UWB Subsurface Radiolocation for Object Location Classification by Artificial Neural Networks Based on Discrete Tomography Approach

The two-dimensional problem of the subsurface object depth determination is solved by the impulse electromagnetic plane wave irradiation of the surface and analysis of reflected wave received by set of probes placed above the surface. The analysis of the signals is carried out by means of artificial neural networks (ANN) improved by additional data usage from the signals and parameters of structure. The problem of Gaussian pulse propagation in the subsurface medium with objects is solved by FDTD method. The electrical field strength amplitudes above the model of a ground in a number of time points form a first part of the set of input data for a multilayer ANN. The second part of input data includes a special linear superposition of data from the first part with coefficients received on the base of discrete tomography approach and ray tracing method. The work of the ANN is verified by the problem of impulse electromagnetic wave irradiation of perfectly conducting object inside ground. The precision of the determination of the object depth and influence of the second part of input data are investigated for test cases.

[1]  Oleksandr M. Dumin,et al.  Time domain analysis of fields reflected from model of human body surface using artificial neural network , 2009, 2009 3rd European Conference on Antennas and Propagation.

[2]  Yu. V. Yastrebov,et al.  Practical application of UWB georadar technique for investigations of cultural heritage objects , 2010, 2010 5th International Confernce on Ultrawideband and Ultrashort Impulse Signals.

[3]  John C. Cook,et al.  Proposed monocycle-pulse very-high-frequency radar for air-borne ice and snow measurement , 1960, Transactions of the American Institute of Electrical Engineers, Part I: Communication and Electronics.

[4]  Chi-Chih Chen,et al.  Ultrawide-bandwidth fully-polarimetric ground penetrating radar classification of subsurface unexploded ordnance , 2001, IEEE Trans. Geosci. Remote. Sens..

[5]  G. Herman,et al.  Discrete tomography : foundations, algorithms, and applications , 1999 .

[6]  Wei-Ping Wang,et al.  Constructive neural network for landmine classification using ultra wideband GPR , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[7]  A. V. Doronin,et al.  Estimation of thickness of subsurface air layer by neuron network technology application to reflected microwave signal , 2008, 2008 12th International Conference on Mathematical Methods in Electromagnetic Theory.

[8]  O. Dumin,et al.  Artificial neural networks in time domain electromagnetics , 2017, 2017 XI International Conference on Antenna Theory and Techniques (ICATT).

[9]  O.O. Drobakhin,et al.  Neural Network Application for Dielectric Structure Parameter Determination by Multifrequency Methods , 2006, 2006 3rd International Conference on Ultrawideband and Ultrashort Impulse Signals.

[10]  V. Katrich,et al.  Analysis of transient fields reflected from model of huma body surface using convolutional neural network , 2010, 2010 International Conference on Mathematical Methods in Electromagnetic Theory.

[11]  Dmitry O. Batrakov,et al.  UWB Signal Processing for the Solving Inverse Scattering Problem of Plane-Layered Media , 2018, 2018 9th International Conference on Ultrawideband and Ultrashort Impulse Signals (UWBUSIS).

[12]  F. J. Yanovsky,et al.  Through-the-wall surveillance technologies , 2012, 2012 6th International Conference on Ultrawideband and Ultrashort Impulse Signals.

[13]  T. Martinez,et al.  Softprop: softmax neural network backpropagation learning , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[14]  Dharmendra Singh,et al.  Non-metallic pipe detection using SF-GPR: A new approach using neural network , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[15]  O. O. Drobakhin,et al.  Recognition of microwave multifrequency images of objects hidden behind wall , 2012, 2012 6th International Conference on Ultrawideband and Ultrashort Impulse Signals.

[16]  Robert Callan,et al.  The essence of neural networks , 1998 .

[17]  O. Dumin,et al.  Application of UWB Electromagnetic Waves for Subsurface Object Location Classification by Artificial Neural Networks , 2018, 2018 9th International Conference on Ultrawideband and Ultrashort Impulse Signals (UWBUSIS).

[18]  P. R. Anurenjan,et al.  A dynamic bow-tie antenna using soft computing methods , 2013, 2013 International Conference on Control Communication and Computing (ICCC).

[19]  Liudmyla A. Varianytsia-Roshchupkina,et al.  Subsurface object imaging with two types of RTR-differential GPR system , 2016, 2016 8th International Conference on Ultrawideband and Ultrashort Impulse Signals (UWBUSIS).

[20]  D.V. Shyrokorad,et al.  Time domain analysis of reflected impulse fields by artificial neural network , 2008, 2008 4th International Conference on Ultrawideband and Ultrashort Impulse Signals.

[21]  James D. Taylor,et al.  Ultrawideband Radar: Applications and Design , 2012 .

[22]  G. Pochanin,et al.  Subsurface Object Identification by Artificial Neural Networks and Impulse Radiolocation , 2018, 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP).

[23]  Sofiène Affes,et al.  Neural Networks for Fingerprinting-Based Indoor Localization Using Ultra-Wideband , 2009, J. Commun..

[24]  T. Bechtel,et al.  Modern trends in development and application of the UWB radar systems , 2016, 2016 8th International Conference on Ultrawideband and Ultrashort Impulse Signals (UWBUSIS).

[25]  Allen Taflove,et al.  Computational Electrodynamics the Finite-Difference Time-Domain Method , 1995 .

[26]  Yasuhiro Fujiwara,et al.  Sigsoftmax: Reanalysis of the Softmax Bottleneck , 2018, NeurIPS.