To solve the real-time through-wall detection problem in the presence of wall ambiguities, an approach based on the kernel extreme learning machine (KELM) is proposed in this paper. The wall ambiguity and propagation effect are included in the single-hidden-layer feedforward networks, and then the technique converts the through-wall problem into a regression problem. The relationship between the scattered data and the target properties is determined after the KELM training process. Numerical results demonstrate the good performance in terms of the effectiveness, generalization, and robustness. Compared with the support vector machine (SVM) and least-squares support vector machine (LS-SVM), the KELM provides almost the same estimated accuracy but at a much faster learning speed, which greatly contributes to solving the real-time detection problem. In addition, the situations of two targets, different target radiuses, and noisy circumstances are discussed.
1. Protiva, P., J. Mrkvica, and J. Machac, "Estimation of wall parameters from time-delay-only through-wall radar measurements," IEEE Trans. Antennas Propagat., Vol. 59, No. 11, 4268-4278, 2011. doi:10.1109/TAP.2011.2164206
2. Dehmollaian, M. and K. Sarabandi, "Refocusing through building walls using synthetic aperture radar," IEEE Trans. Geosci. Remot. Sens., Vol. 46, No. 6, 1589-1599, 2008. doi:10.1109/TGRS.2008.916212
3. Solimene, R., F. Soldovieri, G. Prisco, and R. Pierri, "Three-dimensional through-wall imaging under ambiguous wall parameters," IEEE Trans. Geosci. Remot. Sens., Vol. 47, No. 5, 1310-1317, 2009. doi:10.1109/TGRS.2009.2012698
4. Jin, T., B. Chen, and Z. Zhou, "Image-domain estimation of wall parameters for autofocusing of through-the-wall SAR imagery," IEEE Trans. Geosci. Remot. Sens., Vol. 51, No. 3, 1836-1843, 2013. doi:10.1109/TGRS.2012.2206395
5. Soldovieri, F. and R. Solimene, "Through-wall imaging via a linear inverse scattering algorithm," IEEE Geosc. Rem. Sens. Lett., Vol. 4, No. 4, 513-517, 2007. doi:10.1109/LGRS.2007.900735
6. Li, L. L., W. J. Zhang, and F. Li, "A novel autofocusing approach for real-time through-wall imaging under unknown wall characteristics," IEEE Trans. Geosci. Remot. Sens., Vol. 48, No. 1, 423-431, 2010. doi:10.1109/TGRS.2009.2024686
7. Wang, G. Y., M. G. Amin, and Y. M. Zhang, "New approach for target locations in the presence of wall ambiguities," IEEE Trans. Aero. Elec. Sys., Vol. 42, No. 1, 301-315, 2006. doi:10.1109/TAES.2006.1603424
8. Ahmad, F., M. G. Amin, and G. Mandapati, "Autofocusing of through-the-wall radar imagery under unknown wall characteristics," IEEE Trans. on Image Proc., Vol. 16, No. 7, 1785-1795, 2007. doi:10.1109/TIP.2007.899030
9. Zhang, H. M., Z. B. Wang, Z. H. Wu, F. F. Wang, and Y. R. Zhang, "Real-time through-wall radar image under unknown wall characteristics using LS-SVM-based method," J. Appl. Remote Sens., Vol. 10, No. 2, 020501-1-8, 2016.
10. Huang, G. B., "An insight into extreme learning machines: Random neurons, random features and kernels," Cognitive Computation, Vol. 6, No. 3, 376-390, 2014. doi:10.1007/s12559-014-9255-2
11. Huang, G. B., Q. Y. Zhu, and C. K. Siew, "Extreme learning machine: A new learning scheme of feedforward neural networks," IEEE International Joint Conference on Neural Networks, 985-990, 2004.
12. Huang, G. B., X. J. Ding, and H. M. Zhou, "Optimization method based extreme learning machine for classification," Neurocomputing, Vol. 74, No. 1, 155-163, 2010. doi:10.1016/j.neucom.2010.02.019
13. Huang, G. B., H. M. Zhou, X. J. Ding, and R. Zhang, "Extreme learning machine for regression and multiclass classi¯cation," IEEE Trans. on Sys., Man, and Cybernetics, Part B: Cybernetics, Vol. 42, No. 2, 513-529, 2012. doi:10.1109/TSMCB.2011.2168604
14. Huang, G. B., Y. Lan, and D. H. Wang, "Extreme learning machines: A survey," Int. J. Mach. Learn. Cyb., Vol. 2, No. 2, 107-122, 2011. doi:10.1007/s13042-011-0019-y
15. Frenay, B. and M. Verleysen, "Parameter-insensitive kernel in extreme learning for non-linear support vector regression," Neurocomputing, Vol. 74, No. 16, 2526-2531, 2011. doi:10.1016/j.neucom.2010.11.037