Loading…
Deep-Learning-Based Signal Detection for Banded Linear Systems
Motivated by the recent advances in deep learning, we propose to design high-accuracy low-complexity signal detectors for banded linear systems based on deep neural networks (DNNs). We first design a fully connected DNN for signal detection. Then, to deal with the curse of dimensionality, we propose...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 6 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Congmin Fan Xiaojun Yuan Zhang, Ying-Jun Angela |
| description | Motivated by the recent advances in deep learning, we propose to design high-accuracy low-complexity signal detectors for banded linear systems based on deep neural networks (DNNs). We first design a fully connected DNN for signal detection. Then, to deal with the curse of dimensionality, we propose a novel convolutional neural network (CNN) based on the banded structure of the channel matrix. From simulations, we observe that the proposed CNN outperforms the fully connected DNN in both accuracy and computational time. Moreover, CNN is more robust for the extension to channel matrices with a large size or a wide band. We also run extensive numerical experiments to show that both fully connected DNN and CNN perform much better than existing detectors with comparable complexity. |
| doi_str_mv | 10.1109/GLOCOM.2018.8648123 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8648123</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8648123</ieee_id><sourcerecordid>8648123</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-84c1b5dee4e31a0633e6b33f18fb520f63eee28606c5c62fb9b62e3f47b580023</originalsourceid><addsrcrecordid>eNotj0FrAjEUhNNCodb6C7zsH8g2L2-TjZdC1WoLW_Zge5Zk90VSNMpmL_77BuppGOZjmGFsDqIEEIuXbdOu2q9SCjCl0ZUBiXfsCRRmU8sa79lEqlpzbQAf2SylXyGE1AZzOmGva6ILb8gOMcQDX9pEfbELh2iPxZpG6sZwjoU_D8XSxj5nTYgZLnbXNNIpPbMHb4-JZjedsp_N-_fqgzft9nP11vAAtRq5qTpwqieqCMEKjUjaIXow3ikpvEYikkYL3alOS-8WTktCX9VOmbwWp2z-3xsyuL8M4WSH6_52F_8ATUpIhA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Deep-Learning-Based Signal Detection for Banded Linear Systems</title><source>IEEE Xplore All Conference Series</source><creator>Congmin Fan ; Xiaojun Yuan ; Zhang, Ying-Jun Angela</creator><creatorcontrib>Congmin Fan ; Xiaojun Yuan ; Zhang, Ying-Jun Angela</creatorcontrib><description>Motivated by the recent advances in deep learning, we propose to design high-accuracy low-complexity signal detectors for banded linear systems based on deep neural networks (DNNs). We first design a fully connected DNN for signal detection. Then, to deal with the curse of dimensionality, we propose a novel convolutional neural network (CNN) based on the banded structure of the channel matrix. From simulations, we observe that the proposed CNN outperforms the fully connected DNN in both accuracy and computational time. Moreover, CNN is more robust for the extension to channel matrices with a large size or a wide band. We also run extensive numerical experiments to show that both fully connected DNN and CNN perform much better than existing detectors with comparable complexity.</description><identifier>EISSN: 2576-6813</identifier><identifier>EISBN: 1538647273</identifier><identifier>EISBN: 9781538647271</identifier><identifier>DOI: 10.1109/GLOCOM.2018.8648123</identifier><language>eng</language><publisher>IEEE</publisher><subject>Convolution ; Deep learning ; Detectors ; Feature extraction ; Neural networks ; Neurons ; Signal detection</subject><ispartof>2018 IEEE Global Communications Conference (GLOBECOM), 2018, p.1-6</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8648123$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23929,23930,25139,27924,54554,54931</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8648123$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Congmin Fan</creatorcontrib><creatorcontrib>Xiaojun Yuan</creatorcontrib><creatorcontrib>Zhang, Ying-Jun Angela</creatorcontrib><title>Deep-Learning-Based Signal Detection for Banded Linear Systems</title><title>2018 IEEE Global Communications Conference (GLOBECOM)</title><addtitle>GLOCOM</addtitle><description>Motivated by the recent advances in deep learning, we propose to design high-accuracy low-complexity signal detectors for banded linear systems based on deep neural networks (DNNs). We first design a fully connected DNN for signal detection. Then, to deal with the curse of dimensionality, we propose a novel convolutional neural network (CNN) based on the banded structure of the channel matrix. From simulations, we observe that the proposed CNN outperforms the fully connected DNN in both accuracy and computational time. Moreover, CNN is more robust for the extension to channel matrices with a large size or a wide band. We also run extensive numerical experiments to show that both fully connected DNN and CNN perform much better than existing detectors with comparable complexity.</description><subject>Convolution</subject><subject>Deep learning</subject><subject>Detectors</subject><subject>Feature extraction</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Signal detection</subject><issn>2576-6813</issn><isbn>1538647273</isbn><isbn>9781538647271</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2018</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj0FrAjEUhNNCodb6C7zsH8g2L2-TjZdC1WoLW_Zge5Zk90VSNMpmL_77BuppGOZjmGFsDqIEEIuXbdOu2q9SCjCl0ZUBiXfsCRRmU8sa79lEqlpzbQAf2SylXyGE1AZzOmGva6ILb8gOMcQDX9pEfbELh2iPxZpG6sZwjoU_D8XSxj5nTYgZLnbXNNIpPbMHb4-JZjedsp_N-_fqgzft9nP11vAAtRq5qTpwqieqCMEKjUjaIXow3ikpvEYikkYL3alOS-8WTktCX9VOmbwWp2z-3xsyuL8M4WSH6_52F_8ATUpIhA</recordid><startdate>201812</startdate><enddate>201812</enddate><creator>Congmin Fan</creator><creator>Xiaojun Yuan</creator><creator>Zhang, Ying-Jun Angela</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201812</creationdate><title>Deep-Learning-Based Signal Detection for Banded Linear Systems</title><author>Congmin Fan ; Xiaojun Yuan ; Zhang, Ying-Jun Angela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-84c1b5dee4e31a0633e6b33f18fb520f63eee28606c5c62fb9b62e3f47b580023</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Convolution</topic><topic>Deep learning</topic><topic>Detectors</topic><topic>Feature extraction</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Signal detection</topic><toplevel>online_resources</toplevel><creatorcontrib>Congmin Fan</creatorcontrib><creatorcontrib>Xiaojun Yuan</creatorcontrib><creatorcontrib>Zhang, Ying-Jun Angela</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Congmin Fan</au><au>Xiaojun Yuan</au><au>Zhang, Ying-Jun Angela</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Deep-Learning-Based Signal Detection for Banded Linear Systems</atitle><btitle>2018 IEEE Global Communications Conference (GLOBECOM)</btitle><stitle>GLOCOM</stitle><date>2018-12</date><risdate>2018</risdate><spage>1</spage><epage>6</epage><pages>1-6</pages><eissn>2576-6813</eissn><eisbn>1538647273</eisbn><eisbn>9781538647271</eisbn><abstract>Motivated by the recent advances in deep learning, we propose to design high-accuracy low-complexity signal detectors for banded linear systems based on deep neural networks (DNNs). We first design a fully connected DNN for signal detection. Then, to deal with the curse of dimensionality, we propose a novel convolutional neural network (CNN) based on the banded structure of the channel matrix. From simulations, we observe that the proposed CNN outperforms the fully connected DNN in both accuracy and computational time. Moreover, CNN is more robust for the extension to channel matrices with a large size or a wide band. We also run extensive numerical experiments to show that both fully connected DNN and CNN perform much better than existing detectors with comparable complexity.</abstract><pub>IEEE</pub><doi>10.1109/GLOCOM.2018.8648123</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2576-6813 |
| ispartof | 2018 IEEE Global Communications Conference (GLOBECOM), 2018, p.1-6 |
| issn | 2576-6813 |
| language | eng |
| recordid | cdi_ieee_primary_8648123 |
| source | IEEE Xplore All Conference Series |
| subjects | Convolution Deep learning Detectors Feature extraction Neural networks Neurons Signal detection |
| title | Deep-Learning-Based Signal Detection for Banded Linear Systems |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T01%3A38%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Deep-Learning-Based%20Signal%20Detection%20for%20Banded%20Linear%20Systems&rft.btitle=2018%20IEEE%20Global%20Communications%20Conference%20(GLOBECOM)&rft.au=Congmin%20Fan&rft.date=2018-12&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.eissn=2576-6813&rft_id=info:doi/10.1109/GLOCOM.2018.8648123&rft.eisbn=1538647273&rft.eisbn_list=9781538647271&rft_dat=%3Cieee_CHZPO%3E8648123%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-84c1b5dee4e31a0633e6b33f18fb520f63eee28606c5c62fb9b62e3f47b580023%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8648123&rfr_iscdi=true |