Utilizing Resonant Scattering Signal Characteristics of Magnetic Spheres via Deep Learning for Improved Target Classification

Object classification using LAte-time Resonant Scattering Electromagnetic Signals (LARSESs) is a significant problem found in different areas of application. Due to their special properties, spherical objects play an important role in this field both as a challenging target and analytical LARSES source. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant LARSESs from multi-layer 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 LARSESs of magnetic spheres provides diverse information and features, which result with superior object classification performance. For this purpose, first, time domain LARSESs are generated numerically for single and multi-layer radially symmetrical dielectric and magnetic spheres. Then, by using emerging deep learning tools, particularly Convolutional Neural Network (CNNs), which are trained with spheres having different material properties, a high multi-layer object classification performance is achieved. Moreover, by extending the proposed strategy to measured data via modern data augmentation and transfer learning techniques, an improved classification performance is also obtained for more complex targets.

[1]  B. Luk’yanchuk,et al.  Optically resonant dielectric nanostructures , 2016, Science.

[2]  Ercument Arvas,et al.  High-Frequency Scattering From Radially Uniaxial Dielectric Sphere , 2015, IEEE Antennas and Wireless Propagation Letters.

[3]  Moncef Gabbouj,et al.  A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals , 2009, IEEE Transactions on Biomedical Engineering.

[4]  Mário G. Silveirinha,et al.  Optical meta-atom for localization of light with quantized energy , 2015, Nature Communications.

[5]  Simon A. Wagner,et al.  SAR ATR by a combination of convolutional neural network and support vector machines , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Z. Jacob,et al.  All-dielectric metamaterials. , 2016, Nature nanotechnology.

[7]  M. Alper Selver,et al.  Comparison of scattered signal waveform recovery techniques under low SNR for target identification , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[8]  Mustafa Secmen,et al.  Hierarchical Reconstruction and Structural Waveform Analysis for Target Classification , 2016, IEEE Transactions on Antennas and Propagation.

[9]  Raed M. Shubair,et al.  Classification of Indoor Environments for IoT Applications: A Machine Learning Approach , 2018, IEEE Antennas and Wireless Propagation Letters.

[10]  E. Yeşim Zoral,et al.  Transferring Synthetic Elementary Learning Tasks to Classification of Complex Targets , 2019, IEEE Antennas and Wireless Propagation Letters.

[11]  G. C. Kokkorakis,et al.  Electromagnetic Scattering by a General Rotationally Symmetric Inhomogeneous Anisotropic Sphere , 2015, IEEE Transactions on Microwave Theory and Techniques.

[12]  Wei Cher Chen,et al.  Robust Target Identification Using a Modified Generalized Likelihood Ratio Test , 2014, IEEE Transactions on Antennas and Propagation.

[13]  A. Yapar,et al.  Electromagnetic Scattering by Radially Inhomogeneous Dielectric Spheres , 2015, IEEE Transactions on Antennas and Propagation.

[14]  Si-Wei Chen,et al.  PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural Network , 2018, IEEE Geoscience and Remote Sensing Letters.

[15]  A. Litman,et al.  Small Dielectric Spheres with High Refractive Index as New Multifunctional Elements for Optical Devices , 2015, Scientific Reports.