Estimating the frequency and bandwidth of square-split ring resonator (S-SRR) designs via support vector machines (SVM)

Abstract

In this study Support Vector Machine (SVM) based estimation technique is proposed for estimating the bandstop frequency and bandwidth of square-split ring resonators. Artificially engineered surfaces especially the planar frequency selective surfaces like the SRRs have narrowband properties so that estimating the filtering frequencies and the bandwidth is essential in a cost and design-effective way. The proposed method, which is superior to optimization methods and 3D electromagnetic solvers in terms of cost and computational burden, achieved accurate results via SVMs generalization capability. This study represents two SVM regression models one for predicting frequency and the other for predicting bandwidth having fast response and accuracy. Results of the proposed model reveal that resonance frequency estimation error, in terms of percentage, is bounded in the interval [0.0542, 3.5938], with an overall error of 0.89 % for the test data. The mean and standard deviation of the percentage error is obtained as 0.9861 and 0.9376, respectively. In addition to that -10dB bandwidth is estimated with the bounded error where estimation error in terms of percentage would be lie in the interval [0.068925, 6.876800] with an overall error of 3.68% for the test data.

Keywords

• Bandwidth estimation
• filtering
• frequency estimation
• machine learning
• support vector machine

References

1. Can, S., Yilmaz, A.E., Reduction of specific absorption rate with artificial magnetic conductors, Int. J. RF Microw. Comput. Aided Eng., 26 (4) (2016), 349-354. https://doi.org/10.1002/mmce.20974
2. Munk, B.A., Frequency Selective Surfaces: Theory and Design, John Wiley and Sons Inc., New York, 2000.
3. Vapnik, V.N., The Nature of Statistical Learning Theory, Springer-Verlag, New York, 1995.
4. Tsai, H.H., Chang, Y.C., Facial expression recognition using a combination of multiple facial features and support vector machine. Soft Comput., 22 (2018), 4389-4405. https://doi.org/10.1007/s00500-017-2634-3
5. Aly, S., Mohamed, A., Unknown-length handwritten numeral string recognition using cascade of PCA-SVMNet classifiers, IEEE Access, 7 (2019), 52024-52034. https://doi.org/10.1109/ACCESS.2019.2911851
6. Yaman, S., Pelecanos, J., Using polynomial kernel support vector machines for speaker verification, IEEE Signal Process. Lett., 20 (9) (2013), 901-904. https://doi.org/10.1109/LSP.2013.2273127
7. Gunes, F., Tokan, N.T., Gurgen, F., Support vector design of the microstrip lines, Int. J. RF Microw. Comput. Aided Eng., 18 (2008), 326-336. https://doi.org/10.1002/mmce.20290
8. Zheng, Z., Chen, X., Huang, K., Application of support vector machines to the antenna design, Int. J. RF Microw. Comput. Aided Eng., 21 (1) (2011), 85–90. https://doi.org/10.1002/mmce.20491

9. El Misilmani, H.M., Naous, T., Al Khatib, S.K., A review on the design and optimization of antennas using machine learning algorithms and techniques, Int. J. RF Microw. Comput. Eng., 30 (2020), 22356. https://doi.org/10.1002/mmce.22356
10. Gunn, S.R., Support vector machines for classification and regression, SISI Tech. Reports, (1998) 6459.
11. Cortes, C., Vapnik, V.N., Support vector networks, Mach. L., 20 (1997), 73-297.
12. Yilmaz, A.E., Kuzuoglu, M., Design of the square loop frequency selective surfaces with particle swarm optimization via the equivalent circuit model, Radioengineering, 18 (2) (2009), 95-102.
13. Li, J., Li, Y., Cen,Y., Zhang, C., Luo, T., Yang, D., Applications of neural networks for spectrum prediction and inverse design in the terahertz band, IEEE Photonics J., 12 (5) (2020),1-9. https://doi.org/10.1109/JPHOT.2020.3022053
14. Qiu, T., Deep learning: a rapid and efficient route to automatic metasurface design, Adv. Sci. Lett., 6 (12) (2019), 1900128. https://doi.org/ 10.1002/advs.201900128
15. Alcantara Neto, M.C.A, Oeiras Ferreira, H.R., Leite de Araujo, J.P., Brito Barros F.J., Gomes Neto, A., Oliveira Alencar, M., dos Santos Cavalcante, G.P., Compact ultra-wideband FSS optimized through fast and accurate hybrid bio-inspired multi objective technique, IET Microwaves, Antennas & Propag., 14 (2020), 884-890. https://doi.org/10.1049/iet-map.2019.0821
16. Chaudhary, V., Panwar, R., FSS derived using a new equivalent circuit model backed deep neural network., IEEE Antennas Wirel. Propag. Lett., 20 (10) (2021), 1963-1967. https://doi.org/ 10.1109/LAWP.2021.3101225
17. Bozzi, M., Manara, G., Monorchio, A., Perregrini, L., Automatic design of inductive FSSs using the genetic algorithm and the MoM/BI-RME analysis, IEEE Antennas Wirel. Propag. Lett., 1 (2002), 91-93. https://doi.org/10.1109/LAWP.2002.805129
18. Chakravarty, S., Mittra, R., Design of a frequency selective surface (FSS) with very low cross-polarization discrimination via the parallel micro-genetic algorithm (PMGA), IEEE Trans. Antennas Propag., 51 (7) (2003), 1664-1668. https://doi.org/10.1109/TAP.2003.813637
19. Zhu, D.Z., Werner, P.L., Werner, D.H., Design and optimization of 3-D frequency selective surfaces based on a multi objective lazy ant colony optimization algorithm, IEEE Trans. Antennas Propag., 65 (12) (2017), 7137-7149. https://doi.org/10.1109/TAP.2017.2766660
20. Ohira, M., Deguchi, H., Tsuji, M., Shigesawa, H. Multiband single-layer frequency selective surface designed by combination of genetic algorithm and geometry-refinement technique, IEEE Trans. Antennas Propag., 52 (11) (2004), 2925-2931. https://doi.org/10.1109/TAP.2004.835289
21. Monorchio, A., Manara, G., Serra, U., Marola, G., Pagana, E., Design of waveguide filters by using genetically optimized frequency selective surfaces., IEEE Microw. Wirel. Compon. Lett., 15 (6) (2005), 407-409. https://doi.org/10.1109/LMWC.2005.850482
22. Cui, S., Weile, D.S., Volakis, J.L., Novel planar electromagnetic absorber designs using genetic algorithms., IEEE Trans. Antennas Propag., 54 (6) (2006), 1811-1817. https://doi.org/10.1109/TAP.2006.87546