Publications

Abstract not provided.

Abstract not provided.

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.

Abstract not provided.

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.

Abstract not provided.

Abstract not provided.