Electrical & Computer Engineering Faculty Publications
Document Type
Article
Publication Date
12-1-2003
Abstract
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.
Publisher
IEEE
Publication Title
IEEE Global Telecommunications Conference
ISSN
0-7803-7974-8
First Page
2172
Last Page
2176
DOI
10.1109/GLOCOM.2003.1258620
Language (ISO)
English
Sponsorship
IEEE
Keywords
Chaotic communication, Classification algorithms, Direction of arrival estimation
Recommended Citation
Abdallah, Chaouki T.; Judd A. Rohwer; and Christos G. Christodoulou. "Least squares support vector machines for direction of arrival estimation with error control and validation." IEEE Global Telecommunications Conference (2003): 2172-2176. doi:10.1109/GLOCOM.2003.1258620.
