A Support Vector Machine MUSIC Algorithm

• Published in: IEEE transactions on antennas and propagation 2012-10, Vol.60 (10), p.4901-4910
• Main Authors: El Gonnouni, A., Martinez-Ramon, Manel, Rojo-Alvarez, J. L., Camps-Valls, G., Figueiras-Vidal, A. R., Christodoulou, C. G.
• Format: Article
• Language: English
• Subjects: Algorithms; Antennas; Applied classical electromagnetism; Arrays; Coherence; Derivation; Direction of arrival (DOA); Direction of arrival estimation; Distortion; Electromagnetic wave propagation, radiowave propagation; Electromagnetism; electron and ion optics; Estimation; Exact sciences and technology; Fundamental areas of phenomenology (including applications); Minimum Variance Distortionless Response (MVDR); MUltiple SIgnal Characterization (MUSIC); Multiple signal classification; Noise; Physics; Recursive; Support Vector Machine (SVM); Support vector machines
• ISSN: 0018-926X; 1558-2221
• DOI: 10.1109/TAP.2012.2209195

This paper introduces a new Support Vector Machine (SVM) formulation for the direction of arrival (DOA) estimation problem. We establish a theoretical relationship between the Minimum Variance Distortionless Response (MVDR) and the MUltiple SIgnal Characterization (MUSIC) methods. This leads naturally to the derivation of an SVM-MUSIC algorithm, which combines the benefits of subspace methods with those of SVM. Spatially smoothed versions and a recursive form of the algorithms exhibit good performance against coherent signals. We test the method's performance in scenarios with noncoherent and coherent signals, and in small-sample size-situations obtaining an improved performance in comparison with existing standard approaches.