Title :
Real-time SVM-based approach for localization of sources
Author :
Pastorino, M. ; Randazzo, A.
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Genova
Abstract :
A method for the localization of electromagnetic sources and for the detection of passive scatterers when illuminated by interrogating waves is proposed. The directions of arrival of the signals generated by the sources are estimated by means of a regression technique based on the use of support vector machines (SVM). The proposed method, after a proper training procedure, is able to identify the angles of arrival both in the case in which they are included in training samples and in the case in which they are unknown. Numerical results are provided for the validation of the approach
Keywords :
direction-of-arrival estimation; electromagnetic wave scattering; real-time systems; regression analysis; signal generators; signal processing; support vector machines; angles of arrival; directions of arrival; electromagnetic sources localization; passive scatterer detection; real-time SVM-based approach; regression technique; support vector machine; Direction of arrival estimation; Directive antennas; Electromagnetic scattering; Mobile antennas; Modems; Multiple signal classification; Neural networks; Phased arrays; Signal generators; Support vector machines;
Conference_Titel :
Imaging Systems and Techniques, 2004. (IST). 2004 IEEE International Workshop on
Conference_Location :
Stresa
Print_ISBN :
0-7803-8591-8
DOI :
10.1109/IST.2004.1397270
