Channel Estimation in Long Term Evolution Uplink Using Minimum Mean Square Error-Support Vector Regression

In this paper, minimum mean square error-support vector regression (MMSE-SVR) is proposed, which is shown to be adequate for the estimation of the long term evolution (LTE) uplink channel with nonlinear features. MMSE-SVR was applied to estimate real channel environments such as the vehicular A channels defined by the International Telecommunication Union (ITU). The simulation results show that the proposed method has a better performance than the least squares support vector machine (LS-SVM) and the standard MMSE with linear and spline interpolation.