MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length

In Automatic Modulation Classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propos...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE communications letters 2024-12, Vol.28 (12), p.2864-2868
Hauptverfasser: Zhang, Yezhuo, Zhou, Zinan, Cao, Yichao, Li, Guangyu, Li, Xuanpeng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2868
container_issue 12
container_start_page 2864
container_title IEEE communications letters
container_volume 28
creator Zhang, Yezhuo
Zhou, Zinan
Cao, Yichao
Li, Guangyu
Li, Xuanpeng
description In Automatic Modulation Classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propose a novel AMC framework, designated as the Mamba-based Automatic Modulation Classification (MAMC), which addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model (Mamba), which enhances the model's capabilities in long-term memory and information selection, and reduces computational complexity and spatial overhead. We further design a denoising unit to filter out effective semantic information to improve accuracy. Rigorous experimental evaluations on the publicly available dataset RML2016.10 and TorchSig affirm that MAMC delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://github.com/ZhangYezhuo/MAMC .
doi_str_mv 10.1109/LCOMM.2024.3474519
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LCOMM_2024_3474519</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10705364</ieee_id><sourcerecordid>3143027393</sourcerecordid><originalsourceid>FETCH-LOGICAL-c923-b5ba8bee9a3c70689b00059fa18a12bd437c35a8206a97746c0c96972d6a3eff3</originalsourceid><addsrcrecordid>eNpNkN1LwzAUxYMoOKf_gPhQ8LkzH02TPJYyP2BlDw58DGmabJldO5MW3H9vZn3w5d5z4ZzD5QfAPYILhKB4WpXrqlpgiLMFyVhGkbgAM0QpT3Ecl1FDLlLGBL8GNyHsIYQcUzQDn1VRlen6OLiDapO-SwqtR6_0KVFdkyytddqZLp6290kxDv1BDU4nVd-MbVQxULYqBBd90_nhhl2y_B5M15gmeXfbLvauTLcddrfgyqo2mLu_PQeb5-WmfE1X65e3slilWmCS1rRWvDZGKKIZzLmo47NUWIW4QrhuMsI0oYpjmCvBWJZrqEUuGG5yRYy1ZA4ep9qj779GEwa570cf3wiSoIxAzIgg0YUnl_Z9CN5YefSRgT9JBOWZqfxlKs9M5R_TGHqYQs4Y8y_AICV5Rn4A7Y9zHQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3143027393</pqid></control><display><type>article</type><title>MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length</title><source>IEEE Electronic Library (IEL)</source><creator>Zhang, Yezhuo ; Zhou, Zinan ; Cao, Yichao ; Li, Guangyu ; Li, Xuanpeng</creator><creatorcontrib>Zhang, Yezhuo ; Zhou, Zinan ; Cao, Yichao ; Li, Guangyu ; Li, Xuanpeng</creatorcontrib><description>In Automatic Modulation Classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propose a novel AMC framework, designated as the Mamba-based Automatic Modulation Classification (MAMC), which addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model (Mamba), which enhances the model's capabilities in long-term memory and information selection, and reduces computational complexity and spatial overhead. We further design a denoising unit to filter out effective semantic information to improve accuracy. Rigorous experimental evaluations on the publicly available dataset RML2016.10 and TorchSig affirm that MAMC delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://github.com/ZhangYezhuo/MAMC .</description><identifier>ISSN: 1089-7798</identifier><identifier>EISSN: 1558-2558</identifier><identifier>DOI: 10.1109/LCOMM.2024.3474519</identifier><identifier>CODEN: ICLEF6</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Accuracy ; Adaptation models ; Automatic modulation classification ; Classification ; cognitive radio ; Computational modeling ; Computing time ; Convolution ; Feature extraction ; long sequence ; mamba ; Mathematical models ; Memory management ; Modulation ; Noise reduction ; state space model ; State space models ; Training</subject><ispartof>IEEE communications letters, 2024-12, Vol.28 (12), p.2864-2868</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c923-b5ba8bee9a3c70689b00059fa18a12bd437c35a8206a97746c0c96972d6a3eff3</cites><orcidid>0000-0001-9320-0658 ; 0000-0003-2997-4012 ; 0009-0008-6670-447X ; 0000-0003-4817-0618</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10705364$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,777,781,793,27905,27906,54739</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10705364$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zhang, Yezhuo</creatorcontrib><creatorcontrib>Zhou, Zinan</creatorcontrib><creatorcontrib>Cao, Yichao</creatorcontrib><creatorcontrib>Li, Guangyu</creatorcontrib><creatorcontrib>Li, Xuanpeng</creatorcontrib><title>MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length</title><title>IEEE communications letters</title><addtitle>LCOMM</addtitle><description>In Automatic Modulation Classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propose a novel AMC framework, designated as the Mamba-based Automatic Modulation Classification (MAMC), which addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model (Mamba), which enhances the model's capabilities in long-term memory and information selection, and reduces computational complexity and spatial overhead. We further design a denoising unit to filter out effective semantic information to improve accuracy. Rigorous experimental evaluations on the publicly available dataset RML2016.10 and TorchSig affirm that MAMC delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://github.com/ZhangYezhuo/MAMC .</description><subject>Accuracy</subject><subject>Adaptation models</subject><subject>Automatic modulation classification</subject><subject>Classification</subject><subject>cognitive radio</subject><subject>Computational modeling</subject><subject>Computing time</subject><subject>Convolution</subject><subject>Feature extraction</subject><subject>long sequence</subject><subject>mamba</subject><subject>Mathematical models</subject><subject>Memory management</subject><subject>Modulation</subject><subject>Noise reduction</subject><subject>state space model</subject><subject>State space models</subject><subject>Training</subject><issn>1089-7798</issn><issn>1558-2558</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkN1LwzAUxYMoOKf_gPhQ8LkzH02TPJYyP2BlDw58DGmabJldO5MW3H9vZn3w5d5z4ZzD5QfAPYILhKB4WpXrqlpgiLMFyVhGkbgAM0QpT3Ecl1FDLlLGBL8GNyHsIYQcUzQDn1VRlen6OLiDapO-SwqtR6_0KVFdkyytddqZLp6290kxDv1BDU4nVd-MbVQxULYqBBd90_nhhl2y_B5M15gmeXfbLvauTLcddrfgyqo2mLu_PQeb5-WmfE1X65e3slilWmCS1rRWvDZGKKIZzLmo47NUWIW4QrhuMsI0oYpjmCvBWJZrqEUuGG5yRYy1ZA4ep9qj779GEwa570cf3wiSoIxAzIgg0YUnl_Z9CN5YefSRgT9JBOWZqfxlKs9M5R_TGHqYQs4Y8y_AICV5Rn4A7Y9zHQ</recordid><startdate>202412</startdate><enddate>202412</enddate><creator>Zhang, Yezhuo</creator><creator>Zhou, Zinan</creator><creator>Cao, Yichao</creator><creator>Li, Guangyu</creator><creator>Li, Xuanpeng</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/0000-0001-9320-0658</orcidid><orcidid>https://orcid.org/0000-0003-2997-4012</orcidid><orcidid>https://orcid.org/0009-0008-6670-447X</orcidid><orcidid>https://orcid.org/0000-0003-4817-0618</orcidid></search><sort><creationdate>202412</creationdate><title>MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length</title><author>Zhang, Yezhuo ; Zhou, Zinan ; Cao, Yichao ; Li, Guangyu ; Li, Xuanpeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c923-b5ba8bee9a3c70689b00059fa18a12bd437c35a8206a97746c0c96972d6a3eff3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Adaptation models</topic><topic>Automatic modulation classification</topic><topic>Classification</topic><topic>cognitive radio</topic><topic>Computational modeling</topic><topic>Computing time</topic><topic>Convolution</topic><topic>Feature extraction</topic><topic>long sequence</topic><topic>mamba</topic><topic>Mathematical models</topic><topic>Memory management</topic><topic>Modulation</topic><topic>Noise reduction</topic><topic>state space model</topic><topic>State space models</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Yezhuo</creatorcontrib><creatorcontrib>Zhou, Zinan</creatorcontrib><creatorcontrib>Cao, Yichao</creatorcontrib><creatorcontrib>Li, Guangyu</creatorcontrib><creatorcontrib>Li, Xuanpeng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE 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_linktorsrc</fulltext></delivery><addata><au>Zhang, Yezhuo</au><au>Zhou, Zinan</au><au>Cao, Yichao</au><au>Li, Guangyu</au><au>Li, Xuanpeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length</atitle><jtitle>IEEE communications letters</jtitle><stitle>LCOMM</stitle><date>2024-12</date><risdate>2024</risdate><volume>28</volume><issue>12</issue><spage>2864</spage><epage>2868</epage><pages>2864-2868</pages><issn>1089-7798</issn><eissn>1558-2558</eissn><coden>ICLEF6</coden><abstract>In Automatic Modulation Classification (AMC), extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase memory usage. To bridge the gap between these requirements, we propose a novel AMC framework, designated as the Mamba-based Automatic Modulation Classification (MAMC), which addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model (Mamba), which enhances the model's capabilities in long-term memory and information selection, and reduces computational complexity and spatial overhead. We further design a denoising unit to filter out effective semantic information to improve accuracy. Rigorous experimental evaluations on the publicly available dataset RML2016.10 and TorchSig affirm that MAMC delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://github.com/ZhangYezhuo/MAMC .</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LCOMM.2024.3474519</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0001-9320-0658</orcidid><orcidid>https://orcid.org/0000-0003-2997-4012</orcidid><orcidid>https://orcid.org/0009-0008-6670-447X</orcidid><orcidid>https://orcid.org/0000-0003-4817-0618</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1089-7798
ispartof IEEE communications letters, 2024-12, Vol.28 (12), p.2864-2868
issn 1089-7798
1558-2558
language eng
recordid cdi_crossref_primary_10_1109_LCOMM_2024_3474519
source IEEE Electronic Library (IEL)
subjects Accuracy
Adaptation models
Automatic modulation classification
Classification
cognitive radio
Computational modeling
Computing time
Convolution
Feature extraction
long sequence
mamba
Mathematical models
Memory management
Modulation
Noise reduction
state space model
State space models
Training
title MAMC-Optimal on Accuracy and Efficiency for Automatic Modulation Classification With Extended Signal Length
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T06%3A34%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MAMC-Optimal%20on%20Accuracy%20and%20Efficiency%20for%20Automatic%20Modulation%20Classification%20With%20Extended%20Signal%20Length&rft.jtitle=IEEE%20communications%20letters&rft.au=Zhang,%20Yezhuo&rft.date=2024-12&rft.volume=28&rft.issue=12&rft.spage=2864&rft.epage=2868&rft.pages=2864-2868&rft.issn=1089-7798&rft.eissn=1558-2558&rft.coden=ICLEF6&rft_id=info:doi/10.1109/LCOMM.2024.3474519&rft_dat=%3Cproquest_RIE%3E3143027393%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3143027393&rft_id=info:pmid/&rft_ieee_id=10705364&rfr_iscdi=true