Solving Inverse Problems of Obtaining Super-Resolution Using Neural Networks

This paper considers the problem of obtaining approximate numerical solutions of inverse problems in the form of Fredholm integral equations of the first kind for radio and sonar systems and remote sensing systems using neural networks. The solutions make it possible to significantly increase the accuracy of measurements and to bring the angular resolution to values exceeding the Rayleigh criterion. This allows detailed radio images of various objects and probed areas to be received; the number of individual small-sized objects to be determined in the composition of complex targets that were not recorded separately without the presented signal processing; the coordinates of such small-sized objects to be obtained with high accuracy; and the probability of obtaining correct solutions to problems of recognition and identification of objects to be increased. The method is applicable for multi-element measuring systems. It is based on the extrapolation of signals received by all elements outside the system itself. The problem of creating and training a neural network has been solved. As a result, a new virtual measuring system of a much larger size is synthesized, which makes it possible to dramatically increase the angular resolution and thereby improve the quality of approximate solutions to the inverse problems under consideration. Examples demonstrate the effectiveness of the method and assess the adequacy and stability of the solutions. The degree of excess of the Rayleigh criterion by the virtual goniometer system depending on the signal-to-noise ratio is also investigated.

Keywords

Rayleigh criterion; Fredholm integral equation; extrapolation; neural network.

References

1. Almeida M.S., Figueiredo M.A. Deconvolving Images with Unknown Boundaries Using the Alternating Direction Method of Multipliers. IEEE Transactions on Image Processing, 2013, vol. 22, no. 8, pp. 3074-3086. DOI: 10.1109/TIP.2013.2258354
2. Dudik M., Phillips S.J., Schapire R.E. Maximum Entropy Density Estimation with Generalized Regularization and an Application to Species Distribution Modeling. Journal of Machine Learning Research, 2007, no. 8, pp. 1217-1260.
3. Tan W.Q., Hou Y.G. Estimation of Direction of Source Arrival Based upon MUSIC and Capon. Journal of Nanchang Institute of Technology, 2008, vol. 27, no. 1, pp. 20-23.
4. Candes E.J., Fernandez-Granda C. Super-Resolution from Noisy Data. Journal of Fourier Analysis and Applications, 2013, vol. 19, no. 6, pp. 1229-1254. DOI: 10.48550/arXiv.1211.0290
5. Shchukin A.A., Pavlov A.E. Parameterization of User Functions in Digital Signal Processing for Obtaining Angular Superresolution. Russian Technological Journal, 2022, vol. 10, no. 4, pp. 38-43. DOI: 10.32362/2500-316X-2022-10-4-38-43
6. Lagovsky B. Superresolution by Extrapolation for Solving Remote Sensing Problems. Proceedings of the 25th International Crimean Conference "Microwave and Telecommunication Technology", 2015, vol. 2, pp. 1144-1146.
7. Tikhonov A.N., Arsenin V.Ya. Metody resheniya nekorrektnykh zadach [Methods of Solving Ill-Posed Problems]. Moscow, Nauka, 1974. (in Russian)
8. Uzun I.S., Amira A., Bouridane A. FPGA Implementations of Fast Fourier Transforms for Real-Time Signal and Image Processing. IEE Proceedings-Vision, Image and Signal Processing, 2005, vol. 152, no. 3, pp. 83-296. DOI: 10.1049/ip-vis:20041114
9. Abtahi T., Shea C., Kulkarni A., Mohsenin T. Accelerating Convolutional Neural Network with FFT on Embedded Hardware. IEEE Transactions on Very Large Scale Integration Systems, 2018, vol. 26, no. 9, pp. 1737-1749. DOI: 10.1109/TVLSI.2018.2825145
10. Pratt H., Williams B.M., Coenen F., Zheng Yalin. Fcnn: Fourier Convolutional Neural Networks. Machine Learning and Knowledge Discovery in Databases: European Conference. Skopje, 2017, pp. 786-798. DOI: 10.1007/978-3-319-71249-9_47
11. Xiaolong Chen, Qiaowen Jiang, Ningyuan Su, Baoxin Chen, Jian Guan. LFM Signal Detection and Estimation Based on Deep Convolutional Neural Network. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Lanzhou, 2019, pp. 753-758. DOI: 10.1109/APSIPAASC47483.2019.9023016
12. ChiYan Lee, Hideyuki Hasegawa, Shangce Gao. Complex-Valued Neural Networks: A Comprehensive Survey. Journal of Automatica Sinica, 2022, vol. 9, no. 8, pp. 1406-1426. DOI: 10.1109/JAS.2022.105743
13. Bassey J., Lijun Qian, Xianfang Li. A Survey of Complex-Valued Neural Networks. arXiv: Machine Learning, 2021, 15 p. Avialable at: https://arxiv.org/abs/2101.12249. DOI: 10.48550/arXiv.2101.12249
14. Lysenko P.V., Nasonov I.A., Galyaev A.A., Berlin L.M. Deep Learning Approach to Classification of Acoustic Signals using Information Features. Doklady RAN. Mathematika, Informatika, Processy Upravlenia, 2023, vol. 514, no. 2, pp. 39-48. DOI: 10.31857/S2686954323601239
15. Fawaz H.I., Lucas B., Forestier G., et al. Inceptiontime: Finding Alexnet for Time Series Classification. Data Mining and Knowledge Discovery, 2020, vol. 34, no. 6, pp. 1936-1962. DOI: 10.1007/s10618-020-00710-y
16. Fawaz H.I. Deep Learning for Time Series Classification. Data Mining and Knowledge Discovery, 2019, vol. 33, pp. 917-963. DOI: 10.1007/s10618-019-00619-1
17. Jingyu Sun, Susumu Takeuchi, Ikuo Yamasaki. Prototypical Inception Network with Cross Branch Attention for Time Series Classification. 2021 International Joint Conference on Neural Networks, Shenzhen, 2021, pp. 1-7.
18. Xueyuan Gong, Yain-Whar Si, et al. KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-Series Classification. Information Sciences, 2022, vol. 613, pp. 184-203. DOI: 10.1016/j.ins.2022.08.057
19. Pialla G., Devanne M., Weber J., Idoumghar L., Forestier G. Data Augmentation for Time Series Classification with Deep Learning Models. International Workshop on Advanced Analytics and Learning on Temporal Data, Grenoble, 2022, vol. 13812, pp. 117-132. DOI: 10.1007/978-3-031-24378-3_8
20. Yang Hong, Desell T. Robust Augmentation for Multivariate Time Series Classification. arXiv: Machine Learning, 2022, 11 p. Avialable at: https://arxiv.org/abs/2201.11739v1. DOI: 10.48550/arXiv.2201.11739
21. Gillespie D.T. Exact Numerical Simulation of the Ornstein-Uhlenbeck Process and its Integral. Physical Review E, 1996, vol. 54, no. 2, p. 2084. DOI: 10.1103/PhysRevE.54.2084
22. Galyaev A.A., Medvedev A.I., Nasonov I.A. Neural Network Algorithm for Intercepting Targets Moving Along Known Trajectories by a Dubins' Car. Automation and Remote Control, 2023, vol. 84, no. 3, pp. 3-21. DOI: 10.31857/S0005231023030017
23. Baldi P., Sadowski P.J. Understanding Dropout. Advances in Neural Information Processing Systems, 2013, vol. 26, 9 p.
24. Bock S., Weib M. A Proof of Local Convergence for the Adam Optimizer. 2019 International Joint Conference on Neural Networks, Budapest, 2019, pp. 1-8. DOI: 10.1109/IJCNN.2019.8852239