Recurrent Neural Network Based Narrowband Channel Prediction
Recurrent Neural Network Based Narrowband Channel Prediction
In this contribution, the application of fully connected recurrent neural networks (FCRNNs) is investigated in the context of narrowband channel prediction. Three different algorithms, namely the real time recurrent learning (RTRL), the global extended Kalman filter (GEKF) and the decoupled extended Kalman filter (DEKF) are used for training the recurrent neural network (RNN) based channel predictor. Our simulation results show that the GEKF and DEKF training schemes have the potential of converging faster than the RTRL training scheme as well as attaining a better MSE performance.
2173-2177
Liu, W.
af656440-51e8-45c8-b694-a802e71b671e
Yang, L-L.
ae425648-d9a3-4b7d-8abd-b3cfea375bc7
Hanzo, L.
66e7266f-3066-4fc0-8391-e000acce71a1
2006
Liu, W.
af656440-51e8-45c8-b694-a802e71b671e
Yang, L-L.
ae425648-d9a3-4b7d-8abd-b3cfea375bc7
Hanzo, L.
66e7266f-3066-4fc0-8391-e000acce71a1
Liu, W., Yang, L-L. and Hanzo, L.
(2006)
Recurrent Neural Network Based Narrowband Channel Prediction.
IEEE VTC'06 (Spring), Melbourne, Australia.
07 - 10 May 2006.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this contribution, the application of fully connected recurrent neural networks (FCRNNs) is investigated in the context of narrowband channel prediction. Three different algorithms, namely the real time recurrent learning (RTRL), the global extended Kalman filter (GEKF) and the decoupled extended Kalman filter (DEKF) are used for training the recurrent neural network (RNN) based channel predictor. Our simulation results show that the GEKF and DEKF training schemes have the potential of converging faster than the RTRL training scheme as well as attaining a better MSE performance.
Other
4-07P04.PDF
- Other
More information
Published date: 2006
Additional Information:
Event Dates: 7-10 May 2006
Venue - Dates:
IEEE VTC'06 (Spring), Melbourne, Australia, 2006-05-07 - 2006-05-10
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 262635
URI: http://eprints.soton.ac.uk/id/eprint/262635
PURE UUID: 46e733c8-de48-4aae-bd0b-551f16d0e62f
Catalogue record
Date deposited: 25 May 2006
Last modified: 18 Mar 2024 02:49
Export record
Contributors
Author:
W. Liu
Author:
L-L. Yang
Author:
L. Hanzo
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics