Show simple item record

dc.contributor.authorVarshney, Rajat
dc.contributor.authorGangal, Chirag
dc.contributor.authorSharique, Mohd
dc.contributor.authorAnsari, Mohammad Samar
dc.date.accessioned2022-09-23T09:44:43Z
dc.date.available2022-09-23T09:44:43Z
dc.date.issued2023-01-31
dc.identifierhttps://chesterrep.openrepository.com/bitstream/handle/10034/627189/Sharique____DL_for_Wireless_28_GHz.pdf?sequence=1
dc.identifier.citationVarshney, R., Gangal, C., Sharique, M., Ansari, M. S. (2023). Deep learning based wireless channel prediction: 5G scenario. Procedia Computer Science, 218, 2626-2635. https://doi.org/10.1016/j.procs.2023.01.236en_US
dc.identifier.issn1877-0509
dc.identifier.doi10.1016/j.procs.2023.01.236
dc.identifier.urihttp://hdl.handle.net/10034/627189
dc.description.abstractIn the area of wireless communication, channel estimation is a challenging problem due to the need for real-time implementation as well as system dependence on the estimation accuracy. This work presents a Long-Short Term Memory (LSTM) based deep learning (DL) approach for the prediction of channel response in real-time and real-world non-stationary channels. The model uses the pre-defined history of channel impulse response (CIR) data along with two other features viz. transmitter-receiver update distance and root-mean-square delay spread values which are also changing in time with the channel impulse response. The objective is to obtain an approximate estimate of CIRs using prediction through the DL model as compared to conventional methods. For training the model, a sample dataset is generated through the open-source channel simulation software NYUSIM which realizes samples of CIRs for measurement-based channel models based on various multipath channel parameters. From the model test results, it is found that the proposed DL approach provides a viable lightweight solution for channel prediction in wireless communication.en_US
dc.publisherElsevieren_US
dc.relation.urlhttps://www.sciencedirect.com/journal/procedia-computer-scienceen_US
dc.relation.urlhttps://www.sciencedirect.com/science/article/pii/S1877050923002363?via%3Dihub
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.subjectWireless communicationen_US
dc.subjectDeep learningen_US
dc.titleDeep Learning based Wireless Channel Prediction: 5G Scenarioen_US
dc.typeArticleen_US
dc.contributor.departmentAligarh Muslim University; University of Chesteren_US
dc.identifier.journalProcedia Computer Scienceen_US
dc.identifier.volume218
or.grant.openaccessYesen_US
rioxxterms.funderUnfundeden_US
rioxxterms.identifier.projectUnfundeden_US
rioxxterms.versionAMen_US
dc.source.beginpage2626-2635
dcterms.dateAccepted2022-08-01
rioxxterms.publicationdate2023-01-31
dc.date.deposited2022-09-23en_US


Files in this item

Thumbnail
Name:
Publisher version
Thumbnail
Name:
Sharique____DL_for_Wireless_28 ...
Size:
4.707Mb
Format:
PDF
Request:
Article

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nc-nd/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-nd/4.0/