Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics

The Novel Channel Estimation Algorithm Relying on ELM

Authors
Qingfeng DING
Corresponding Author
Qingfeng DING
Available Online April 2015.
DOI
10.2991/ameii-15.2015.173How to use a DOI?
Keywords
Channel Estimation; Extreme Learning Machine; Low-pass Filter; OFDM
Abstract

An Extreme Learning Machine (ELM)-based novel channel estimation algorithm is proposed for orthogonal frequency division multiplexing (OFDM) communication system with multi-path propagation characteristics. In addition, a low-pass filter is utilized to filter the noise components which are separated from the information component of the channel characteristics. The simulation results show that the proposed novel algorithm significantly outdo the traditional least squares (LS) algorithm, linear minimum mean square error (LMMSE) estimation algorithm sometime even better than the Maximum Likelihood (ML) algorithm.

Copyright
© 2015, 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)

Volume Title
Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
Series
Advances in Engineering Research
Publication Date
April 2015
ISBN
10.2991/ameii-15.2015.173
ISSN
2352-5401
DOI
10.2991/ameii-15.2015.173How to use a DOI?
Copyright
© 2015, 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/).

Cite this article

TY  - CONF
AU  - Qingfeng DING
PY  - 2015/04
DA  - 2015/04
TI  - The Novel Channel Estimation Algorithm Relying on ELM
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 933
EP  - 938
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.173
DO  - 10.2991/ameii-15.2015.173
ID  - DING2015/04
ER  -