Detection of Frequency-Hopping Signals With Deep Learning
Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolution...
Gespeichert in:
| Veröffentlicht in: | IEEE communications letters 2020-05, Vol.24 (5), p.1042-1046 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1046 |
|---|---|
| container_issue | 5 |
| container_start_page | 1042 |
| container_title | IEEE communications letters |
| container_volume | 24 |
| creator | Lee, Kyung-Gyu Oh, Seong-Jun |
| description | Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolutional neural network (CNN) and hybrid CNN/recurrent neural network (RNN)-based schemes. The CNN-based scheme alleviates spectral leakage by using feature maps. The hybrid CNN/RNN-based scheme mitigates the time-frequency resolution trade-off by using feature maps extracted from spectrograms of various window lengths. In simulations, the hybrid CNN/RNN-based scheme is shown to outperform the CNN-based and conventional detection schemes. |
| doi_str_mv | 10.1109/LCOMM.2020.2971216 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LCOMM_2020_2971216</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8979431</ieee_id><sourcerecordid>2401142491</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-bfaa8bed840d0d341898ee2a481de17a7dd519dd0ca58dbad680a95f7441617a3</originalsourceid><addsrcrecordid>eNo9kMFOwzAQRC0EEqXwA3CJxDlh17Fr-4haSpFS9QCIo-XGm5IKkuCkh_49Lq247K40M6vRY-wWIUME81BMV8tlxoFDxo1CjpMzNkIpdcrjOI83aJMqZfQlu-r7LQBoLnHEzIwGKoe6bZK2SuaBfnbUlPt00XZd3WyS13rTuK8--aiHz2RG1CUFudBE6ZpdVFGhm9Mes_f509t0kRar55fpY5GW3MghXVfO6TV5LcCDzwVqo4m4Exo9oXLKe4nGeyid1H7t_ESDM7JSQuAk6vmY3R__dqGN5frBbttdOJSyXACi4MJgdPGjqwxt3weqbBfqbxf2FsEeENk_RPaAyJ4QxdDdMVQT0X9AG2VEjvkvNGVh0A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2401142491</pqid></control><display><type>article</type><title>Detection of Frequency-Hopping Signals With Deep Learning</title><source>IEEE Electronic Library (IEL)</source><creator>Lee, Kyung-Gyu ; Oh, Seong-Jun</creator><creatorcontrib>Lee, Kyung-Gyu ; Oh, Seong-Jun</creatorcontrib><description>Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolutional neural network (CNN) and hybrid CNN/recurrent neural network (RNN)-based schemes. The CNN-based scheme alleviates spectral leakage by using feature maps. The hybrid CNN/RNN-based scheme mitigates the time-frequency resolution trade-off by using feature maps extracted from spectrograms of various window lengths. In simulations, the hybrid CNN/RNN-based scheme is shown to outperform the CNN-based and conventional detection schemes.</description><identifier>ISSN: 1089-7798</identifier><identifier>EISSN: 1558-2558</identifier><identifier>DOI: 10.1109/LCOMM.2020.2971216</identifier><identifier>CODEN: ICLEF6</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Artificial neural networks ; CNN ; Computer simulation ; Deep learning ; Detection ; Feature extraction ; Feature maps ; Frequency hopping ; hybrid CNN-RNN ; Leakage ; Neural networks ; Recurrent neural networks ; Signal resolution ; Signal to noise ratio ; Spectrogram ; Spectrograms ; Time-frequency analysis ; Tradeoffs ; Training</subject><ispartof>IEEE communications letters, 2020-05, Vol.24 (5), p.1042-1046</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-bfaa8bed840d0d341898ee2a481de17a7dd519dd0ca58dbad680a95f7441617a3</citedby><cites>FETCH-LOGICAL-c295t-bfaa8bed840d0d341898ee2a481de17a7dd519dd0ca58dbad680a95f7441617a3</cites><orcidid>0000-0002-0235-9987 ; 0000-0001-9917-9845</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8979431$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8979431$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Lee, Kyung-Gyu</creatorcontrib><creatorcontrib>Oh, Seong-Jun</creatorcontrib><title>Detection of Frequency-Hopping Signals With Deep Learning</title><title>IEEE communications letters</title><addtitle>COML</addtitle><description>Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolutional neural network (CNN) and hybrid CNN/recurrent neural network (RNN)-based schemes. The CNN-based scheme alleviates spectral leakage by using feature maps. The hybrid CNN/RNN-based scheme mitigates the time-frequency resolution trade-off by using feature maps extracted from spectrograms of various window lengths. In simulations, the hybrid CNN/RNN-based scheme is shown to outperform the CNN-based and conventional detection schemes.</description><subject>Artificial neural networks</subject><subject>CNN</subject><subject>Computer simulation</subject><subject>Deep learning</subject><subject>Detection</subject><subject>Feature extraction</subject><subject>Feature maps</subject><subject>Frequency hopping</subject><subject>hybrid CNN-RNN</subject><subject>Leakage</subject><subject>Neural networks</subject><subject>Recurrent neural networks</subject><subject>Signal resolution</subject><subject>Signal to noise ratio</subject><subject>Spectrogram</subject><subject>Spectrograms</subject><subject>Time-frequency analysis</subject><subject>Tradeoffs</subject><subject>Training</subject><issn>1089-7798</issn><issn>1558-2558</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kMFOwzAQRC0EEqXwA3CJxDlh17Fr-4haSpFS9QCIo-XGm5IKkuCkh_49Lq247K40M6vRY-wWIUME81BMV8tlxoFDxo1CjpMzNkIpdcrjOI83aJMqZfQlu-r7LQBoLnHEzIwGKoe6bZK2SuaBfnbUlPt00XZd3WyS13rTuK8--aiHz2RG1CUFudBE6ZpdVFGhm9Mes_f509t0kRar55fpY5GW3MghXVfO6TV5LcCDzwVqo4m4Exo9oXLKe4nGeyid1H7t_ESDM7JSQuAk6vmY3R__dqGN5frBbttdOJSyXACi4MJgdPGjqwxt3weqbBfqbxf2FsEeENk_RPaAyJ4QxdDdMVQT0X9AG2VEjvkvNGVh0A</recordid><startdate>20200501</startdate><enddate>20200501</enddate><creator>Lee, Kyung-Gyu</creator><creator>Oh, Seong-Jun</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/0000-0002-0235-9987</orcidid><orcidid>https://orcid.org/0000-0001-9917-9845</orcidid></search><sort><creationdate>20200501</creationdate><title>Detection of Frequency-Hopping Signals With Deep Learning</title><author>Lee, Kyung-Gyu ; Oh, Seong-Jun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-bfaa8bed840d0d341898ee2a481de17a7dd519dd0ca58dbad680a95f7441617a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>CNN</topic><topic>Computer simulation</topic><topic>Deep learning</topic><topic>Detection</topic><topic>Feature extraction</topic><topic>Feature maps</topic><topic>Frequency hopping</topic><topic>hybrid CNN-RNN</topic><topic>Leakage</topic><topic>Neural networks</topic><topic>Recurrent neural networks</topic><topic>Signal resolution</topic><topic>Signal to noise ratio</topic><topic>Spectrogram</topic><topic>Spectrograms</topic><topic>Time-frequency analysis</topic><topic>Tradeoffs</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lee, Kyung-Gyu</creatorcontrib><creatorcontrib>Oh, Seong-Jun</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 & 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>Lee, Kyung-Gyu</au><au>Oh, Seong-Jun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detection of Frequency-Hopping Signals With Deep Learning</atitle><jtitle>IEEE communications letters</jtitle><stitle>COML</stitle><date>2020-05-01</date><risdate>2020</risdate><volume>24</volume><issue>5</issue><spage>1042</spage><epage>1046</epage><pages>1042-1046</pages><issn>1089-7798</issn><eissn>1558-2558</eissn><coden>ICLEF6</coden><abstract>Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolutional neural network (CNN) and hybrid CNN/recurrent neural network (RNN)-based schemes. The CNN-based scheme alleviates spectral leakage by using feature maps. The hybrid CNN/RNN-based scheme mitigates the time-frequency resolution trade-off by using feature maps extracted from spectrograms of various window lengths. In simulations, the hybrid CNN/RNN-based scheme is shown to outperform the CNN-based and conventional detection schemes.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LCOMM.2020.2971216</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0002-0235-9987</orcidid><orcidid>https://orcid.org/0000-0001-9917-9845</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1089-7798 |
| ispartof | IEEE communications letters, 2020-05, Vol.24 (5), p.1042-1046 |
| issn | 1089-7798 1558-2558 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_LCOMM_2020_2971216 |
| source | IEEE Electronic Library (IEL) |
| subjects | Artificial neural networks CNN Computer simulation Deep learning Detection Feature extraction Feature maps Frequency hopping hybrid CNN-RNN Leakage Neural networks Recurrent neural networks Signal resolution Signal to noise ratio Spectrogram Spectrograms Time-frequency analysis Tradeoffs Training |
| title | Detection of Frequency-Hopping Signals With Deep Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T08%3A16%3A24IST&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=Detection%20of%20Frequency-Hopping%20Signals%20With%20Deep%20Learning&rft.jtitle=IEEE%20communications%20letters&rft.au=Lee,%20Kyung-Gyu&rft.date=2020-05-01&rft.volume=24&rft.issue=5&rft.spage=1042&rft.epage=1046&rft.pages=1042-1046&rft.issn=1089-7798&rft.eissn=1558-2558&rft.coden=ICLEF6&rft_id=info:doi/10.1109/LCOMM.2020.2971216&rft_dat=%3Cproquest_RIE%3E2401142491%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=2401142491&rft_id=info:pmid/&rft_ieee_id=8979431&rfr_iscdi=true |