Title :
Least squares support vector machines for fixed-step and fixed-set CDMA power control
Author :
Rohwer, Judd A. ; Abdallah, Chaouki T. ; Christodoulou, Christos G.
Author_Institution :
Sandia Nat. Labs., Albuquerque, NM, USA
Abstract :
This paper presents two machine learning based algorithms for CDMA power control. The least squares support vector machine (LS-SVM) algorithms classify eigenvalues estimates into sets of power control commands. A binary LS-SVM algorithm generates fixed step power control (FSPC) commands, while the one vs. one multiclass LS-SVM algorithm generates estimates for fixed set power control.
Keywords :
3G mobile communication; cellular radio; code division multiple access; eigenvalues and eigenfunctions; learning (artificial intelligence); least squares approximations; power control; probability; support vector machines; cellular radio; eigenvalues; fixed set CDMA power control; fixed step CDMA power control; fixed step power control commands; least squares SVM algorithms; least squares support vector machine algorithms; machine learning based algorithms; probability; Eigenvalues and eigenfunctions; Least squares approximation; Least squares methods; Machine learning; Machine learning algorithms; Multiaccess communication; Power control; Power generation; Support vector machine classification; Support vector machines;
Conference_Titel :
Decision and Control, 2003. Proceedings. 42nd IEEE Conference on
Print_ISBN :
0-7803-7924-1
DOI :
10.1109/CDC.2003.1272444
