SVM based on LMMSE for high-speed coded OFDM channel with normal and extended cyclic prefix
We propose in this article, a Linear Minimum Mean Squares Error-Support Vector Machine regression (LMMSE-SVR) method which is employed high-speed 3GPP Long Term Evolution (LTE) downlink coded channel estimation environment. LMMSE-SVR approach is applied to track and estimate the fast fluctuations ca...
Saved in:
Published in | Physical communication Vol. 29; pp. 288 - 295 |
---|---|
Main Author | |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.08.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We propose in this article, a Linear Minimum Mean Squares Error-Support Vector Machine regression (LMMSE-SVR) method which is employed high-speed 3GPP Long Term Evolution (LTE) downlink coded channel estimation environment. LMMSE-SVR approach is applied to track and estimate the fast fluctuations caused by Doppler effect of a 3GPP realistic Extended Vehicular A model (EVA) channel. We integrate in this contribution both channel estimation at pilot symbols and interpolation at data symbols into the LMMSE-SVR process with and without turbo coding scheme. Bit Error Rate (BER) performance of our channel environment estimation proposal is validated via simulation of LTE downlink system for both coded and uncoded high-speed scenarios with normal and extended Cyclic Prefix (CP) modes. |
---|---|
ISSN: | 1874-4907 1876-3219 |
DOI: | 10.1016/j.phycom.2018.07.008 |