Electrical & Computer Engineering Faculty Publications
Document Type
Article
Publication Date
11-9-2003
Abstract
This paper presents binary and multiclass machine learning techniques for CDMA power control. The power control commands are based on estimates of the signal and noise subspace eigenvalues and the signal subspace dimension. Results of two different sets of machine learning algorithms are presented. Binary machine learning algorithms generate fixed-step power control (FSPC) commands based on estimated eigenvalues and SIRs. A fixed-set of power control commands are generated with multiclass machine learning algorithms. The results show the limitations of a fixed-set power control system, but also show that a fixed-set system achieves comparable performance to high complexity closed-loop power control systems.
Publisher
IEEE
Publication Title
Conference Record of the Thirty-Seventh Asilomar Conference on Signals
ISSN
0-7803-8104-1
First Page
207
Last Page
211
DOI
10.1109/ACSSC.2003.1291898
Language (ISO)
English
Sponsorship
IEEE
Keywords
Chaos, Eigenvalues and eigenfunctions, Machine learning
Recommended Citation
Abdallah, Chaouki T.; Judd A. Rohwer; and Christos G. Christodoulou. "Machine learning based CDMA power control." Conference Record of the Thirty-Seventh Asilomar Conference on Signals (2003): 207-211. doi:10.1109/ACSSC.2003.1291898.
