Title :
Combination of supervised and unsupervised algorithms for communication systems with linear precoding
Author :
Dapena, Adriana ; Castro, Paula M. ; Labrador, Josmary
Author_Institution :
Dept. of Electron. & Syst., Univ. of A Coruna, Coruna, Spain
Abstract :
It is well-known that precoding is an attractive way to remove interferences because it reduces cost and power consumption in the receive equipment. When implementing precoding, however, the base station should know the Channel State Information (CSI) which is normally acquired at the receiver side by using pilot symbols. In Frequency Division Duplex (FDD) systems, this information is sent by means of a feedback channel. In order to reduce the overhead inherent to the periodical transmission of training data, we propose to obtain the CSI by means of combining supervised and unsupervised algorithms. The simulation results show that the performance achieved with the proposed scheme is clearly better than that with standard algorithms.
Keywords :
learning (artificial intelligence); mobile radio; precoding; unsupervised learning; wireless channels; CSI; channel state information; feedback channel; frequency division duplex; linear precoding; supervised algorithm; unsupervised algorithms;
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6916-1
DOI :
10.1109/IJCNN.2010.5596907