Progress In Electromagnetics Research M
ISSN: 1937-8726
Home | Search | Notification | Authors | Submission | PIERS Home | EM Academy
Home > Vol. 95 > pp. 53-61


By A. Alzahed, S. Mikki, and Y. M. M. Antar

Full Article PDF (263 KB)

We derive and verify a new type of low-complexity neural networks using the recently introduced spatial singularity expansion method (S-SEM). The neural network consists of a single layer (Shallow Learning approach to machine learning) but with its activation function replaced by specialized S-SEM radiation mode functions derived by electromagnetic theory. The proposed neural network can be trained by measured near- or far-field data, e.g., RCS, probe-measured fields, array manifold samples, in order to reproduce the unknown source current on the radiating structure. We apply the method to wire structures and show that the various spatial resonances of the radiating current can be very efficiently predicted by the S-SEM-based neural network. Convergence results are compared with Genetic Algorithms and are found to be considerably superior in speed and accuracy.

A. Alzahed, S. Mikki, and Y. M. M. Antar, "A Spatial SEM-Based Shallow Neural Network for Electromagnetic Inverse Source Modeling," Progress In Electromagnetics Research M, Vol. 95, 53-61, 2020.

1. Ishimaru, A., Electromagnetic Wave Propagation, Radiation, and Scattering: From Fundamentals to Applications, Wiley-IEEE Press, 2017.

2. Wang, Y. and X. Chen, "3-D interferometric inverse synthetic aperture radar imaging of ship target with complex motion," IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 7, 3693-3708, Jul. 2018.

3. Mooney, J. E. and L. S. Riggs, "Robust target identification in white gaussian noise for ultra wideband radar systems," IEEE Transactions on Antennas and Propagation, Vol. 46, No. 12, 1817-1823, Dec. 1998.

4. Bialkowski, K. S., J. Marimuthu, and A. M. Abbosh, "Low-cost microwave biomedical imaging," 2016 International Conference on Electromagnetics in Advanced Applications (ICEAA), 697-699, Sept. 2016.

5. Christodoulou, C. and M. Georgiopoulos, Applications of Neural Networks in Electromagnetics, Artech House, 2001.

6. Junior, W. S. S., G. M. Araujo, E. A. B. da Silva, and S. K. Goldenstein, "Facial fiducial points detection using discriminative filtering on principal components," 2010 IEEE International Conference on Image Processing, 2681-2684, Sept. 2010.

7. Boerner, W., "Electromagnetic inverse methods and its applications to medical imaging --- A current-state-of-the-art review," IEEE International Symposium on Circuits and Systems, Vol. 2, 999-1006, May 1989.

8. Afsari, A. and A. Abbosh, "Fast onsite electromagnetic imaging method for medical applications," 2018 Australian Microwave Symposium (AMS), 83-84, Feb. 2018.

9. Ambrosanio, M., P. Kosmasy, and V. Pascazio, "An adaptive multi-threshold iterative shrinkage algorithm for microwave imaging applications," 2016 10th European Conference on Antennas and Propagation (EuCAP), 1-3, Apr. 2016.

10. Alqadah, H. F. and N. Valdivia, "Distributed radar imaging using a spatially enhanced linear sampling method," 2013 International Conference on Electromagnetics in Advanced Applications (ICEAA), 425-428, Sep. 2013.

11. Mittra, R., W. L. Ko, and P. Harms, "Detection of high conductivity objects buried in sea oor sediments," Proceedings of IEEE Antennas and Propagation Society International Symposium and URSI National Radio Science Meeting, Vol. 3, 1426-1429, Jun. 1994.

12. Mikki, S. M., A. M. Alzahed, and Y. M. M. Antar, "The spatial singularity expansion method for electromagnetics," IEEE Access, Vol. 7, 124 576-124 595, Feb. 2019.

13. Mikki, S., A. Hanoon, J. Persano, A. Alzahed, Y. Antar, and J. Aulin, "Theory of electromagnetic intelligent agents with applications to MIMO and DoA systems," 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting, 525-526, Jul. 2017.

14. Schmidhuber, J., "Deep learning in neural networks: An overview," Neural Networks, Vol. 61, 85-117, 2015.

15. Alzahed, A. M., Y. M. M. Antar, and S. M. Mikki, "Electromagnetic deep learning technology for radar target identification," 2019 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, 579-580, Jul. 2019.

16. Alzahed, A., S. Mikki, and Y. Antar, "Electromagnetic machine learning for inverse modeling using the spatial singularity expansion method," IEEE Journal on Multiscale and Multiphysics Computational Techniques, 1-1, 2020.

17. Mikki, S. M. and Y. M. M. Antar, New foundations for Applied Electromagnetics: The Spatial Structure of Fields, Artech House, 2016.

18. Mikki, S. M. and Y. M. M. Antar, "On the fundamental relationship between the transmitting and receiving modes of general antenna systems: A new approach," IEEE Antennas and Wireless Propagation Letters, Vol. 11, 232-235, 2012.

19. Mikki, S. M. and Y. M. M. Antar, "The antenna current Green’s function formalism: Part I," IEEE Transactions on Antennas and Propagation, Vol. 61, No. 9, 4493-4504, Sept. 2013.

20. Mikki, S. M. and Y. M. M. Antar, "The antenna current Green’s function formalism: Part II," IEEE Transactions on Antennas and Propagation, Vol. 61, No. 9, 4505-4519, Sept. 2013.

21. Goodfellow, I., Deep Learning, The MIT Press, Cambridge, Massachusetts, 2016.

22. Kolundzija, B. and M. Pavlovic, "Emulating magnetic ferrite tiles properties by wipl-d software suite," 2017 11th European Conference on Antennas and Propagation (EUCAP), 3611-3613, Mar. 2017.

23. Anderson, J. A., An introduction to Neural Networks, MIT Press, 1995.

24. Sapna, S., "Backpropagation learning algorithm based on Levenberg Marquardt algorithm," Computer Science & Information Technology (CS & IT), 393-398, 2012.

© Copyright 2010 EMW Publishing. All Rights Reserved