Accurate Forecasting of Underground Fading Channel Based on Improved LS-SVM

DOI

10.2991/wartia-16.2016.296How to use a DOI?

Keywords

Channel Forecasting, LS-SVM, Fading Channel, Abnormal Data

Abstract

Aiming at the shortcomings of traditional fading channel forecasting algorithms, least square support vector machine(LS-SVM) is applied to predicting underground fading channel. In light of complicated and changeable underground environment, the measured data may be abnormal. Thus, an improved LS-SVM with abnormal data detection is proposed in this paper to forecast underground fading channels. This algorithm utilizes amplitude of the fading channel as observed values to establish studying model and then implements nonlinear prediction with the help of learning and judgment ability of LS-SVM. The experiment shows that the prediction algorithm based on improved LS-SVM raises the prediction accuracy of fading channels and is an effective and feasible nonlinear fading channel forecasting method.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Anyi Wang
AU  - Xi Xi
PY  - 2016/05
DA  - 2016/05
TI  - Accurate Forecasting of Underground Fading Channel Based on Improved LS-SVM
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1447
EP  - 1452
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.296
DO  - 10.2991/wartia-16.2016.296
ID  - Wang2016/05
ER  -