Electromagnetic Radiation Source Identification Based on Spatial Characteristics by Using Support Vector Machines
Keywords:
Band receiver array, electromagnetic radiation source identification, spatial characteristics, support vector machinesAbstract
In the radio monitoring, electromagnetic interference diagnostics and radar detection, the electromagnetic radiation source identification (ERSI) is a key technology. A new method for ERSI was proposed. The support vector machines (SVMs) have been applied to facilitate the ERSI on the basis of the spatial characteristics of the electromagnetic radiation sources. The radiation sources were located by the triangulation method, and then their spatial characteristics were collected by a band receiver array, and converted from 3D data to 1D vector with subscripts as the inputs for the SVMs. We trained the model with these 1D vectors to enable it to identify the radiation source types with both high speed and accuracy. The identification time needs only a few seconds, which is much faster than the artificial neural networks (ANNs). The influence of parameters (e.g., noise from the ambient environment, the data collection method, the scaling method for the input data, and the penalty parameter) were discussed. The proposed method has good performance even in the noisy environments. The results were verified by a designed measurement. The proposed approach is very useful for the ERSI of unknown radiation sources in practice.
Downloads
References
Z. F. Song and D. L. Su, “A novel electromagnetic radiated emission source identification methodology,” Proceeding of 2010 Asia-Pacific International Symposium on Electromagnetic Compatibility, pp. 645-648, 2010.
H. Weng, X. Dong, X. Hu, D. G. Beetner, T. Hubing, and D. Wunsch, “Neural network detection and identification of electronic devices based on their unintended emissions,” International Symposium on EMC, vol. 1, pp. 245-249, 2005.
X. Dong, H. Weng, and D. G. Beetner, “Detection and identification of vehicles based on their unintended electromagnetic emissions,” IEEE Transaction on Electromagnetic Compatibility, vol. 48, no. 4, pp. 752-759, 2006.
T. Hubing, D. Beetner, X. Dong, H. Weng, M. Noll, B. Moss, and D. Wunsch, “Electromagnetic detection and identification of automobiles,” Proceeding of EuroEM, Magdeburg Germany, July 2004.
H. Weng, X. Dong, X. Hu, D. Beetner, T. Hubing, and D. Wunsch, “Neural network detection and identification of electronic devices based on their unintended emissions,” in Proc. IEEE Int. Symp. Electromagn. Compat., 2005, vol. 1, pp. 245-249, 2005.
C. J. Kaufman, J. Dudczyk, J. Matuszewski, and M. Wnuk, “Applying the radiated emission to the specific emitter identification,” in Proc. 15th Int. Conf. Microwave, Radio Wireless Commun., Warsaw, Poland, vol. 2, pp. 431-434, May 17-19, 2004.
M. D’Amore, A. Morriello, and M. S. Sarto, “A neural network approach for identification of EM field sources: Analysis of PCB configurations,” in Proc. IEEE Int. Symp. Electromagn. Compat., Denver, CO, vol. 2, pp. 664-669, Aug. 24-28, 1998.
K. Aunchaleevarapan, K. Paithoonwatanakij, Y. Prempreaneerach, W. Khanngern, and S. Nitta, “Classification of PCB configurations from radiated EMI by using neural network,” in Proc. CEEM, Shanghai, China, pp. 105-110, May 3-7, 2000.
C.-S. Shieh and C.-T. Lin, “A vector neural network for emitter identification,” IEEE Trans. Antennas Propag., vol. 50, no. 8, pp. 1120-1127, Aug. 2002.
H. Liu, Z. Liu, and W. Jiang, “Approach based on combination of vector neural networks for emitter identification ,” IET Signal Processing, vol. 4, no.2, pp. 137-148, 2010.
H. Liu, Z. Liu, and W. Jiang, “Incremental learning approach based on vector neural network for emitter identification,” IET Signal Processing, vol. 4, no.1, pp. 45-54, 2010.
L. Li, H. B. Ji, and L. Jiang, “Quadratic timefrequency analysis and sequential recognition for specific emitter identification,” IET Signal Processing, vol. 5, no. 6, pp. 568-574, 2011.
M. Wnuk, A. Kawalec, and J. Dudczyk, “The method of regression analysis approach to the specific emitter identification,” Proceeding of 16th International Conference on Microwaves, Radar and Wireless Communications, Krakow, Poland, pp. 491-494, May 22-24, 2006.
X. Chen and W. D. Hu, “Approach based on interval type-2 fuzzy logic system for emitter identification,” Electronics Letters, vol. 48, no. 18, 2012.
M. Liu and J. F. Doherty, “Nonlinearity estimation for specific emitter identification in multipath channels,” IEEE Transactions on Information Forensics and Security, vol. 6, no. 3, pp. 1076- 1085, 2011.
H. Ye, Z Liu, and W. Jiang, “Comparison of unintentional frequency and phase modulation features for specific emitter identification,” Electronics Letters, vol. 48, iss. 14, pp. 875-877, 2012.
L. Anjaneyulu, N. S. Murthy, and N. Sarma, “Radar emitter classification using self-organising neural network models,” Proceedings of International Conference on Recent Advances in Microwave Theory and Applications, Jaipur, Rajasthan, India, pp. 431-433, Nov. 21-24, 2008.
Y. Zhang, H. P. Zhao, and Q. Wan, “Single snapshot 2D-DOA estimation in impulsive noise environment using linear arrays,” ACES Journal, vol. 27, no. 12, pp. 991-998, 2012.
F. Mavromatis, A. Boursianis, T. Samaras, C. Koukourlis1, and J. N. Sahalos, “A broadband monitoring system for electromagnetic-radiation assessment,” IEEE Antennas and Propagation Magazine, vol. 51, iss. 1, pp. 71-79, 2009.
C. Camilo Rodríguez, C. Andrés Forero, and H. Ortega Boada, “Electromagnetic field measurement method to generate radiation map,” IEEE Colombian Communications Conference, pp. 1-7, 2012.
D. Shi and Y. G. Gao, “A new method for identifying electromagnetic radiation sources using backpropagation neural network,” IEEE Transactions on Electromagnetic Compatibility, vol. 55, iss. 5, pp. 842-848, 2013.
D. Shi and Y. G. Gao, “A method of identifying electromagnetic radiation sources by using support vector machines,” China Communications, vol. 10, iss. 7, pp. 36-43, 2013.
C. Nello and S.-T. John, An Introduction To Support Vector Machines And Other Kernel-based Learning Methods. Cambridge University Press, 2000.
B. Schölkopf, C. J. C. Burges, and A. J. Smola, Advances In Kernel Methods: Support Vector Learning. MIT Press, Cambridge, MA, 1999.
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273-297, 1995.
Q. Yuan, Q. Chen, and K. Sawaya, “Accurate DOA estimation using array antenna with arbitrary geometry,” IEEE Transactions on Antennas and Propagation, vol. 53, no. 4, pp. 1352-1357, 2005.
A Practical Approach to Identifying and Tracking Unauthorized 802.11 Cards and Access Points. http://www.interlinknetworks.com/graphics/news/ wireless_detection_and_tracking.pdf
ANSYS[EB/OL]. http://www.ansys.com/Products/ Simulation+Technology/Electromagnetics/HighPerformance+Electronic+Design/ANSYS+HFSS
