Neural Network Detection of Data Sequences in Communication Systems

We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel models. Moreover, when the channel model is known, we demonstrate that it is possible to train detectors that do not require channel state inform...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on signal processing Ročník 66; číslo 21; s. 5663 - 5678
Hlavní autori:	Farsad, Nariman, Goldsmith, Andrea
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.11.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Artificial neural networks Bit error rate Channel estimation Channel models Communication systems deep learning detection Detection algorithms Detectors Error detection free-space optical communication Machine learning molecular communication Neural networks optical communication Performance evaluation Receivers Recurrent neural networks Sensors supervised learning
ISSN:	1053-587X, 1941-0476
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel models. Moreover, when the channel model is known, we demonstrate that it is possible to train detectors that do not require channel state information (CSI). In particular, a technique we call a sliding bidirectional recurrent neural network (SBRNN) is proposed for detection where, after training, the detector estimates the data in real time as the signal stream arrives at the receiver. We evaluate this algorithm, as well as other neural network (NN) architectures, using the Poisson channel model, which is applicable to both optical and molecular communication systems. In addition, we also evaluate the performance of this detection method applied to data sent over a molecular communication platform, where the channel model is difficult to model analytically. We show that SBRNN is computationally efficient, and can perform detection under various channel conditions without knowing the underlying channel model. We also demonstrate that the bit error rate performance of the proposed SBRNN detector is better than that of a Viterbi detector with imperfect CSI as well as that of other NN detectors that have been previously proposed. Finally, we show that the SBRNN can perform well in rapidly changing channels, where the coherence time is on the order of a single symbol duration.
AbstractList	We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel models. Moreover, when the channel model is known, we demonstrate that it is possible to train detectors that do not require channel state information (CSI). In particular, a technique we call a sliding bidirectional recurrent neural network (SBRNN) is proposed for detection where, after training, the detector estimates the data in real time as the signal stream arrives at the receiver. We evaluate this algorithm, as well as other neural network (NN) architectures, using the Poisson channel model, which is applicable to both optical and molecular communication systems. In addition, we also evaluate the performance of this detection method applied to data sent over a molecular communication platform, where the channel model is difficult to model analytically. We show that SBRNN is computationally efficient, and can perform detection under various channel conditions without knowing the underlying channel model. We also demonstrate that the bit error rate performance of the proposed SBRNN detector is better than that of a Viterbi detector with imperfect CSI as well as that of other NN detectors that have been previously proposed. Finally, we show that the SBRNN can perform well in rapidly changing channels, where the coherence time is on the order of a single symbol duration.
Author	Goldsmith, Andrea Farsad, Nariman
Author_xml	– sequence: 1 givenname: Nariman surname: Farsad fullname: Farsad, Nariman email: nfarsad@stanford.edu organization: Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA – sequence: 2 givenname: Andrea surname: Goldsmith fullname: Goldsmith, Andrea email: andrea@wsl.stanford.edu organization: Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
BookMark	eNp9kD1PwzAQhi0EEm1hR2KJxJzic2wnHlHKl1QVpHZgi-z0LKU0cbFdof570g8xMDC9NzzP3ekdkvPOdUjIDdAxAFX3i_n7mFEoxqyQRcbYGRmA4pBSnsvzfqYiS0WRf1ySYQgrSoFzJQeknOHW63Uyw_jt_GcywYh1bFyXOJtMdNTJHL-22NUYkqZLSte2266p9QGZ70LENlyRC6vXAa9POSKLp8dF-ZJO355fy4dpWjMFMZWWWqM4r5daIYhcsKwPI41iRlIrcjC5ZFRYCaiNVNoqY4BpKpaGMpWNyN1x7ca7_qUQq5Xb-q6_WDGAHIqcFqyn5JGqvQvBo63qJh7ejV436wpote-r6vuq9n1Vp756kf4RN75ptd_9p9welQYRf_GCC54xkf0AZhB3RQ
CODEN	ITPRED
CitedBy_id	crossref_primary_10_1109_LWC_2024_3402398 crossref_primary_10_3390_s21072414 crossref_primary_10_1109_ACCESS_2019_2930317 crossref_primary_10_3390_app10134622 crossref_primary_10_1109_LCOMM_2022_3193644 crossref_primary_10_1109_TVT_2022_3162887 crossref_primary_10_1109_JIOT_2025_3534166 crossref_primary_10_1109_JSEN_2023_3304971 crossref_primary_10_1109_JSAC_2020_3036954 crossref_primary_10_1109_LWC_2024_3387991 crossref_primary_10_2478_amns_2025_0445 crossref_primary_10_1109_TMBMC_2023_3278532 crossref_primary_10_1016_j_optcom_2019_03_013 crossref_primary_10_1109_COMST_2021_3066905 crossref_primary_10_1109_TCOMM_2021_3114682 crossref_primary_10_1109_LSP_2019_2953673 crossref_primary_10_1109_TMBMC_2020_3003532 crossref_primary_10_1109_ACCESS_2019_2929444 crossref_primary_10_1109_TWC_2020_3032663 crossref_primary_10_1109_MNANO_2023_3262377 crossref_primary_10_1109_TWC_2019_2924424 crossref_primary_10_1109_TAES_2021_3054073 crossref_primary_10_1016_j_dsp_2021_103086 crossref_primary_10_1121_10_0005474 crossref_primary_10_1134_S1063785019070241 crossref_primary_10_1109_TSP_2022_3140926 crossref_primary_10_1109_JSAC_2020_3036964 crossref_primary_10_1109_TMBMC_2025_3546503 crossref_primary_10_1109_JSAC_2021_3087252 crossref_primary_10_1109_TMBMC_2019_2926722 crossref_primary_10_1109_ACCESS_2025_3573096 crossref_primary_10_1109_LCOMM_2021_3082708 crossref_primary_10_1049_cmu2_12618 crossref_primary_10_1109_MWC_001_2200587 crossref_primary_10_1109_LCOMM_2020_3018260 crossref_primary_10_1016_j_comnet_2024_110233 crossref_primary_10_1109_JLT_2020_2994576 crossref_primary_10_1109_JPROC_2024_3437730 crossref_primary_10_1109_TWC_2021_3123220 crossref_primary_10_1109_TMBMC_2024_3360341 crossref_primary_10_1109_TCCN_2019_2943455 crossref_primary_10_1109_TVT_2021_3064868 crossref_primary_10_1109_ACCESS_2020_3010896 crossref_primary_10_1109_TSP_2021_3071210 crossref_primary_10_1109_LCOMM_2020_3011560 crossref_primary_10_1109_LCOMM_2022_3219382 crossref_primary_10_1109_JIOT_2023_3326142 crossref_primary_10_1371_journal_pone_0242361 crossref_primary_10_1109_TCOMM_2023_3321735 crossref_primary_10_1109_TSP_2022_3229947 crossref_primary_10_1016_j_phycom_2024_102503 crossref_primary_10_1109_JLT_2021_3102064 crossref_primary_10_1109_ACCESS_2022_3218802 crossref_primary_10_1155_2022_8992478 crossref_primary_10_1109_ACCESS_2024_3519310 crossref_primary_10_1016_j_phycom_2023_102222 crossref_primary_10_1038_s41598_021_98609_1 crossref_primary_10_1063_5_0067795 crossref_primary_10_1109_ACCESS_2020_3025597 crossref_primary_10_1109_JPROC_2019_2957798 crossref_primary_10_1109_TWC_2024_3367179 crossref_primary_10_1109_TNB_2020_3014958 crossref_primary_10_1109_TMBMC_2020_3035383 crossref_primary_10_1109_TNNLS_2023_3291702 crossref_primary_10_1007_s13540_025_00444_y crossref_primary_10_1109_TSP_2024_3510623 crossref_primary_10_1109_LCOMM_2020_2968319 crossref_primary_10_1109_JSAC_2020_3041377 crossref_primary_10_1109_TMBMC_2025_3546208 crossref_primary_10_1109_JSTSP_2022_3144020 crossref_primary_10_1109_ACCESS_2019_2937982 crossref_primary_10_1109_LCOMM_2024_3381600 crossref_primary_10_1109_TMBMC_2024_3412669 crossref_primary_10_1007_s00034_022_01968_x crossref_primary_10_1109_LCOMM_2021_3093651 crossref_primary_10_1109_LWC_2025_3554889 crossref_primary_10_1109_TII_2020_3015241 crossref_primary_10_1016_j_neunet_2023_05_005 crossref_primary_10_1109_TCCN_2022_3225790 crossref_primary_10_1007_s11760_025_04392_1 crossref_primary_10_1109_TWC_2022_3155945 crossref_primary_10_1109_COMST_2019_2935810 crossref_primary_10_1109_JPHOT_2020_3036464 crossref_primary_10_1109_TCCN_2018_2881442 crossref_primary_10_1109_TCOMM_2024_3394039 crossref_primary_10_1186_s13677_020_00168_9 crossref_primary_10_1109_TSP_2019_2899805 crossref_primary_10_1007_s11276_025_03985_5 crossref_primary_10_1109_LWC_2021_3079522 crossref_primary_10_1109_TCCN_2023_3279260 crossref_primary_10_1016_j_yofte_2024_104069 crossref_primary_10_1364_AO_386509 crossref_primary_10_1109_LCOMM_2021_3136508 crossref_primary_10_1111_exsy_13211 crossref_primary_10_1109_TVT_2021_3111081 crossref_primary_10_1109_TSIPI_2023_3335330 crossref_primary_10_1109_MCOM_001_2000957 crossref_primary_10_1016_j_yofte_2021_102724 crossref_primary_10_1109_TVT_2021_3103568 crossref_primary_10_1049_cmu2_12424 crossref_primary_10_1049_cmu2_12669 crossref_primary_10_1109_JIOT_2024_3373097 crossref_primary_10_1109_LCOMM_2024_3350369 crossref_primary_10_3390_s22010333 crossref_primary_10_1109_COMST_2021_3053615 crossref_primary_10_1016_j_comnet_2021_107930 crossref_primary_10_1109_MCOM_001_2000050 crossref_primary_10_1109_JLT_2022_3148270 crossref_primary_10_1016_j_dsp_2021_103161 crossref_primary_10_1109_TWC_2024_3485991 crossref_primary_10_3390_electronics11193130 crossref_primary_10_1016_j_nancom_2023_100476 crossref_primary_10_1109_TMBMC_2023_3297135 crossref_primary_10_1109_TWC_2022_3159762 crossref_primary_10_1109_TWC_2023_3272525 crossref_primary_10_1016_j_dcan_2024_10_006 crossref_primary_10_1063_5_0082856 crossref_primary_10_1109_TSP_2019_2908906 crossref_primary_10_1109_TSP_2021_3066069 crossref_primary_10_1109_JPROC_2023_3247480 crossref_primary_10_1016_j_compeleceng_2024_109425 crossref_primary_10_1109_MBITS_2022_3212978 crossref_primary_10_1109_ACCESS_2024_3381542 crossref_primary_10_1007_s11277_022_10111_7 crossref_primary_10_1109_TWC_2023_3241841 crossref_primary_10_1016_j_optcom_2022_128868 crossref_primary_10_1109_JSAC_2019_2934004 crossref_primary_10_1109_OJIES_2025_3560946 crossref_primary_10_1016_j_dsp_2021_103170 crossref_primary_10_1109_JSAC_2019_2933969 crossref_primary_10_1109_TNB_2023_3262555 crossref_primary_10_1109_TWC_2023_3270236 crossref_primary_10_1109_TCCN_2020_3018736 crossref_primary_10_1109_TCOMM_2024_3516504 crossref_primary_10_1109_TCCN_2020_2990773 crossref_primary_10_1109_LWC_2020_3009170 crossref_primary_10_1016_j_phycom_2022_101922 crossref_primary_10_3390_rs15184553 crossref_primary_10_1109_JSAC_2019_2933964 crossref_primary_10_1109_TWC_2025_3533959 crossref_primary_10_1109_TVT_2022_3158692 crossref_primary_10_1109_LCOMM_2023_3297129 crossref_primary_10_1109_TCOMM_2022_3219141 crossref_primary_10_1109_TVT_2019_2951822 crossref_primary_10_1109_ACCESS_2024_3483443 crossref_primary_10_1109_TCOMM_2019_2954399 crossref_primary_10_1109_JPROC_2019_2941458 crossref_primary_10_1109_LCOMM_2022_3189030 crossref_primary_10_32604_cmc_2021_016230 crossref_primary_10_1109_JLT_2024_3519360 crossref_primary_10_1109_JPHOT_2020_3019824 crossref_primary_10_2478_amns_2025_0605 crossref_primary_10_1109_TSP_2021_3139506 crossref_primary_10_1109_LCOMM_2021_3105601 crossref_primary_10_1109_JSEN_2023_3274293 crossref_primary_10_1109_TMBMC_2023_3342731 crossref_primary_10_1109_TWC_2020_2972352
Cites_doi	10.1109/JSAC.2016.2525538 10.1002/9780470741627 10.1109/COMST.2016.2527741 10.1002/ecja.20352 10.1109/78.650093 10.1016/j.neunet.2005.06.042 10.1016/S0165-1684(00)00030-X 10.1109/MCOM.2009.4752682 10.1109/49.339913 10.1073/pnas.1508521112 10.1109/MCOM.2012.6122529 10.1371/journal.pone.0082935 10.1016/j.comnet.2008.04.001 10.1109/JSTSP.2017.2788405 10.1126/scitranslmed.aaa3519 10.1109/JSAC.2009.091203 10.1109/TCOMM.2018.2792457 10.1016/j.jmb.2005.10.076 10.1109/TCCN.2017.2758370 10.1038/nature14539 10.1109/MSP.2012.2205597 10.1109/PROC.1973.9030 10.1109/TWC.2015.2436398 10.1109/TCOMM.2013.112513.130142 10.1049/ip-i-2.1990.0056 10.1007/s11277-007-9293-0 10.1109/72.554195 10.1109/26.153366 10.1109/JSTSP.2017.2784180 10.1017/CBO9781139149693 10.1109/TIT.2012.2193554 10.1109/JSTSP.2018.2794062 10.1109/TMBMC.2015.2502858 10.1109/TNB.2014.2337239 10.1162/neco.1997.9.8.1735
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TSP.2018.2868322
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0476
EndPage	5678
ExternalDocumentID	10_1109_TSP_2018_2868322 8454325
Genre	orig-research
GrantInformation_xml	– fundername: ONR grantid: N00014-18-1-2191 – fundername: NSF Center for Science of Information grantid: NSF-CCF-0939370
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RNS TAE TN5 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D RIG
ID	FETCH-LOGICAL-c291t-6f0fb944cda9e157523e15b6b92b60f571b76205f61eab69af9bb12a05db0293
IEDL.DBID	RIE
ISICitedReferencesCount	265
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000446159800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1053-587X
IngestDate	Mon Jun 30 10:12:37 EDT 2025 Tue Nov 18 22:35:49 EST 2025 Sat Nov 29 04:10:47 EST 2025 Wed Aug 27 02:50:49 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	21
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-6f0fb944cda9e157523e15b6b92b60f571b76205f61eab69af9bb12a05db0293
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-0157-1596
PQID	2117187082
PQPubID	85478
PageCount	16
ParticipantIDs	proquest_journals_2117187082 crossref_citationtrail_10_1109_TSP_2018_2868322 ieee_primary_8454325 crossref_primary_10_1109_TSP_2018_2868322
PublicationCentury	2000
PublicationDate	2018-11-01
PublicationDateYYYYMMDD	2018-11-01
PublicationDate_xml	– month: 11 year: 2018 text: 2018-11-01 day: 01
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on signal processing
PublicationTitleAbbrev	TSP
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref13 ref12 ref59 ref15 ref58 majumdar (ref56) 0; 6709 ref53 ref55 amodei (ref31) 0 ref17 ghassemlooy (ref35) 2012 lingyun (ref61) 0; 1 nachmani (ref19) 2017 ref50 shamai (ref52) 0; 137 grzybowski (ref10) 2009 ref48 ref47 ref42 li (ref34) 0 o’shea (ref18) 0 samuel (ref23) 0 ref43 ref49 forney (ref60) 0; 61 murillo-fuentes (ref14) 2006 ref4 ref3 ref5 ref40 jamali (ref39) 0 ref37 viterbi (ref44) 2013 ref36 jamali (ref38) 2016; 64 graves (ref30) 0 ref1 he (ref28) 0 lecun (ref6) 2015; 521 ibnkahla (ref8) 2000; 80 cammerer (ref22) 0 moritani (ref2) 0 nachmani (ref16) 0 farsad (ref41) 0 o’shea (ref25) 0 krizhevsky (ref27) 0 dahlman (ref45) 2013 lee (ref24) 2017 kingma (ref62) 0 ref26 ref64 ref20 farsad (ref9) 0 ref63 ref65 slomovic (ref66) 0; 112 ref21 cover (ref46) 2006 ref29 graves (ref51) 0 cho (ref33) 0 goodfellow (ref7) 2016 bahdanau (ref32) 2015 farsad (ref54) 0 debnath (ref11) 2011
References_xml	– start-page: 939 year: 2006 ident: ref14 article-title: Gaussian processes for multiuser detection in DS-CDMA receivers publication-title: Proc Adv Neural Inf Process Syst – start-page: 369 year: 0 ident: ref51 article-title: Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks publication-title: Proc Int Conf Mach Learn – ident: ref43 doi: 10.1109/JSAC.2016.2525538 – volume: 64 start-page: 423 year: 2016 ident: ref38 article-title: Channel estimation for diffusive molecular communications publication-title: IEEE Trans Commun – year: 2009 ident: ref10 publication-title: Chemistry in Motion Reaction-Diffusion Systems for Micro- And Nanotechnology doi: 10.1002/9780470741627 – ident: ref5 doi: 10.1109/COMST.2016.2527741 – ident: ref55 doi: 10.1002/ecja.20352 – year: 2017 ident: ref19 article-title: RNN decoding of linear block codes publication-title: arXiv 1702 07560 – year: 2016 ident: ref7 publication-title: Deep Learning – start-page: 1097 year: 0 ident: ref27 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref49 doi: 10.1109/78.650093 – year: 2015 ident: ref32 article-title: Neural machine translation by jointly learning to align and translate – ident: ref50 doi: 10.1016/j.neunet.2005.06.042 – start-page: 2468 year: 0 ident: ref54 article-title: Capacity of molecular channels with imperfect particle-intensity modulation and detection publication-title: Proc IEEE Int Symp Inf Theory – start-page: 5 year: 0 ident: ref2 article-title: Molecular communication for health care applications publication-title: Proc 4th Annu IEEE Int Conf Pervasive Comput Commun Workshops – start-page: 223 year: 0 ident: ref18 article-title: Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention publication-title: Proc IEEE Int Symp Signal Process Inf Technol – volume: 80 start-page: 1185 year: 2000 ident: ref8 article-title: Applications of neural networks to digital communications: A survey publication-title: Signal Process doi: 10.1016/S0165-1684(00)00030-X – ident: ref1 doi: 10.1109/MCOM.2009.4752682 – year: 0 ident: ref34 article-title: Protein secondary structure prediction using cascaded convolutional and recurrent neural networks publication-title: Proc Int Joint Conf Artif Intell – year: 2012 ident: ref35 publication-title: Optical Wireless Communications System and Channel Modelling with MATLAB – ident: ref13 doi: 10.1109/49.339913 – volume: 112 start-page: 14 429 year: 0 ident: ref66 article-title: Synthetic biology devices for in vitro and in vivo diagnostics publication-title: Proc Nat Acad Sci doi: 10.1073/pnas.1508521112 – ident: ref63 doi: 10.1109/MCOM.2012.6122529 – year: 0 ident: ref62 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent – start-page: 1724 year: 0 ident: ref33 article-title: Learning phrase representations using RNN encoder-decoder for statistical machine translation publication-title: Proc Conf Emp Methods Natural Lang Process – start-page: 173 year: 0 ident: ref31 article-title: Deep speech 2: End-to-end speech recognition in English and Mandarin publication-title: Proc Int Conf Mach Learn – year: 2017 ident: ref24 article-title: Machine learning based channel modeling for molecular MIMO communications publication-title: Proc IEEE Int Workshop Signal Process Adv Wireless Commun – ident: ref42 doi: 10.1371/journal.pone.0082935 – start-page: 1 year: 0 ident: ref41 article-title: A novel experimental platform for in-vessel multi-chemical molecular communications publication-title: Proc IEEE Global Commun Conf – start-page: 1 year: 0 ident: ref25 article-title: Learning approximate neural estimators for wireless channel state information publication-title: Proc IEEE 27th Int Workshop Mach Learn Signal Process – year: 2013 ident: ref45 publication-title: 4G LTE/LTE-Advanced for Mobile Broadband – ident: ref3 doi: 10.1016/j.comnet.2008.04.001 – ident: ref20 doi: 10.1109/JSTSP.2017.2788405 – ident: ref65 doi: 10.1126/scitranslmed.aaa3519 – year: 2006 ident: ref46 publication-title: Elements of Information Theory – ident: ref57 doi: 10.1109/JSAC.2009.091203 – volume: 6709 year: 0 ident: ref56 article-title: Reconstruction of probability density function of intensity fluctuations relevant to free-space laser communications through atmospheric turbulence publication-title: Proc SPIE – start-page: 1 year: 0 ident: ref22 article-title: Scaling deep learning-based decoding of polar codes via partitioning publication-title: Proc IEEE Global Commun Conf – start-page: 1764 year: 0 ident: ref30 article-title: Towards end-to-end speech recognition with recurrent neural networks publication-title: Proc 31st Int Conf Mach Learn – ident: ref40 doi: 10.1109/TCOMM.2018.2792457 – start-page: 770 year: 0 ident: ref28 article-title: Deep residual learning for image recognition publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref64 doi: 10.1016/j.jmb.2005.10.076 – ident: ref26 doi: 10.1109/TCCN.2017.2758370 – volume: 521 start-page: 436 year: 2015 ident: ref6 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – start-page: 1 year: 0 ident: ref9 article-title: A molecular communication system using acids, bases and hydrogen ions publication-title: Proc IEEE 17th Int Workshop Signal Process Advances Wireless Commun – start-page: 3190 year: 0 ident: ref39 article-title: SCW codes for optimal CSI-free detection in diffusive molecular communications publication-title: Proc IEEE Int Symp Inf Theory – ident: ref29 doi: 10.1109/MSP.2012.2205597 – volume: 61 start-page: 268 year: 0 ident: ref60 article-title: The Viterbi algorithm publication-title: Proc IEEE doi: 10.1109/PROC.1973.9030 – ident: ref36 doi: 10.1109/TWC.2015.2436398 – ident: ref53 doi: 10.1109/TCOMM.2013.112513.130142 – volume: 137 start-page: 424 year: 0 ident: ref52 article-title: Capacity of a pulse amplitude modulated direct detection photon channel publication-title: IEE Proc I-Commun Speech Vis doi: 10.1049/ip-i-2.1990.0056 – ident: ref15 doi: 10.1007/s11277-007-9293-0 – ident: ref47 doi: 10.1109/72.554195 – ident: ref12 doi: 10.1109/26.153366 – ident: ref17 doi: 10.1109/JSTSP.2017.2784180 – volume: 1 start-page: 699 year: 0 ident: ref61 article-title: Efficient Viterbi beam search algorithm using dynamic pruning publication-title: Proc 7th Int Conf Signal Process – year: 2013 ident: ref44 publication-title: Principles of Digital Communication and Coding – ident: ref4 doi: 10.1017/CBO9781139149693 – ident: ref58 doi: 10.1109/TIT.2012.2193554 – start-page: 1 year: 0 ident: ref23 article-title: Deep MIMO detection publication-title: proc IEEE 18th Int Workshop Signal Process Adv Wireless Commun – ident: ref21 doi: 10.1109/JSTSP.2018.2794062 – year: 2011 ident: ref11 publication-title: Nonlinear partial differential equations for scientists and engineers – ident: ref37 doi: 10.1109/TMBMC.2015.2502858 – start-page: 341 year: 0 ident: ref16 article-title: Learning to decode linear codes using deep learning publication-title: Proc 54th Annu Allerton Conf Commun Control Comput – ident: ref59 doi: 10.1109/TNB.2014.2337239 – ident: ref48 doi: 10.1162/neco.1997.9.8.1735
SSID	ssj0014496
Score	2.665132
Snippet	We consider detection based on deep learning, and show it is possible to train detectors that perform well without any knowledge of the underlying channel...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5663
SubjectTerms	Artificial neural networks Bit error rate Channel estimation Channel models Communication systems deep learning detection Detection algorithms Detectors Error detection free-space optical communication Machine learning molecular communication Neural networks optical communication Performance evaluation Receivers Recurrent neural networks Sensors supervised learning
Title	Neural Network Detection of Data Sequences in Communication Systems
URI	https://ieeexplore.ieee.org/document/8454325 https://www.proquest.com/docview/2117187082
Volume	66
WOSCitedRecordID	wos000446159800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0476 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014496 issn: 1053-587X databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH9sw4Me_JridEoOXgS7pV3SNEfZHB5kDDZkt5KkCQykk63z7zdJu-JQBE_t4SWUXz7e7_V9AdwrgmXMJA0kx0lABkIG3FkpSaaIJllilG8H9PbKJpNkseDTBjzWuTBaax98pnvu1fvys5Xaul9l_YRQMohoE5qMsTJXq_YYEOJ7cVm6MAhowhY7lyTm_fls6mK4kl6UxG4D76kg31Plx0Xstcv45H_fdQrHFYtET-Wyn0FD5-dw9K22YBuGruyGlZmUcd5opAsfdZWjlUEjUQg020VRo2WO9hJFUFXH_ALm4-f58CWoOiYEKuJhEcQGG8kJUZngOrRMLBrYh4wlj2SMDWWhtJcfpiYOtZAxF4ZLGUYC00xiq_gvoZWvcn0FiMVKSGG5FrGMihrCmckyq8siRR0liDrQ32GYqqqauGtq8Z56qwLz1KKeOtTTCvUOPNQjPspKGn_Ith3KtVwFcAe6u2VKq6O2Sa0Fa_Urs1Tm-vdRN3Do5i4TCLvQKtZbfQsH6rNYbtZ3fhd9Ab6dw4Q
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD7MKagP3sV5zYMvgnVplrTNo2yOiXMIDtlbSdIEBtLJ1vn7TdJuOBTBp_bhhJQvl_OdnhvAtaJYRrFkgeQ4CWhLyIA7KyXJFNU0S4zy7YDe-vFgkIxG_KUGt8tcGK21Dz7Td-7V-_KziZq7X2XNhDLaImwN1hmlJCyztZY-A0p9Ny5LGFoBS-LRwimJeXP4-uKiuJI7kkRuC68oId9V5cdV7PVLd_d_X7YHOxWPRPflwu9DTecHsP2tuuAhtF3hDSszKCO9UUcXPu4qRxODOqIQ6HURR43GOVpJFUFVJfMjGHYfhu1eUPVMCBThYRFEBhvJKVWZ4Dq0XIy07ENGkhMZYcPiUNrrDzMThVrIiAvDpQyJwCyT2Kr-Y6jnk1yfAIojJaSwbItaTsUM5bHJMqvNiGKOFJAGNBcYpqqqJ-7aWryn3q7APLWopw71tEK9ATfLER9lLY0_ZA8dyku5CuAGnC-WKa0O2yy1NqzVsLElM6e_j7qCzd7wuZ_2HwdPZ7Dl5inTCc-hXkzn-gI21Gcxnk0v_Y76AhcWxss
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Neural+Network+Detection+of+Data+Sequences+in+Communication+Systems&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Farsad%2C+Nariman&rft.au=Goldsmith%2C+Andrea&rft.date=2018-11-01&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=66&rft.issue=21&rft.spage=5663&rft.epage=5678&rft_id=info:doi/10.1109%2FTSP.2018.2868322&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSP_2018_2868322
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon