M. Alper SELVER, E. Yeşim ZORAL, Tuğçe TOPRAK, Mustafa SEÇMEN

Utilizing resonant scattering signal characteristics via deep learning for improved classification of complex targets

Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties, spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover, existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and coatings. However, especially for metamaterials, magneto-dielectric inclusions require consideration of magnetic properties as well as dielectric ones. In this respect, this study shows that the utilization late-time resonant scattering electromagnetic signals of magnetic spheres provide diverse information and features, which result in superior object classification performance. For this purpose, first, time-domain late-time resonant scattering electromagnetic signals are generated numerically for single and multilayer radially symmetrical dielectric and magnetic spheres. Then, by using emerging deep learning tools, particularly convolutional neural networks trained with spheres having different material properties, a high multilayer object classification performance is achieved. Furthermore, by incorporating the frequency characteristics of the late-time resonant scattering electromagnetic signals to the classification process through Fourier transform and convolutional neural network layers for feature extraction, a convolutional neural network with long short term memory algorithm is developed. The outcome of the proposed algorithm design is shown to be particularly successful even in the case of limited available data on challenging targets. This extended strategy is also shown to outperform modern data augmentation and transfer learning techniques in terms of accuracy as well as the computational cost

PDF

___

1] Kuznetsov AI, Miroshnichenko AE, Brongersma ML, Kivshar YS, Luk’yanchuk B. Optically resonant dielectric nanostructures. Science 2016; 354 (6314): 2472. doi: 10.1126/science.aag2472
[2] Jahani S, Jacob Z. All-dielectric metamaterials. Nature Nanotechnology 2016; 11 (1): 23-36. doi: 10.1038/nnano.2015.304
[3] Tribelsky MI, Geffrin JM, Litman A, Eyraud C, Moreno F. Small dielectric spheres with high refractive index as new multifunctional elements for optical devices. Scientific Reports 2015; 5 (1): 1-7. doi: 10.1038/srep12288
[4] Selver MA, Taygur MM, Seçmen M, Zoral EY. Hierarchical reconstruction and structural waveform analy- sis for target classification. IEEE Transactions on Antennas and Propagation 2016; 64 (7): 3120-3129. doi: 10.1109/TAP.2016.2567438
[5] Lannebère S, Silveirinha MG. Optical meta-atom for localization of light with quantized energy. Nature Commu- nications 2015; 6 (1): 1-7. doi: 10.1038/ncomms9766
[6] Shore RA. Scattering of an electromagnetic linearly polarized plane wave by a multilayered sphere: obtaining a computational form of mie coeﬀicients for the scattered field. IEEE Antennas and Propagation Magazine 2015; 57 (6): 69-116. doi: 10.1109/MAP.2015.2453885
[7] Kavur AE, Gezer NS, Barış M, Şahin Y, Özkan S et al. Comparison of semi-automatic and deep learning-based automatic methods for liver segmentation in living liver transplant donors. Diagnostic and Interventional Radiology 2020; 26 (1): 11-21. doi: 10.5152/dir.2019.19025
[8] Selver MA. A robotic system for warped stitching based compressive strength prediction of marbles. IEEE Trans- actions on Industrial Informatics 2019; 16 (11): 6796-6805. doi: 10.1109/TII.2019.2926372
[9] Toprak T, Belenlioğlu B, Aydın B, Güzeliş C, Selver MA. Conditional weighted ensemble of transferred models for camera based onboard pedestrian detection in railway driver support systems. IEEE Transactions on Vehicular Technology 2020; 69 (5): 5041 - 5054. doi: 10.1109/TVT.2020.2983825
[10] Dollar P, Wojek C, Schiele B, Perona P. Pedestrian detection: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition; Miami, FL, USA; 2009. pp. 304-311.
[11] Benenson R, Omran M, Hosang J, Schiele B. Ten years of pedestrian detection, what have we learned?. In: European Conference on Computer Vision; Zurich, Switzerland; 2014. pp. 613-627.
[12] Yu D, Deng L. Deep learning and its applications to signal and information processing. IEEE Signal Processing Magazine 2011; 28 (1): 145 - 154. doi: 10.1109/MSP.2010.939038
[13] Selver MA, Seçmen M, Zoral EY. Comparison of scattered signal waveform recovery techniques under low SNR for target identification. In: IEEE 2017 11th European Conference on Antennas and Propagation; Paris, France; 2017. pp. 1091-1095.
[14] Yazdani M, Mautz J, Murphy L, Arvas E. High-frequency scattering from radially uniaxial dielectric sphere. IEEE Antennas and Wireless Propagation Letters 2015; 14: 1577-1581. doi: 10.1109/LAWP.2015.2413399
[15] Bilgin EE, Yapar A. Electromagnetic scattering by radially inhomogeneous dielectric spheres. IEEE Transactions on Antennas and Propagation 2015; 63 (6): 2677-2685. doi: 10.1109/TAP.2015.2415856
[16] Zouros GP, Kokkorakis GC. Electromagnetic scattering by a general rotationally symmetric inhomogeneous anisotropic sphere. IEEE Transactions on Microwave Theory and Techniques 2015; 63 (10): 3054-3065. doi: 10.1109/TMTT.2015.2472399
[17] Chen S, Tao C. PolSAR Image classification using polarimetric- feature-driven deep convolutional neural network. IEEE Geoscience and Remote Sensing Letters 2018; 15 (4): 627-631. doi: 10.1109/LGRS.2018.2799877
[18] Wagner SA. SAR ATR by a combination of convolutional neural network and support vector machines. IEEE Transactions on Aerospace and Electronic Systems 2016; 52 (6): 2861-2872. doi: 10.1109/TAES.2016.160061
[19] AlHajri MI, Ali NT, Shubair RM. Classification of indoor environments for iot applications: a ma- chine learning approach. IEEE Antennas and Wireless Propagation Letters 2018; 17 (12): 2164-2168. doi: 10.1109/LAWP.2018.2869548
[20] Kavur AE, Kuncheva LI, Selver MA. Basic Ensembles of Vanilla-Style Deep Learning Models Improve Liver Segmentation From CT Images. arXiv preprint 2020; arXiv:2001.09647.
[21] Chen WC, Shuley NVZ. Robust target identification using a modified generalized likelihood ratio test. IEEE Transactions on Antennas and Propagation 2013; 62 (1): 264-273. doi: 10.1109/TAP.2013.2287019
[22] Selver MA, Toprak T, Seçmen M, Zoral EY. Transferring synthetic elementary learning tasks to classifica- tion of complex targets. IEEE Antennas and Wireless Propagation Letters 2019; 18 (11): 2267-2271. doi: 10.1109/LAWP.2019.2930602
[23] Jithesh V, Sagayaraj MJ, Srinivasa KG. LSTM recurrent neural networks for high resolution range profile based radar target classification. In: 3rd International Conference on Computational Intelligence and Communication Technology; Ghaziabad, India; 2017. pp. 1-6.
[24] Sehgal B, Shekhawat HS, Jana SK. Automatic target recognition using recurrent neural networks. In: International Conference on Range Technology; Balasore, OR, India; 2019. pp. 1-5.
[25] Zhang F, Hu C, Yin Q, Li W, Li HC et al. Multi-aspect-aware bidirectional LSTM networks for synthetic aperture radar target recognition. IEEE Access 2017; 5: 26880-26891. doi: 10.1109/ACCESS.2017.2773363
[26] Balanis CA. Advanced Engineering Electromagnetics. 2nd edition. New York, NY, USA: John Wiley & Sons, 2012.
[27] Zhang X, Geng Y, Cheng Z. A multiple-reflection solution to electromagnetic scattering by a buried sphere. IEEE Transactions on Antennas and Propagation 2020; 68 (4): 3313-3317. doi: 10.1109/TAP.2020.2971620
[28] Gholami R, Okhmatovski V. Surface-volume-surface efie formulation for fast direct solution of scattering problem on General 3-D Composite Metal-Dielectric Objects. IEEE Transactions on Antennas and Propagation 2020; 68 (7): 5742-5747. doi: 10.1109/TAP.2020.2968762
[29] Ince T, Kiranyaz S, Gabbouj M. A generic and robust system for automated patient-specific classification of ECG Signals. IEEE Transactions on Biomedical Engineering 2009; 56 (5): 1415-1426. doi: 10.1109/TBME.2009.2013934.
[30] Wu J. Target classification and identification techniques for advanced metric wave radar. In: Wu J (editor). Advanced Metric Wave Radar. 1st ed. Singapore: Springer, 2020, pp. 255-294.