An Innovative Multiresolution Approach for DOA Estimation Based on a Support Vector Classification
- 5 June 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 57 (8) , 2279-2292
Abstract
The knowledge of the directions of arrival (DOAs) of the signals impinging on an antenna receiver enables the use of adaptive control algorithm suitable for limiting the effects of interferences and increasing the gain towards the desired signals in order to improve the performances of wireless communication systems. In this paper, an innovative multi-resolution approach for the real-time DOA estimation of multiple signals impinging on a planar array is presented. The method is based on a support vector classifier and it exploits a multi-scaling procedure to enhance the angular resolution of the detection process in the regions of incidence of the incoming waves. The data acquired from the array sensors are iteratively processed with a support vector machine (SVM) customized to the problem at hand. The final result is the definition of a map of the probability that a signal impinges on the antenna from a fixed angular direction. Selected numerical results, concerned with both single and multiple signals, are provided to assess potentialities and current limitations of the proposed approach.Keywords
This publication has 22 references indexed in Scilit:
- A classification approach based on SVM for electromagnetic subsurface sensingIEEE Transactions on Geoscience and Remote Sensing, 2005
- A smart antenna system for direction of arrival estimation based on a support vector regressionIEEE Transactions on Antennas and Propagation, 2005
- A MULTI-SOURCE STRATEGY BASED ON A LEARNING-BY-EXAMPLES TECHNIQUE FOR BURIED OBJECT DETECTIONProgress In Electromagnetics Research, 2004
- A digital architecture for support vector machines: theory, algorithm, and fpga implementationIEEE Transactions on Neural Networks, 2003
- The control of adaptive antenna arrays with genetic algorithms using dominance and diploidyIEEE Transactions on Antennas and Propagation, 2001
- A neural network-based smart antenna for multiple source trackingIEEE Transactions on Antennas and Propagation, 2000
- Maximum-likelihood DOA estimation by data-supported grid searchIEEE Signal Processing Letters, 1999
- Performance of radial-basis function networks for direction of arrival estimation with antenna arraysIEEE Transactions on Antennas and Propagation, 1997
- Planar dipole arrays with equal element input impedancesElectronics Letters, 1995
- Maximum likelihood localization of multiple sources by alternating projectionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988