The least squares SVM approach for a non-linear channel prediction in the MIMO system

Abstract

In this paper we investigate the problem of a Multiple-Input Multiple-Output (MIMO) frequency in a non-selective channel prediction. We develop a new method for the channel prediction which is based on the Least Squares Support Vector Machine (SVM). We develop a new method for the channel which allows us to predict a signal. The proposed method is evaluated through simulation in a MIMO system under a channel prediction. © 2011 Springer-Verlag.