Publications

Least squares support vector machines for direction of arrival estimation

Rohwer, Judd A.; Abdallah, Chaouki T.; Christodoulou, Christos G.

A multiclass LS-SVM architecture for DOA estimation as applied to a CDMA cellular system is presented. As such, simulation results showed a high degree of accuracy, as related to the DOA classes and proved that the LS-SVM DDAG system has a wide range of performance capabilities. The broad range of the research in machine learning based DOA estimation includes multilabel and multiclass classification, classification accuracy, error control and validation, kernel selection, estimation of signal subspace dimension, and overall performance characterization of the LS-SVM DDAG DOA estimation algorithm.