Application of Sparse Representation of Complex Data in Railway Positioning and Collision Alert Systems Using Millimeter Wave Radar
EDN: UEWJIR
Abstract
The article presents the results from the experimental study of a modified artificial neural network MFNN (minimum fuel neural network). Sparse representation of complex data with overcomplete basis and L0/L1 norm optimization is used instead of the classical fast Fourier transform (FFT) algorithm. The results showed a significant enhancement in the abilities of obstacle recognition and autonomous railway control systems to distinguish between close objects, such as trains on adjacent tracks of marshalling yards.
About the Authors
N. V. Panokin
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
I. A. Kostin
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
A. V. Averin
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
A. V. Karlovskiy
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
D. I. Orelkina
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
A. Yu. Nalivaiko
Moscow Polytechnic University
Russian Federation
Moscow
Russian Federation
Moscow
References
1. Cheng, P., Wang, X., Zhao, J., and Cheng, J., A Fast and Accurate Compressed Sensing Reconstruction Algorithm for ISAR Imaging, IEEE Access, 2019, vol. 7, pp. 157019–157026, doi: 10.1109/ACCESS.2019.2949756.
2. Roy, R., Kailath, T., ESPRIT-estimation of signal parameters via rotational invariance techniques, IEEE Transactions on Acoustics, Speech, and Signal Processing, Jul 1989, vol. 37, no. 7, pp. 984–995, doi: 10.1109/29.32276.
3. Souden, M., Benesty, J., Affes, S., On optimal frequency domain multichannel linear filtering for noise reduction, IEEE Transactions on Audio, Speech, and Language Processing, 2010, vol. 18, no. 2, pp. 260–276, doi: 10.1109/TASL.2009.2025790.
4. Cichocki, A., Unbehauen, R., Neural networks for solving systems of linear equations – Part II: Minimax and least absolute value problems, IEEE Trans. Circuits Syst., Sept. 1992, vol. 39, pp. 619–633, doi:10.1109/82.193316.
5. Neural Networks for Optimization and Signal Processing, Stuttgart, Germany: Teubner-Wiley, 1993.
6. Xiong, K., Zhao, G., Shi, G., Wang, Y., A Convex Optimization Algorithm for Compressed Sensing in a Complex Domain: The Complex-Valued Split Bregman Method, Sensors (Basel), 2019, Oct. 18;19(20):4540, doi: 10.3390/s19204540. PMID: 31635423; PMCID: PMC6832202.
7. Stanković, L., Sejdić, E., Stanković, S. et al., A Tutorial on Sparse Signal Reconstruction and Its Applications in Signal Processing, Circuits Syst Signal Process, 2019, vol. 38, pp. 1206–1263, doi: 10.1007/ s00034-018.9-0909-2.
8. Changhao Yi, Cunlu Zhou, Jun Takahashi, Quantum Phase Estimation by Compressed Sensing, https://doi.org/10.48550/arXiv.2306.07008.
9. Bandler, J.W., Kellerman, W., Madsen, K., A nonlinear L1 optimization algorithm for design, modeling, and diagnosis of networks, IEEE Trans. Circuits Syst., Feb. 1987, vol. 34, pp. 174–18.91, doi: 10.1109/TCS.1987.1086100.
10. Zhang, Y., Xiao, S., Huang, D., Sun, D., Liu, L., Cui, H., L0-norm penalised shrinkage linear and widely linear LMS algorithms for sparse system identification, IET Signal Process, 2017, vol. 11, pp. 86–94, doi: 10.1049/iet-spr.2015.0218.
11. Ishii, Y., Koide, S., Hayakawa, K., L0-norm Constrained Autoencoders for Unsupervised Outlier Detection, Lauw, H., Wong, RW., Ntoulas, A., Lim, EP., Ng, SK., Pan, S. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2020. Lecture Notes in Computer Science, vol. 12085, Springer, Cham., doi: 10.1007/978-3-030-47436-2_51.
12. Rajko, R., Studies on the adaptability of different Borgen norms applied in selfmodeling curve resolution (SMCR) method, Journal of Chemometrics, 2009, vol. 23(6), pp. 265–274, doi: 10.1002/cem.1221.
13. Jahan, K., Niemeijer, J., Kornfeld, N., Roth, M., Deep Neural Networks for Railway Switch Detection and Classification Using Onboard Camera, IEEE Symposium Series on Computational Intelligence, October 2021, doi:10.1109/SSCI50451.2021. 9659983.
14. Malioutov, D.M., Cetin, M., Willsky, A.S., Optimal sparse representations in general overcomplete bases, Proceedings of the 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, QC, Canada, 2004, pp. ii-793, doi: 10.1109/ICASSP.2004.1326377.
15. Wang, Z.S., Cheung, J.Y., Xia, Y.S., Chen, J.D.Z., Minimum fuel neural networks and their applications to overcomplete signal representations, IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications, 2000, vol. 47(8), pp. 1146–1159, doi: 10.1109/81.873870.
16. Panokin, N.V., Averin, A.V., Kostin, I.A., Karlovskiy, A.V., Orelkina, D.I., and Nalivaiko, A.Yu., 2024. Method for Sparse Representation of Complex Data Based on Overcomplete Basis, l1 Norm, and Neural MFNN-like Network Applied Sciences 14, no. 5: 1959. https://doi.org/10.3390/app14051959.
17. Охотников А.Л. Алгоритм выбора оборудования для систем технического зрения на железнодорожном транспорте // Наука и технологии железных дорог. 2021. Т. 5, № 1 (17). С. 65–74. EDN: TWRACV.
18. Хатламаджиян A.E., Орлов В.В., Николаев И.С. Повышение безопасности движения поездов с помощью бортовой системы технического зрения // Эксплуатационная надежность локомотивного парка и повышение эффективности тяги поездов: материалы VII Всероссийской научно-технической конференции с международным участием. Омск: ОмГУПС, 2022. С. 328–334. EDN: JTLVDQ.
19. Мащенко П.Е., Шутилов К.В. Анализ сенсоров систем технического зрения для нужд промышленного железнодорожного транспорта // Вестник Института проблем естественных монополий: Техника железных дорог. 2021. № 1 (53). С. 40–45. EDN: FEUABX.
20. Magaz, B., Belouchrani, A., Hamadouche, M., Automatic Threshold Selection in Os-Cfar Radar Detection Using Information Theoretic Criteria, Progress In Electromagnetics Research B, 2011, 30, 157–175, doi:10.2528/PIERB10122502.
Review
For citations:
Panokin N.V., Kostin I.A., Averin A.V., Karlovskiy A.V., Orelkina D.I., Nalivaiko A.Yu. Application of Sparse Representation of Complex Data in Railway Positioning and Collision Alert Systems Using Millimeter Wave Radar. Gyroscopy and Navigation. 2024;32(1):84-93. (In Russ.) EDN: UEWJIR
Views:
6
Email this article 