Classification Weighted Deep Neural Network Based Channel Equalization for Massive MIMO-OFDM Systems

Simple item page
dc.contributor.authorGe, L.
dc.contributor.authorQi, C.
dc.contributor.authorGuo, Y.
dc.contributor.authorQian, L.
dc.contributor.authorTong, J.
dc.contributor.authorWei, P.
dc.coverage.issue3cs
dc.coverage.volume31cs
dc.date.accessioned2022-08-03T13:09:35Z
dc.date.available2022-08-03T13:09:35Z
dc.date.issued2022-09cs
dc.description.abstractMassive multi-input multi-output (MIMO) has attracted significant interest in academia and industry, which can efficiently increase the transmission rate. However, the error rate of conventional channel equalizations in massive MIMO systems may be high owing to the dynamic channel states in practical conditions. To solve this problem, in this paper, we propose an improved channel equalization framework based on the deep neural network (DNN). Based on the analyzed relationship between the input and output of the DNN, the data can be recovered without the channel state information. Furthermore, aiming at reducing the convergence time and enhancing the learning ability of the DNN, a classification weighted algorithm is proposed to optimize the cost function of the DNN, which is named as classification weighted deep neural network (CW-DNN). Simulation results demonstrate that compared to conventional counterparts, the proposed CW-DNN based equalizer can achieve a better normalized mean square error (NMSE). Upon approximating the optimal neural network parameters with the significantly improved convergence speed and reduced training time of the network, under the condition of the fixed learning rate.en
dc.formattextcs
dc.format.extent346-356cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 2022 vol. 31, č. 3, s. 346-356. ISSN 1210-2512cs
dc.identifier.doi10.13164/re.2022.0346en
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/208216
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttps://www.radioeng.cz/fulltexts/2022/22_03_0346_0356.pdfcs
dc.rightsCreative Commons Attribution 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectChannel equalizationen
dc.subjectclassification weighteden
dc.subjectdeep neural networken
dc.subjectmassive MIMOen
dc.subjectoptimization algorithmen
dc.titleClassification Weighted Deep Neural Network Based Channel Equalization for Massive MIMO-OFDM Systemsen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
22_03_0346_0356.pdf
Size:
519.75 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2022/3