volume | PIER Journals

Abstract

In the framework of buried object detection and subsurface sensing, some of the main difficulties in the reconstruction process are certainly due to the aspect-limited nature of available measurement data and to the requirement of an on-line reconstruction. To limit these problems, a multi-source (MS) learning-by-example (LBE) technique is proposed in this paper. In order to fully exploit the more attractive features of the MS strategy, the proposed approach is based on a support vector machine (SVM). The effectiveness of the MS-LBE technique is evaluated by comparing the achieved results with those obtained by means of a previously developed single-source (SS) SVMbased procedure for an ideal as well as a noisy environment.

1. Budko, N. V. and P. M. van den Berg, "Estimation of the average contrast of a buried object," Radio Science, Vol. 35, No. 2, 547-555, 2000.
doi:10.1029/1999RS900066 Google Scholar

2. Cui, T. J., W. C. Chew, A. A. Aleaddin, and S. Chen, "Inverse scattering of two-dimensional dielectric objects buried in a lossy earth using the distorted Born iterative method," IEEE Trans. on Geoscience and Remote Sensing, Vol. 39, No. 2, 339-346, 2001.
doi:10.1109/36.905242 Google Scholar

3. Caorsi, S., G. L. Gragnani, and M. Pastorino, "An electromagnetic imaging approach using a multi-illumination technique," IEEE Trans. Biomedical Engineering, Vol. 41, 406-409, 1994.
doi:10.1109/10.284973 Google Scholar

4. Chiu, C.-C. and C.-P. Huang, "Inverse scattering of dielectric cylinders buried in a half-space," Microwave and Optical Tech. Lett., Vol. 13, No. 2, 96-99, 1996.
doi:10.1002/(SICI)1098-2760(19961005)13:2<96::AID-MOP12>3.0.CO;2-7 Google Scholar

5. Bermani, E., S. Caorsi, and M. Raffetto, "An inverse scattering approach based on a neural network technique for the detection of dielectric cylinders buried in a lossy half-space," Progress in Electromagnetic Research, Vol. 26, 67-87, 2000.
doi:10.2528/PIER99052001 Google Scholar

6. Rekanos, I. T., "Inverse scattering of dielectric cylinders by using radial basis function neural networks," Radio Science, Vol. 36, No. 5, 841-849, 2001.
doi:10.1029/2000RS002545 Google Scholar

7. Bermani, E., A. Boni, S. Caorsi, and A. Massa, "An innovative real-time technique for buried object detection," IEEE Trans. on Geoscience and Remote Sensing, Vol. 41, No. 4, 927-931, 2003.
doi:10.1109/TGRS.2003.810928 Google Scholar

8. Caorsi, S., D. Anguita, E. Bermani, A. Boni, M. Donelli, and A. Massa, "A comparative study of NN and SVM based electromagnetic inverse scattering approaches to on-line detection of buried objects," Journal of the Applied Computational, Vol. 18, No. 2, 1-11, 2003. Google Scholar

9. Christodoulou, C. and M. Georgiopoulos, Applications of Neural Networks in Electromagnetics, Artech House, 2001.

10. Vapnik, V. N., The Nature of Statistical Learning Theory, John Wiley & Sons, 1999.

11. Platt, J., "Fast training of support vector machines using sequential minimal optimization," Advances in Kernel Methods â€” Support Vector Learning, 1999. Google Scholar

12. Mattera, D., F. Palmieri, and S. Haykin, "An explicit algorithm for training support vector machines," IEEE Signal Processing Letters, Vol. 6, No. 9, 243-245, 1999.
doi:10.1109/97.782071 Google Scholar

Dr. Emanuela Bermani

Dr. Andrea Boni

Dr. Salvatore Caorsi

Prof. Massimo Donelli

Prof. Andrea Massa