AMCRN: Few-Shot Learning for Automatic Modulation Classification

Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, the AMC under few-shot conditions is considered in this letter, where a novel network architecture is proposed, namely aut...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters 2022-03, Vol.26 (3), p.542-546
Main Authors: Zhou, Quan, Zhang, Ronghui, Mu, Junsheng, Zhang, Hongming, Zhang, Fangpei, Jing, Xiaojun
Format: Article
Language:English
Subjects:
automatic modulation classification
Classification
Computer architecture
Convolution
Convolutional neural networks
Deep learning
Feature extraction
Few shot learning
Kernel
Machine learning
Modulation
relation network
Signal to noise ratio
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3
cites cdi_FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3
container_end_page 546
container_issue 3
container_start_page 542
container_title IEEE communications letters
container_volume 26
creator Zhou, Quan
Zhang, Ronghui
Mu, Junsheng
Zhang, Hongming
Zhang, Fangpei
Jing, Xiaojun
description Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, the AMC under few-shot conditions is considered in this letter, where a novel network architecture is proposed, namely automatic modulation classification relation network (AMCRN), and verified with the baseline methods. Experimental results state that the accuracy of proposed AMCRN exceeds 90% and 10% to 50% improvements are obtained compared with classical schemes when the signal-to-noise ratio (SNR) is greater than −2 dB.
doi_str_mv 10.1109/LCOMM.2021.3135688
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2637441445</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9650842</ieee_id><sourcerecordid>2637441445</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3</originalsourceid><addsrcrecordid>eNo9kFtLxDAQhYMouK7-AX0p-Nw19yY-WcquCq0LXp5Dtk20S7dZkxbx35u94MvMHOacGfgAuEZwhhCUd2WxrKoZhhjNCCKMC3ECJogxkeJYTuMMhUyzTIpzcBHCGkIoMEMT8JBXxevLfbIwP-nblxuS0mjft_1nYp1P8nFwGz20dVK5Zuzi5Pqk6HQIrW3rvbwEZ1Z3wVwd-xR8LObvxVNaLh-fi7xMayzZkNqac65XusEacZhJQ4iR1sQlllozaWuCG0tXkNAGao0Ey6SkwmQ2SgkNmYLbw92td9-jCYNau9H38aXCnGSUIkpZdOGDq_YuBG-s2vp2o_2vQlDtSKk9KbUjpY6kYujmEGqNMf8ByRkUFJM_3TlkAA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2637441445</pqid></control><display><type>article</type><title>AMCRN: Few-Shot Learning for Automatic Modulation Classification</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Zhou, Quan ; Zhang, Ronghui ; Mu, Junsheng ; Zhang, Hongming ; Zhang, Fangpei ; Jing, Xiaojun</creator><creatorcontrib>Zhou, Quan ; Zhang, Ronghui ; Mu, Junsheng ; Zhang, Hongming ; Zhang, Fangpei ; Jing, Xiaojun</creatorcontrib><description>Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, the AMC under few-shot conditions is considered in this letter, where a novel network architecture is proposed, namely automatic modulation classification relation network (AMCRN), and verified with the baseline methods. Experimental results state that the accuracy of proposed AMCRN exceeds 90% and 10% to 50% improvements are obtained compared with classical schemes when the signal-to-noise ratio (SNR) is greater than −2 dB.</description><identifier>ISSN: 1089-7798</identifier><identifier>EISSN: 1558-2558</identifier><identifier>DOI: 10.1109/LCOMM.2021.3135688</identifier><identifier>CODEN: ICLEF6</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>automatic modulation classification ; Classification ; Computer architecture ; Convolution ; Convolutional neural networks ; Deep learning ; Feature extraction ; Few shot learning ; Kernel ; Machine learning ; Modulation ; relation network ; Signal to noise ratio ; Training</subject><ispartof>IEEE communications letters, 2022-03, Vol.26 (3), p.542-546</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3</citedby><cites>FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3</cites><orcidid>0000-0003-2560-4364 ; 0000-0002-5352-8314 ; 0000-0001-7838-0638 ; 0000-0003-1547-3065</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9650842$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Zhou, Quan</creatorcontrib><creatorcontrib>Zhang, Ronghui</creatorcontrib><creatorcontrib>Mu, Junsheng</creatorcontrib><creatorcontrib>Zhang, Hongming</creatorcontrib><creatorcontrib>Zhang, Fangpei</creatorcontrib><creatorcontrib>Jing, Xiaojun</creatorcontrib><title>AMCRN: Few-Shot Learning for Automatic Modulation Classification</title><title>IEEE communications letters</title><addtitle>LCOMM</addtitle><description>Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, the AMC under few-shot conditions is considered in this letter, where a novel network architecture is proposed, namely automatic modulation classification relation network (AMCRN), and verified with the baseline methods. Experimental results state that the accuracy of proposed AMCRN exceeds 90% and 10% to 50% improvements are obtained compared with classical schemes when the signal-to-noise ratio (SNR) is greater than −2 dB.</description><subject>automatic modulation classification</subject><subject>Classification</subject><subject>Computer architecture</subject><subject>Convolution</subject><subject>Convolutional neural networks</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Few shot learning</subject><subject>Kernel</subject><subject>Machine learning</subject><subject>Modulation</subject><subject>relation network</subject><subject>Signal to noise ratio</subject><subject>Training</subject><issn>1089-7798</issn><issn>1558-2558</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNo9kFtLxDAQhYMouK7-AX0p-Nw19yY-WcquCq0LXp5Dtk20S7dZkxbx35u94MvMHOacGfgAuEZwhhCUd2WxrKoZhhjNCCKMC3ECJogxkeJYTuMMhUyzTIpzcBHCGkIoMEMT8JBXxevLfbIwP-nblxuS0mjft_1nYp1P8nFwGz20dVK5Zuzi5Pqk6HQIrW3rvbwEZ1Z3wVwd-xR8LObvxVNaLh-fi7xMayzZkNqac65XusEacZhJQ4iR1sQlllozaWuCG0tXkNAGao0Ey6SkwmQ2SgkNmYLbw92td9-jCYNau9H38aXCnGSUIkpZdOGDq_YuBG-s2vp2o_2vQlDtSKk9KbUjpY6kYujmEGqNMf8ByRkUFJM_3TlkAA</recordid><startdate>20220301</startdate><enddate>20220301</enddate><creator>Zhou, Quan</creator><creator>Zhang, Ronghui</creator><creator>Mu, Junsheng</creator><creator>Zhang, Hongming</creator><creator>Zhang, Fangpei</creator><creator>Jing, Xiaojun</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-2560-4364</orcidid><orcidid>https://orcid.org/0000-0002-5352-8314</orcidid><orcidid>https://orcid.org/0000-0001-7838-0638</orcidid><orcidid>https://orcid.org/0000-0003-1547-3065</orcidid></search><sort><creationdate>20220301</creationdate><title>AMCRN: Few-Shot Learning for Automatic Modulation Classification</title><author>Zhou, Quan ; Zhang, Ronghui ; Mu, Junsheng ; Zhang, Hongming ; Zhang, Fangpei ; Jing, Xiaojun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>automatic modulation classification</topic><topic>Classification</topic><topic>Computer architecture</topic><topic>Convolution</topic><topic>Convolutional neural networks</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Few shot learning</topic><topic>Kernel</topic><topic>Machine learning</topic><topic>Modulation</topic><topic>relation network</topic><topic>Signal to noise ratio</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Quan</creatorcontrib><creatorcontrib>Zhang, Ronghui</creatorcontrib><creatorcontrib>Mu, Junsheng</creatorcontrib><creatorcontrib>Zhang, Hongming</creatorcontrib><creatorcontrib>Zhang, Fangpei</creatorcontrib><creatorcontrib>Jing, Xiaojun</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE communications letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Quan</au><au>Zhang, Ronghui</au><au>Mu, Junsheng</au><au>Zhang, Hongming</au><au>Zhang, Fangpei</au><au>Jing, Xiaojun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AMCRN: Few-Shot Learning for Automatic Modulation Classification</atitle><jtitle>IEEE communications letters</jtitle><stitle>LCOMM</stitle><date>2022-03-01</date><risdate>2022</risdate><volume>26</volume><issue>3</issue><spage>542</spage><epage>546</epage><pages>542-546</pages><issn>1089-7798</issn><eissn>1558-2558</eissn><coden>ICLEF6</coden><abstract>Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, the AMC under few-shot conditions is considered in this letter, where a novel network architecture is proposed, namely automatic modulation classification relation network (AMCRN), and verified with the baseline methods. Experimental results state that the accuracy of proposed AMCRN exceeds 90% and 10% to 50% improvements are obtained compared with classical schemes when the signal-to-noise ratio (SNR) is greater than −2 dB.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LCOMM.2021.3135688</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0003-2560-4364</orcidid><orcidid>https://orcid.org/0000-0002-5352-8314</orcidid><orcidid>https://orcid.org/0000-0001-7838-0638</orcidid><orcidid>https://orcid.org/0000-0003-1547-3065</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1089-7798
ispartof IEEE communications letters, 2022-03, Vol.26 (3), p.542-546
issn 1089-7798
1558-2558
language eng
recordid cdi_proquest_journals_2637441445
source IEEE Electronic Library (IEL) Journals
subjects automatic modulation classification
Classification
Computer architecture
Convolution
Convolutional neural networks
Deep learning
Feature extraction
Few shot learning
Kernel
Machine learning
Modulation
relation network
Signal to noise ratio
Training
title AMCRN: Few-Shot Learning for Automatic Modulation Classification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T23%3A18%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AMCRN:%20Few-Shot%20Learning%20for%20Automatic%20Modulation%20Classification&rft.jtitle=IEEE%20communications%20letters&rft.au=Zhou,%20Quan&rft.date=2022-03-01&rft.volume=26&rft.issue=3&rft.spage=542&rft.epage=546&rft.pages=542-546&rft.issn=1089-7798&rft.eissn=1558-2558&rft.coden=ICLEF6&rft_id=info:doi/10.1109/LCOMM.2021.3135688&rft_dat=%3Cproquest_ieee_%3E2637441445%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c295t-fc666abad2a16079e33e9fec2929aa59fc32df4b034d0aa18579948e7fd0a90e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2637441445&rft_id=info:pmid/&rft_ieee_id=9650842&rfr_iscdi=true