MEG Sensor Selection for Neural Speech Decoding

Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 8; s. 1
Hlavní autoři: Dash, Debadatta, Wisler, Alan, Ferrari, Paul, Davenport, Elizabeth, Maldjian, Joseph, Wang, Jun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Autoencoder
brain-computer interface
Brain-computer interfaces
Channels
Decoding
Electroencephalography
forward selection algorithm
Gradiometers
Human-computer interface
Liquid helium
Magnetic measurement
Magnetoencephalography
Magnetometers
Medical imaging
Modular design
neural speech decoding
OPM
Optimization
Production
Selectivity
Sensors
Spatial resolution
Speech
Speech processing
Support vector machines
SVM
Temporal resolution
Wearable technology
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors (200-300) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca's area were found to be commonly contributing among the higher-ranked sensors across all subjects.
AbstractList Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors (200 - 300) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca's area were found to be commonly contributing among the higher-ranked sensors across all subjects.Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors (200 - 300) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca's area were found to be commonly contributing among the higher-ranked sensors across all subjects.
Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors (200 – 300) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca’s area were found to be commonly contributing among the higher-ranked sensors across all subjects.
Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in providing communication assistance to locked-in patients. Magnetoencephalography (MEG) has recently shown great potential as a non-invasive neuroimaging modality for neural speech decoding, owing in part to its spatial selectivity over other high-temporal resolution devices. Standard MEG systems have a large number of cryogenically cooled channels/sensors ([Formula Omitted]) encapsulated within a fixed liquid helium dewar, precluding their use as wearable BCI devices. Fortunately, recently developed optically pumped magnetometers (OPM) do not require cryogens, and have the potential to be wearable and movable making them more suitable for BCI applications. This design is also modular allowing for customized montages to include only the sensors necessary for a particular task. As the number of sensors bears a heavy influence on the cost, size, and weight of MEG systems, minimizing the number of sensors is critical for designing practical MEG-based BCIs in the future. In this study, we sought to identify an optimal set of MEG channels to decode imagined and spoken phrases from the MEG signals. Using a forward selection algorithm with a support vector machine classifier we found that nine optimally located MEG gradiometers provided higher decoding accuracy compared to using all channels. Additionally, the forward selection algorithm achieved similar performance to dimensionality reduction using a stacked-sparse-autoencoder. Analysis of spatial dynamics of speech decoding suggested that both left and right hemisphere sensors contribute to speech decoding. Sensors approximately located near Broca’s area were found to be commonly contributing among the higher-ranked sensors across all subjects.
Author Wisler, Alan
Ferrari, Paul
Davenport, Elizabeth
Wang, Jun
Maldjian, Joseph
Dash, Debadatta
AuthorAffiliation 3 Department of Speech, Language, and Hearing Sciences, University of Texas at Austin, Austin, TX 78712, USA
2 Department of Neurology, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USA
1 Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712, USA
4 MEG Laboratory, Dell Children’s Medical Center, Austin, TX 78723, USA
6 Department of Radiology, University of Texas at Southwestern, Dallas, TX 75390, USA
5 Department of Psychology, The University of Texas at Austin, Austin, TX 78712, USA
AuthorAffiliation_xml – name: 6 Department of Radiology, University of Texas at Southwestern, Dallas, TX 75390, USA
– name: 2 Department of Neurology, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USA
– name: 4 MEG Laboratory, Dell Children’s Medical Center, Austin, TX 78723, USA
– name: 1 Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712, USA
– name: 5 Department of Psychology, The University of Texas at Austin, Austin, TX 78712, USA
– name: 3 Department of Speech, Language, and Hearing Sciences, University of Texas at Austin, Austin, TX 78712, USA
Author_xml – sequence: 1
  givenname: Debadatta
  surname: Dash
  fullname: Dash, Debadatta
  organization: Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX 78712 USA and Department of Neurology, Dell Medical School, University of Texas at Austin, Austin, TX 78712 USA
– sequence: 2
  givenname: Alan
  surname: Wisler
  fullname: Wisler, Alan
  organization: Department of Speech, Language, and Hearing Sciences, University of Texas at Austin, Austin, TX 78712 USA
– sequence: 3
  givenname: Paul
  surname: Ferrari
  fullname: Ferrari, Paul
  organization: MEG Lab, Dell Children's Medical Center, Austin, TX 78723 USA and Department of Psychology, University of Texas at Austin, Austin, TX 78712 USA
– sequence: 4
  givenname: Elizabeth
  surname: Davenport
  fullname: Davenport, Elizabeth
  organization: Department of Radiology, University of Texas at Southwestern, Dallas, TX 75390 USA
– sequence: 5
  givenname: Joseph
  surname: Maldjian
  fullname: Maldjian, Joseph
  organization: Department of Radiology, University of Texas at Southwestern, Dallas, TX 75390 USA
– sequence: 6
  givenname: Jun
  surname: Wang
  fullname: Wang, Jun
  organization: Department of Neurology, Dell Medical School, University of Texas at Austin, Austin, TX 78712 USA and Department of Speech, Language, and Hearing Sciences, University of Texas at Austin, Austin, TX 78712 USA. (e-mail: jun.wang@austin.utexas.edu)
BookMark eNp9UUtvEzEQtlARfdBf0EskLlyS-rV-XJCqNJRKBQ6Bs-XHOHW0WQfvLhL_HqcbEO0BX8Yz_r5vPPOdo5Mud4DQFcELQrC-vlkuV-v1gmKKFwxTpRh5hc4oEXrOGiZO_rmfosu-3-J6VC018g06ZYxi3kh9hq4_r-5ma-j6XGpowQ8pd7NYsy8wFtvO1nsA_zi7BZ9D6jZv0eto2x4uj_ECff-4-rb8NH_4ene_vHmYe67FMLfSEeYJw0ypALTxTjipOVUWuI8OQqTeOgJRSBd5sFIER23DKJE0CILZBbqfdEO2W7MvaWfLL5NtMk-FXDbGliH5FozkqjbV3kXqONbCSg_BRtxE2yhBQ9X6MGntR7eD4KEb6mTPRJ-_dOnRbPJPI4VQnJAq8P4oUPKPEfrB7FLvoW1tB3nsDeWCqKb-QVfouxfQbR5LV1dVUQ0XCmPJK0pPKF9y3xeIxqfBHlZf-6fWEGwOLpvJZXNw2Rxdrlz2gvtnkP-zriZWAoC_DE0J50qz35PDsrI
CODEN IAECCG
CitedBy_id crossref_primary_10_1016_j_neuroimage_2025_121403
crossref_primary_10_1109_TNSRE_2021_3096874
crossref_primary_10_1016_j_bspc_2025_108068
crossref_primary_10_1044_2024_JSLHR_24_00157
crossref_primary_10_3389_fnhum_2024_1305058
crossref_primary_10_1007_s11517_025_03340_y
crossref_primary_10_1016_j_neuroimage_2025_121182
crossref_primary_10_3389_fnhum_2022_874199
crossref_primary_10_1109_TIM_2024_3472830
crossref_primary_10_3390_bioengineering11060609
crossref_primary_10_1007_s11571_024_10085_1
crossref_primary_10_1038_s41467_021_27725_3
crossref_primary_10_31083_j_jin2304073
crossref_primary_10_1016_j_neucom_2025_130928
crossref_primary_10_1038_s41597_023_02286_w
crossref_primary_10_3390_s24216965
crossref_primary_10_1016_j_fmre_2024_04_011
crossref_primary_10_1016_j_neuroimage_2024_120864
crossref_primary_10_1109_ACCESS_2024_3524397
crossref_primary_10_1109_THMS_2025_3554449
Cites_doi 10.1007/s10548-013-0329-3
10.1073/pnas.94.26.14965
10.1063/1.323659
10.3389/fneng.2010.00009
10.1007/978-3-030-05587-5_16
10.1109/EMBC.2019.8857874
10.1113/JP277899
10.1523/JNEUROSCI.3814-11.2012
10.1016/j.neuroimage.2018.09.006
10.1093/brain/awg104
10.1038/s41598-019-41763-4
10.1109/ICASSP.2017.7952714
10.1016/j.neuroimage.2016.12.048
10.3389/fnins.2019.01267
10.1111/j.2044-8317.1992.tb00992.x
10.1088/1741-2552/ab0c59
10.1152/jn.00251.2010
10.1093/geronb/gbx008
10.1121/1.4800429
10.1044/nnsld13.3.4
10.1016/j.jneuroling.2009.08.006
10.1016/j.neuroimage.2019.06.010
10.3389/fpsyg.2012.00169
10.1016/j.isci.2018.09.016
10.1152/jn.00075.2011
10.1038/s41467-019-10994-4
10.1016/j.clinph.2005.11.002
10.1016/j.neuroimage.2019.05.063
10.1001/jama.2019.19813
10.1016/j.tics.2005.11.006
10.1109/TMI.2018.2836965
10.3390/brainsci8040057
10.1088/1741-2552/aa8235
10.1155/2016/7489108
10.1016/j.neuroimage.2011.01.046
10.1016/S1388-2457(02)00057-3
10.1007/s13311-018-00692-2
10.3390/s20082248
10.1126/science.1127647
10.1016/j.neuroimage.2012.10.001
10.1162/089892902760807140
10.3389/fnins.2014.00386
10.1007/978-3-642-34713-9_13
10.5755/j01.eie.23.2.18002
10.3389/fnins.2019.00060
10.1016/j.neuroimage.2017.10.011
10.1016/j.neuroimage.2017.01.034
10.21437/Interspeech.2019-3105
10.1038/s41586-019-1119-1
10.1016/j.specom.2010.01.001
10.3389/fnins.2016.00141
10.1016/j.jphysparis.2017.07.002
10.1016/j.clinph.2019.07.020
10.3389/fnint.2019.00028
10.1109/SMC.2019.8914246
10.1109/GlobalSIP.2018.8646401
10.3389/fnins.2020.00290
10.1109/JSEN.2010.2096465
10.1016/j.ejor.2017.08.040
10.1016/j.tics.2014.05.001
10.21437/Interspeech.2019-3109
10.1523/JNEUROSCI.0559-06.2006
10.1126/science.1164318
10.3389/fnins.2015.00217
10.1038/nature26147
10.1007/978-3-642-02574-7_5
10.1371/journal.pone.0225756
10.1016/S0140-6736(10)61156-7
10.1523/JNEUROSCI.2875-08.2008
10.1227/01.neu.0000333510.03970.80
10.1016/j.neulet.2012.08.030
10.3389/fnins.2018.00422
10.1016/S0042-6989(97)00169-7
10.1007/s00415-012-6821-y
10.1371/journal.pone.0072351
10.3389/fnins.2010.00161
10.1109/NER.2019.8717186
10.1109/ICBBE.2010.5515807
10.3389/fnins.2019.01058
10.1109/TASLP.2017.2758164
10.1007/s00779-017-1083-4
10.1371/journal.pone.0178602
10.1238/Physica.Topical.105a00027
10.1109/ICASSP.2019.8683453
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
7X8
5PM
DOA
DOI 10.1109/ACCESS.2020.3028831
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
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
METADEX
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic


Materials Research Database
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 1
ExternalDocumentID oai_doaj_org_article_748c499cbf2b4096a7cedaf05fa5862d
PMC7668411
10_1109_ACCESS_2020_3028831
9214489
Genre orig-research
GrantInformation_xml – fundername: University of Texas System Brain Initiative
  grantid: 362221
– fundername: National Institutes of Health
  grantid: R01DC016621; R03DC013990
  funderid: 10.13039/100000002
GroupedDBID 0R~
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
4.4
AAYXX
AGSQL
CITATION
EJD
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
7X8
5PM
ID FETCH-LOGICAL-c496t-a7b13c130388de25cb6b79428ae4cfbedf2cab1ef67bf4da76db2a532172d6103
IEDL.DBID RIE
ISICitedReferencesCount 28
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000577882500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:53:18 EDT 2025
Thu Aug 21 18:27:43 EDT 2025
Thu Jul 10 19:19:24 EDT 2025
Sun Jun 29 15:56:20 EDT 2025
Sat Nov 29 04:14:16 EST 2025
Tue Nov 18 22:23:55 EST 2025
Wed Aug 27 02:30:36 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c496t-a7b13c130388de25cb6b79428ae4cfbedf2cab1ef67bf4da76db2a532172d6103
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-7265-217X
0000-0002-0543-0304
OpenAccessLink https://ieeexplore.ieee.org/document/9214489
PMID 33204579
PQID 2454680074
PQPubID 4845423
PageCount 1
ParticipantIDs crossref_citationtrail_10_1109_ACCESS_2020_3028831
doaj_primary_oai_doaj_org_article_748c499cbf2b4096a7cedaf05fa5862d
proquest_miscellaneous_2461854999
crossref_primary_10_1109_ACCESS_2020_3028831
proquest_journals_2454680074
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7668411
ieee_primary_9214489
PublicationCentury 2000
PublicationDate 2020-01-01
PublicationDateYYYYMMDD 2020-01-01
PublicationDate_xml – month: 01
  year: 2020
  text: 2020-01-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2020
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
ref56
ref12
ref59
ref15
ref14
ref53
ref52
ref55
ref11
ref54
ref10
ref17
ref16
ref19
ref18
bengio (ref85) 2006
ref51
ref50
ref46
ref89
ref45
ref48
ref47
ref86
ref42
ref41
ref88
ref44
ref87
ref43
weston (ref58) 2001
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref82
ref81
dash (ref70) 2020
ref40
ref84
ref83
ref80
ref79
ref35
ref78
ref34
ref37
ref36
ref75
ref31
ref74
ref77
ref33
ref76
ref32
ref2
ref1
ref39
ref38
van der maaten (ref73) 2008; 9
ref71
ref72
ref68
ref24
ref67
ref23
ref26
ref69
ref25
ref64
ref20
ref63
ref66
ref22
ref65
ref21
ref28
ref27
ref29
sun (ref30) 2019
ref60
ref62
ref61
References_xml – ident: ref42
  doi: 10.1007/s10548-013-0329-3
– ident: ref74
  doi: 10.1073/pnas.94.26.14965
– ident: ref88
  doi: 10.1063/1.323659
– ident: ref33
  doi: 10.3389/fneng.2010.00009
– ident: ref65
  doi: 10.1007/978-3-030-05587-5_16
– ident: ref11
  doi: 10.1109/EMBC.2019.8857874
– ident: ref51
  doi: 10.1113/JP277899
– ident: ref81
  doi: 10.1523/JNEUROSCI.3814-11.2012
– ident: ref41
  doi: 10.1016/j.neuroimage.2018.09.006
– ident: ref75
  doi: 10.1093/brain/awg104
– ident: ref50
  doi: 10.1038/s41598-019-41763-4
– ident: ref10
  doi: 10.1109/ICASSP.2017.7952714
– ident: ref55
  doi: 10.1016/j.neuroimage.2016.12.048
– ident: ref18
  doi: 10.3389/fnins.2019.01267
– ident: ref57
  doi: 10.1111/j.2044-8317.1992.tb00992.x
– volume: 9
  start-page: 2579
  year: 2008
  ident: ref73
  article-title: Visualizing data using t-SNE
  publication-title: J Mach Learn Res
– ident: ref17
  doi: 10.1088/1741-2552/ab0c59
– ident: ref38
  doi: 10.1152/jn.00251.2010
– ident: ref56
  doi: 10.1093/geronb/gbx008
– ident: ref86
  doi: 10.1121/1.4800429
– ident: ref40
  doi: 10.1044/nnsld13.3.4
– ident: ref72
  doi: 10.1016/j.jneuroling.2009.08.006
– ident: ref49
  doi: 10.1016/j.neuroimage.2019.06.010
– ident: ref39
  doi: 10.3389/fpsyg.2012.00169
– ident: ref62
  doi: 10.1016/j.isci.2018.09.016
– ident: ref37
  doi: 10.1152/jn.00075.2011
– ident: ref19
  doi: 10.1038/s41467-019-10994-4
– ident: ref6
  doi: 10.1016/j.clinph.2005.11.002
– ident: ref53
  doi: 10.1016/j.neuroimage.2019.05.063
– ident: ref7
  doi: 10.1001/jama.2019.19813
– ident: ref63
  doi: 10.1016/j.tics.2005.11.006
– ident: ref61
  doi: 10.1109/TMI.2018.2836965
– ident: ref5
  doi: 10.3390/brainsci8040057
– ident: ref24
  doi: 10.1088/1741-2552/aa8235
– ident: ref89
  doi: 10.1155/2016/7489108
– ident: ref66
  doi: 10.1016/j.neuroimage.2011.01.046
– ident: ref3
  doi: 10.1016/S1388-2457(02)00057-3
– ident: ref14
  doi: 10.1007/s13311-018-00692-2
– ident: ref45
  doi: 10.3390/s20082248
– ident: ref84
  doi: 10.1126/science.1127647
– ident: ref64
  doi: 10.1016/j.neuroimage.2012.10.001
– start-page: 1
  year: 2020
  ident: ref70
  article-title: Role of brainwaves in neural speech decoding
  publication-title: Proc IEEE 28th Eur Signal Process Conf
– ident: ref35
  doi: 10.1162/089892902760807140
– ident: ref78
  doi: 10.3389/fnins.2014.00386
– ident: ref36
  doi: 10.1007/978-3-642-34713-9_13
– ident: ref60
  doi: 10.5755/j01.eie.23.2.18002
– ident: ref29
  doi: 10.3389/fnins.2019.00060
– ident: ref27
  doi: 10.1016/j.neuroimage.2017.10.011
– ident: ref47
  doi: 10.1016/j.neuroimage.2017.01.034
– ident: ref59
  doi: 10.21437/Interspeech.2019-3105
– ident: ref16
  doi: 10.1038/s41586-019-1119-1
– ident: ref4
  doi: 10.1016/j.specom.2010.01.001
– ident: ref34
  doi: 10.3389/fnins.2016.00141
– ident: ref87
  doi: 10.1016/j.jphysparis.2017.07.002
– ident: ref32
  doi: 10.1016/j.clinph.2019.07.020
– ident: ref83
  doi: 10.3389/fnint.2019.00028
– ident: ref22
  doi: 10.1109/SMC.2019.8914246
– ident: ref46
  doi: 10.1109/GlobalSIP.2018.8646401
– ident: ref12
  doi: 10.3389/fnins.2020.00290
– ident: ref68
  doi: 10.1109/JSEN.2010.2096465
– ident: ref69
  doi: 10.1016/j.ejor.2017.08.040
– start-page: 153
  year: 2006
  ident: ref85
  article-title: Greedy layer-wise training of deep networks
  publication-title: Proc 19th Int Conf Neural Inf Process Syst
– ident: ref76
  doi: 10.1016/j.tics.2014.05.001
– ident: ref20
  doi: 10.21437/Interspeech.2019-3109
– start-page: 668
  year: 2001
  ident: ref58
  article-title: Feature selection for SVMs
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref77
  doi: 10.1523/JNEUROSCI.0559-06.2006
– ident: ref9
  doi: 10.1126/science.1164318
– ident: ref15
  doi: 10.3389/fnins.2015.00217
– ident: ref48
  doi: 10.1038/nature26147
– ident: ref21
  doi: 10.1007/978-3-642-02574-7_5
– ident: ref82
  doi: 10.1371/journal.pone.0225756
– ident: ref2
  doi: 10.1016/S0140-6736(10)61156-7
– ident: ref79
  doi: 10.1523/JNEUROSCI.2875-08.2008
– ident: ref80
  doi: 10.1227/01.neu.0000333510.03970.80
– ident: ref43
  doi: 10.1016/j.neulet.2012.08.030
– ident: ref28
  doi: 10.3389/fnins.2018.00422
– ident: ref71
  doi: 10.1016/S0042-6989(97)00169-7
– ident: ref1
  doi: 10.1007/s00415-012-6821-y
– ident: ref67
  doi: 10.1371/journal.pone.0072351
– ident: ref8
  doi: 10.3389/fnins.2010.00161
– ident: ref44
  doi: 10.1109/NER.2019.8717186
– year: 2019
  ident: ref30
  article-title: Brain2Char: A deep architecture for decoding text from brain recordings
  publication-title: arXiv 1909 01401
– ident: ref13
  doi: 10.1109/ICBBE.2010.5515807
– ident: ref31
  doi: 10.3389/fnins.2019.01058
– ident: ref25
  doi: 10.1109/TASLP.2017.2758164
– ident: ref23
  doi: 10.1007/s00779-017-1083-4
– ident: ref54
  doi: 10.1371/journal.pone.0178602
– ident: ref52
  doi: 10.1238/Physica.Topical.105a00027
– ident: ref26
  doi: 10.1109/ICASSP.2019.8683453
SSID ssj0000816957
Score 2.3405788
Snippet Direct decoding of speech from the brain is a faster alternative to current electroencephalography (EEG) speller-based brain-computer interfaces (BCI) in...
SourceID doaj
pubmedcentral
proquest
crossref
ieee
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Algorithms
Autoencoder
brain-computer interface
Brain-computer interfaces
Channels
Decoding
Electroencephalography
forward selection algorithm
Gradiometers
Human-computer interface
Liquid helium
Magnetic measurement
Magnetoencephalography
Magnetometers
Medical imaging
Modular design
neural speech decoding
OPM
Optimization
Production
Selectivity
Sensors
Spatial resolution
Speech
Speech processing
Support vector machines
SVM
Temporal resolution
Wearable technology
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEB5EPOhBfGJ1lQoeLdtm2zyO6_o6qAg-8BaSNEFBusu6-vudaeuyvejFU6FJS_NNk_m-NnwDcIKUG_OmZ4kqkL5hCvCJRR2UmLKwqTQ-k_Xf8-cbcXcnX17U_UKpL9oT1tgDN8D1RS4dsnJnA7OoRbgRzpcmpEUwBbLxklZfZD0LYqpeg2XGVSFam6EsVf3haIQjQkHIUKemVGM366Si2rG_LbHSYZvdvZILyedyA9Zb1hgPm6fdhCVfbcHagpfgNvRvL67iBxSl4yke3usdVlWMlDQm_w28-GHivXuNz1FvUr7agafLi8fRddJWQ0hw_HyWGGGzgaOUI2XpWeEstziZGAKau2B9GZgzNvOBC9p8ZwRVijLFgCpQlUiSBruwXI0rvwcxc04MZI5c0as8BERVlYKnwTjSf4ZFwH6A0a61CqeKFe-6lgyp0g2amtDULZoRnM4vmjROGb93PyPE513J5ro-gcHXbfD1X8GPYJviNb-JIgM4qSLo_cRPt1PyQ7O8yLkkyhTB8bwZJxP9ITGVH39SH478hURgBKIT985zdluqt9falltwLvMs2_-PgR3AKoHVfOvpwfJs-ukPYcV9zd4-pkf1u_4NUocAoQ
  priority: 102
  providerName: Directory of Open Access Journals
Title MEG Sensor Selection for Neural Speech Decoding
URI https://ieeexplore.ieee.org/document/9214489
https://www.proquest.com/docview/2454680074
https://www.proquest.com/docview/2461854999
https://pubmed.ncbi.nlm.nih.gov/PMC7668411
https://doaj.org/article/748c499cbf2b4096a7cedaf05fa5862d
Volume 8
WOSCitedRecordID wos000577882500001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB21FQc4AKUgAmUVJI4Nm3gTfxzLsm0PtEIqoL1ZtmOrlapstd3lyG9nxnGjRkJIvSRR7ET22Na85483AJ8QcqPf9KxQDcI3dAG-sMiDCtM2tpTGVzKunv_6Ji4u5HKpvu_A0XAWxnsfN5_5z_QY1_LbldvSVNlUkb6XVLuwK4Toz2oN8ykUQEI1IgkLVaWaHs_nWAekgAyZaUlRdauR84ka_SmoyghfjndHPnA3Jy8eV9CX8DzByvy47wf7sOO7V_DsgdjgAUzPF6f5JbLW1RpvN3ELVpcjZs1JoAM_vrz13l3lX5GQkkN7DT9PFj_mZ0UKl1C4WvFNYYStZo58kpStZ42z3OJoY2jx2gXr28CcsZUPXNDuPCMolJRpZhSiqkUUNXsDe92q828hZ86JmawRTHpVh4A0R7WCl8E4IoiGZcDu7ahd0hKnkBY3OnKKUune-JqMr5PxMzgaPrrtpTT-n_0LNdCQlXSw4wu0tE7DSotaYuWVs4FZZKrcCOdbE8ommAa5WpvBAbXO8JPUMBkc3je3TmP2TrO6qbkkTJXBxyEZRxstoZjOr7aUhyPAIZaYgRh1k1E5xynd9VXU7Racy7qq3v27TO_hKVW_n945hL3Neus_wBP3e3N9t55gl1_KSZwxwOv5n8Ukdv-_Mzv_3A
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQceLWIQIEgcWzYxOvnsSwtRWxXSC2oN8txbLVSla22u_x-Zpw0aiSExClRbEf22NZ8nx_fAHxEyI1-M7DCCIRv6AJCUSMPKlwj6lK7UOm0e_5rrhYLfX5ufmzB_nAXJoSQDp-FT_Sa9vKbpd_QUtnEkL6XNvfgvuCcVd1trWFFhUJIGKF6aaGqNJOD2QxbgSSQITctKa5uNXI_SaW_D6syQpjj85F3HM7R0_-r6jN40gPL_KAbCc9hK7Qv4PEducEdmJwcfs1PkbcuV_i4Soew2hxRa04SHVj49DoEf5F_QUpKLm0Xfh4dns2Oiz5gQuG5kevCqbqaevJKWjeBCV_LGucbQ5tzH-vQROZdXYUoFZ3Pc4qCSTkxpSBVDeKo6UvYbpdteAU5815NNUc4GQyPEYmOaZQso_NEER3LgN3a0fpeTZyCWlzZxCpKYzvjWzK-7Y2fwf5Q6LoT0_h39s_UQUNWUsJOH9DStp9YVnGNjTe-jqxGriqd8qFxsRTRCWRrTQY71DvDT_qOyWDvtrttP2tvLOOCS02oKoMPQzLON9pEcW1YbiiPRIhDPDEDNRomo3qOU9rLi6TcraTUvKpe_71O7-Hh8dnJ3M6_Lb6_gUdkim6xZw-216tNeAsP_O_15c3qXRr4fwCW-wAk
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=MEG+Sensor+Selection+for+Neural+Speech+Decoding&rft.jtitle=IEEE+access&rft.au=DASH%2C+DEBADATTA&rft.au=WISLER%2C+ALAN&rft.au=FERRARI%2C+PAUL&rft.au=DAVENPORT%2C+ELIZABETH+MOODY&rft.date=2020-01-01&rft.eissn=2169-3536&rft.volume=8&rft.spage=182320&rft.epage=182337&rft_id=info:doi/10.1109%2Faccess.2020.3028831&rft_id=info%3Apmid%2F33204579&rft.externalDocID=PMC7668411
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon