Least squares support vector machines for direction of arrival estimation with error control and validation

The paper presents a multiclass, multilabel implementation of least squares support vector machines (LS-SVM) for direction of arrival (DOA) estimation in a CDMA system. For any estimation or classification system, the algorithm´s capabilities and performance must be evaluated. Specifically, for classification algorithms, a high confidence level must exist along with a technique to tag misclassifications automatically. The presented learning algorithm includes error control and validation steps for generating statistics on the multiclass evaluation path and the signal subspace dimension. The error statistics provide a confidence level for the classification accuracy.