Hybrid neural coded modulation: Design and training methods
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Sung Hoon | - |
dc.contributor.author | Han, Jiyong | - |
dc.contributor.author | Noh, Wonjong | - |
dc.contributor.author | Song, Yujae | - |
dc.contributor.author | Jeon, Sang-Woon | - |
dc.date.accessioned | 2022-12-20T05:54:03Z | - |
dc.date.available | 2022-12-20T05:54:03Z | - |
dc.date.issued | 2022-03 | - |
dc.identifier.issn | 2405-9595 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/111379 | - |
dc.description.abstract | We propose a hybrid coded modulation scheme which composes of inner and outer codes. The outer-code can be any standard binary linear code with efficient soft decoding capability (e.g. low-density parity-check (LDPC) codes). The inner code is designed using a deep neural network (DNN) which takes the channel coded bits and outputs modulated symbols. For training the DNN, we propose to use a loss function that is inspired by the generalized mutual information. The resulting constellations are shown to outperform the conventional quadrature amplitude modulation (QAM) based coding scheme for modulation order 16 and 64 with 5G standard LDPC codes. (C) 2022 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. | - |
dc.format.extent | 6 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | 한국통신학회 | - |
dc.title | Hybrid neural coded modulation: Design and training methods | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.doi | 10.1016/j.icte.2022.01.018 | - |
dc.identifier.scopusid | 2-s2.0-85125126373 | - |
dc.identifier.wosid | 000821050300005 | - |
dc.identifier.bibliographicCitation | ICT Express, v.8, no.1, pp 25 - 30 | - |
dc.citation.title | ICT Express | - |
dc.citation.volume | 8 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 25 | - |
dc.citation.endPage | 30 | - |
dc.type.docType | Article | - |
dc.identifier.kciid | ART002828971 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Modulation | - |
dc.subject.keywordAuthor | Channel coding | - |
dc.subject.keywordAuthor | Generalized mutual information | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S2405959522000182?via%3Dihub | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.