Fully Dense Neural Network for the Automatic Modulation Recognition

Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-ph...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-12
Hauptverfasser: Du, Miao, Yu, Qin, Shaomin Fei, Wang, Chen, Gong, Xiaofeng, Luo, Ruisen
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Du, Miao
Yu, Qin
Shaomin Fei
Wang, Chen
Gong, Xiaofeng
Luo, Ruisen
description Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2323280973</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2323280973</sourcerecordid><originalsourceid>FETCH-proquest_journals_23232809733</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwdivNyalUcEnNK05V8EstLUrMAVIl5flF2Qpp-UUKJRmpCo6lJfm5iSWZyQq--SmlOUBWfp5CUGpyfnpeJojNw8CalphTnMoLpbkZlN1cQ5w9dAuK8gtLU4tL4rPyS4vygFLxRsZAaGFgaW5sTJwqAO19Oi4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2323280973</pqid></control><display><type>article</type><title>Fully Dense Neural Network for the Automatic Modulation Recognition</title><source>Free E- Journals</source><creator>Du, Miao ; Yu, Qin ; Shaomin Fei ; Wang, Chen ; Gong, Xiaofeng ; Luo, Ruisen</creator><creatorcontrib>Du, Miao ; Yu, Qin ; Shaomin Fei ; Wang, Chen ; Gong, Xiaofeng ; Luo, Ruisen</creatorcontrib><description>Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Automatic modulation recognition ; Convolution ; Feature extraction ; Feature recognition ; Machine learning ; Neural networks ; Quadratures ; Spectrograms</subject><ispartof>arXiv.org, 2019-12</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Du, Miao</creatorcontrib><creatorcontrib>Yu, Qin</creatorcontrib><creatorcontrib>Shaomin Fei</creatorcontrib><creatorcontrib>Wang, Chen</creatorcontrib><creatorcontrib>Gong, Xiaofeng</creatorcontrib><creatorcontrib>Luo, Ruisen</creatorcontrib><title>Fully Dense Neural Network for the Automatic Modulation Recognition</title><title>arXiv.org</title><description>Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.</description><subject>Artificial neural networks</subject><subject>Automatic modulation recognition</subject><subject>Convolution</subject><subject>Feature extraction</subject><subject>Feature recognition</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Quadratures</subject><subject>Spectrograms</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwdivNyalUcEnNK05V8EstLUrMAVIl5flF2Qpp-UUKJRmpCo6lJfm5iSWZyQq--SmlOUBWfp5CUGpyfnpeJojNw8CalphTnMoLpbkZlN1cQ5w9dAuK8gtLU4tL4rPyS4vygFLxRsZAaGFgaW5sTJwqAO19Oi4</recordid><startdate>20191207</startdate><enddate>20191207</enddate><creator>Du, Miao</creator><creator>Yu, Qin</creator><creator>Shaomin Fei</creator><creator>Wang, Chen</creator><creator>Gong, Xiaofeng</creator><creator>Luo, Ruisen</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20191207</creationdate><title>Fully Dense Neural Network for the Automatic Modulation Recognition</title><author>Du, Miao ; Yu, Qin ; Shaomin Fei ; Wang, Chen ; Gong, Xiaofeng ; Luo, Ruisen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23232809733</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Artificial neural networks</topic><topic>Automatic modulation recognition</topic><topic>Convolution</topic><topic>Feature extraction</topic><topic>Feature recognition</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Quadratures</topic><topic>Spectrograms</topic><toplevel>online_resources</toplevel><creatorcontrib>Du, Miao</creatorcontrib><creatorcontrib>Yu, Qin</creatorcontrib><creatorcontrib>Shaomin Fei</creatorcontrib><creatorcontrib>Wang, Chen</creatorcontrib><creatorcontrib>Gong, Xiaofeng</creatorcontrib><creatorcontrib>Luo, Ruisen</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Du, Miao</au><au>Yu, Qin</au><au>Shaomin Fei</au><au>Wang, Chen</au><au>Gong, Xiaofeng</au><au>Luo, Ruisen</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Fully Dense Neural Network for the Automatic Modulation Recognition</atitle><jtitle>arXiv.org</jtitle><date>2019-12-07</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-12
issn 2331-8422
language eng
recordid cdi_proquest_journals_2323280973
source Free E- Journals
subjects Artificial neural networks
Automatic modulation recognition
Convolution
Feature extraction
Feature recognition
Machine learning
Neural networks
Quadratures
Spectrograms
title Fully Dense Neural Network for the Automatic Modulation Recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T06%3A24%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Fully%20Dense%20Neural%20Network%20for%20the%20Automatic%20Modulation%20Recognition&rft.jtitle=arXiv.org&rft.au=Du,%20Miao&rft.date=2019-12-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2323280973%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2323280973&rft_id=info:pmid/&rfr_iscdi=true