SV-Training and Kernel Change Detection Algorithm for the Abrupt Modification in EMI Data for Buried Metallic Target Localization and Identification
Keywords:
Decision index, electromagnetic induction, kernel change detection algorithm, mine detection, support vector trainingAbstract
In this paper, we propose a new method to identify and to locate buried metallic object in ElectroMagnetic Induction (EMI) data based on the Kernel Change Detection (KCD) algorithm. The signature of the object in the EMI data is typically of low amplitude. Particularly, in the case where two objects are located at different depths, the amplitude of the deeper buried object is negligible compared to that of the object buried in the first centimeter of the soil. This would result in the fact that, the EMI system can neglect the signature of this object and consequently increases miss rate or False Negative Rate (FNR). The aim of the proposed method is to calculate a decision index for each EMI measurement in a so-called hypotheses space using KCD algorithm. The amplitude of these decision indexes in the case of objects at different depths are in the same range, which make their variance smaller. Indeed, this index will be compared to a threshold for judging the presence or absence of a rupture. The validation of the proposed method is performed by processing real EMI data derived from a series of measurements on real objects.
Downloads
References
Y. Matriche, M. Feliachi, A. Zaoui, and M. Abdellah, “An EMI inversing problem for landmine characterization based on improved particle swarm optimization and finite element analysis,” Progress In Electromagnetics Research, B, vol. 49, pp. 411-428, March 2013.
K. Paulsen, I. Shamatava, F. Shubitidze, K. O’Neill, and K. Sun, “Fundamental mode approach to forward problem solutions in EMI scattering inferring fundamental solutions from training data,” Applied Computational Electromagnetics Society-Conference Computational Techniques, 2004.
K. P. Prokopidis and T. D. Tsiboukis, “Modeling of ground-penetrating radar for detecting buried objects in dispersive soils,” Applied Computational Electromagnetics Society, vol. 22, no. 2, 2007.
H. Huang, B. SanFilipo, A. Oren, and I. J. Won, “Coaxial coil towed EMI sensor array for uxo detection and characterization,” Journal of Applied Geophysics., vol. 61, no. 3-4, pp. 217- 226, March 2007.
F. Shubitidze, J. P. Fernandez, I. Shamatava, L. R. Pasion, B. E. Barrowes, and K. O’Neill, “Application of the normalized surface magnetic source model to a blind unexploded ordnance discrimination test,” Applied Computational Electromagnetics Society, vol. 25, no. 1, 2010.
S. Saidi and J. B. S. Hadj, “Improving convergence time of the electromagnetic inverse method based on genetic algorithm using the PZMI and neural network,” Progress In Electromagnetics Research, B, vol. 51, pp. 389- 406, April 2013.
M. Mahmoudi and S. Y. Tan, “Depth detection of conducting marine mines via eddy-current and current-channeling response,” Progress In Electromagnetics Research, PIER, vol. 90, pp. 287-307, 2009.
F. Desobry and M. Davy, “Support vector-based online detection of abrupt changes,” Proceedings IEEE Int. Conf. Acoust. Speech, Signal Process, (ICASSP 03), vol. 4, pp. 872-875, 2003.
F. Desobry, M. Davy, and C. Doncarli, “An online kernel change detection algorithm,” IEEE Trans. Signal Process, vol. 53, no. 8, pp. 2961-2974, August 2005.
M. Al Sharkawy, M. Sharkas, and D. Ragab, “Breast cancer detection using support vector machine technique applied on extracted electromagnetic waves,” Applied Computational Electromagnetics Society, vol. 27, no. 4, 2012.
D. Potin, P. Vanheeghe, E. Duflos, and M. Davy, “An abrupt change detection algorithm for buried landmines localization,” IEEE Trans. Geosci. Remote Sensing, vol. 44, no. 2, pp. 260-272, 2006.
S. Caorsi, D. Anguita, E. Bermani, A. Boni, and M. Donelli, “A comparative study of NN and SVM-based electromagnetic inverse scattering approaches to on-line detection of buried objects,” Applied Computational Electromagnetics Society, vol. 18, no. 2, 2003.
V. Vapnik, “The nature of statistical learning theory,” 2nd ed., Ser. Statistics for Engineering and Information Science, Springer, 1999.
T. Coleman and Y. Li, “A reflective Newton method for minimizing a quadratic function subject to bounds on some of the variables,” SIAM Journal on Optimization, vol. 6, no. 4, pp. 1040- 1058, 1996.
N. Gould and P. L. Toint, “Preprocessing for quadratic programming,” Mathematical Programming, Series B, vol. 100, pp. 95-132, 2004.
L. Capineri, S. Ivashov, T. Bechtel, A. Zhuravlev, P. Falorni, C. Windsor, G. Borgioli, I. Vasiliev, and A. Sheyko, “Comparison of GPR sensor types for landmine detection and classification,” 12th International Conference on Ground Penetrating Radar, 2008.