interference Monitoring, Detection, and Classification System,” in MDPI Sensors, vol. 23(7), 3452, Mar. 2023.
  6. Y. S. Kim, F. Mokaya, E. Chen, and P. Tague, “All Your Jammers Belong to us – Localization of Wireless Sensors Under Jamming Attack,” in ICC, Ottawa, ON, Nov. 2012.
  7. J. R. van der Merwe, D. C. Franco, D. Jdidi, T. Feigl, A. Rügamer, and W. Felber, “Low-cost COTS GNSS Interference Detection and Classification Platform: Initial Results,” in ICL-GNSS, Tampere, Finland, Jun. 2022.
  8. “Tesla Spoofing Discussed, Explained,” Jul. 2019.
  9. “Reuters: Finland Detects GPS Disturbance Near Russia’s Kaliningrad,” Mar. 2022.
  10. T. Brieger, N. L. Raichur, D. Jdidi, F. Ott, T. Feigl, J. R. van der Merwe, A. Rügamer, and W. Felber, “Multimodal Learning for Reliable Interference Classification in GNSS Signals,” in ION GNSS+, Denver, CO, Sep. 2022, pp. 3210–3234.
  11. J. H. Yang, C. H. Kang, S. Y. Kim, and C. G. Park, “Intentional GNSS Interference Detection and Characterization Algorithm Using AGC and Adaptive IIR Notch Filter,” in IJASS, vol. 13(4), 2012, pp. 491–498.
  12. C. J. Swinney and J. C. Woods, “GNSS Jamming Classification via CNN, Transfer Learning & the Novel Concatenation of Signal Representations,” in CyberSA, Dublin, Ireland, Jun. 2021.
  13. J. Snell, K. Swersky, and R. Zemel, “Prototypical Networks for Few-shot Learning,” in NIPS, Dec. 2017, pp. 4080–4090.
  14. Y. Wang, W.-L. Chao, K. Q. Weinberger, and L. van der Maaten, “SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning,” in arXiv preprint arXiv:1911.04623, Nov. 2019.
  15. O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra, “Matching Networks for One Shot Learning,” in NIPS, Dec. 2016.
  16. F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales, “Learning to Compare: Relation Network for Few-Shot Learning,” in CVPR, Salt Lake City, UT, Jun. 2018.
  17. X. Luo, H. Wu, J. Zhang, L. Gao, J. Xu, and J. Song, “A Closer Look at Few-shot Classification Again,” in ICML, Jul. 2023.
  18. H.-J. Ye, H. Hu, D.-C. Zhan, and F. Sha, “Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions,” in CVPR, 2020.
  19. J. Liu, L. Song, and Y. Qin, “Prototype Rectification for Few-Shot Learning,” in ECCV, Nov. 2020, pp. 741–756.
  20. I. M. Ziko, J. Dolz, E. Granger, and I. B. Ayed, “Laplacian Regularized Few-Shot Learning,” in ICML, vol. 119, 2020.
  21. F. Ott, “Representation Learning for Domain Adaptation and Cross-modal Retrieval,” in Dissertation, LMU Munich, Sep. 2023.
  22. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A Simple Framework for Contrastive Learning of Visual Representations,” in ICML, vol. 149, Jul. 2020, pp. 1597–1607.
  23. F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in CVPR, Jun. 2015.
  24. W. Chen, X. Chen, J. Zhang, and K. Huang, “Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification,” in CVPR, Honolulu, HI, Jul. 2017.
  25. T.-T. Do, T. Tran, I. Reid, V. Kumar, T. Hoang, and G. Carneiro, “A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning,” in CVPR, Long Beach, CA, Jun. 2019.
  26. E. P. Marcos, S. Caizzone, A. Konovaltsev, M. Cuntz, W. Elmarissi, K. Yinusa, and M. Meurer, “Interference Awareness and Characterization for GNSS Maritime Applications,” in PLANS, Monterey, CA, Apr. 2018, pp. 908–919.
  27. M. J. Murrian, L. Narula, and T. E. Humphreys, “Characterizing Terrestrial GNSS Interference from Low Earth Orbit,” in ION GNSS+, Miami, Florida, Sep. 2019, pp. 3239–3253.
  28. A. G. Dempster and E. Cetin, “Interference Localization for Satellite Navigation Systems,” in Proc. of the IEEE, vol. 104(6), Mar. 2016, pp. 1318–1326.
  29. S. K. Biswas and E. Cetin, “Particle Filter based Approach for GNSS Interference Source Tracking: A Feasibility Study,” in XXXIIIrd General Assembly and Scientific Symposium of the Intl. Union of Radio Science, Rome, Italy, Oct. 2020.
  30. D. Borio and P. Closas, “Robust Transform Domain Signal Processing for GNSS,” in WILEY, Apr. 2019.
  31. R. M. Ferre, A. de la Fuente, and E. S. Lohan, “Jammer Classification in GNSS Bands via Machine Learning Algorithms,” in MDPI Sensors, vol. 19(22), Nov. 2019.
  32. W. Li, Z. Huang, R. Lang, H. Qin, K. Zhou, and Y. Cao, “A Real-time Interference Monitoring Technique for GNSS Based on a Twin Support Vector Machine Method,” in MDPI Sensors, Mar. 2016.
  33. J. Xu, S. Ying, and H. Li, “GPS Interference Signal Recognition Based on Machine Learning,” in Mobile Networks and Applications, vol. 25, Jul. 2020.
  34. I. E. Mehr and F. Dovis, “Detection and Classification of GNSS Jammers Using Convolutional Neural Networks,” in ICL-GNSS, Tampere, Finland, Jun. 2022.
  35. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in CVPR, Las Vegas, NV, Jun. 2016.
  36. D. Borio, C. Gioia, A. S̆tern, F. Dimc, and G. Baldini, “Jammer Localization: From Crowdsourcing to Synthetic Detection,” in ION GNSS+, Portland, Oregon, Sep. 2016, pp. 3107–3116.
  37. D. Jdidi, T. Brieger, T. Feigl, D. C. Franco, J. R. van der Merwe, A. Rügamer, J. Seitz, and W. Felber, “Unsupervised Disentanglement for Post-Identification of GNSS Interference in the Wild,” in ION GNSS+, Denver, CO, Sep. 2022, pp. 1176–1208.
  38. Y. Song, T. Wang, S. K. Mondal, and J. P. Sahoo, “A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities,” in arXiv:2205.06743, May 2022.
  39. F. Ott, D. Rügamer, L. Heublein, B. Bischl, and C. Mutschler, “Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift,” in ACMMM, Lisboa, Portugal, Oct. 2022, pp. 5934–5943.
  40. A. Klaß, S. M. Lorenz, M. W. Lauer-Schmaltz, D. Rügamer, B. Bischl, C. Mutschler, and F. Ott, “Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift,” in IJCAI-ECAI STRL, vol. 3190, Vienna, Austria, Jul. 2022.
  41. F. Ott, D. Rügamer, L. Heublein, B. Bischl, and C. Mutschler, “Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition,” in IEEE Access, vol. 11, Aug. 2023, pp. 94 148–94 172.
  42. Y. Lv, Y. Gu, and X. Liu, “The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification,” in NIPS, 2020.
  43. F. Warburg, M. Jørgensen, J. Civera, and S. Hauber, “Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval,” in ICCV, Montreal, QC, Oct. 2021.
  44. K. Zheng, C. Lan, W. Zeng, Z. Zhang, and Z.-J. Zha, “Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification,” in AAAI, vol. 35(4), Feb. 2021, pp. 3538–3546.
  45. Z. Wu, Y. Yang, J. Gu, and V. Tresp, “Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning,” in ICHI, 2021, pp. 63–72.
  46. H. Liu, Z. Dai, D. R. So, and Q. V. Le, “Pay Attention to MLPs,” in NIPS, May 2021.
  47. G. Zerveas, S. Jayaraman, D. Patel, A. Bhamidipaty, and C. Eickhoff, “A Transformer-based Framework for Multivariate Time Series Representation Learning,” in SIGKDD, Aug. 2021, pp. 2114–2124.
  48. B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles,” in NIPS, Dec. 2017, pp. 6405–6416.
  49. Y. Kwon, J.-H. Won, B. J. Kim, and M. C. Paik, “Uncertainty Quantification Using Bayesian Neural Networks in Classification: Application to Ischemic Stroke Lesion Segmentation,” in MIDL, Apr. 2018.
  50. L. van der Maaten and G. Hinton, “Visualizing Data Using t-SNE,” in JMLR, vol. 9(86), Nov. 2008, pp. 2579–2605.
Citations (4)
View on Semantic Scholar

Summary

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

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