Integrating language models into classifiers for BCI communication: a review

The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing fie...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of neural engineering Jg. 13; H. 3; S. 031002
Hauptverfasser: Speier, W, Arnold, C, Pouratian, N
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England 01.06.2016
Schlagworte:
ISSN:1741-2552, 1741-2552
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models. Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation. Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.
AbstractList The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems.OBJECTIVEThe present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems.The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models.APPROACHThe domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models.Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation.MAIN RESULTSAlthough this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation.Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.SIGNIFICANCEEach of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.
The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models. Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation. Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.
Author Arnold, C
Speier, W
Pouratian, N
Author_xml – sequence: 1
  givenname: W
  surname: Speier
  fullname: Speier, W
  organization: Department of Neurosurgery, University of California, Los Angeles, CA 90095, USA. Medical Imaging Informatics Group, University of California, Los Angeles, CA 90095, USA
– sequence: 2
  givenname: C
  surname: Arnold
  fullname: Arnold, C
– sequence: 3
  givenname: N
  surname: Pouratian
  fullname: Pouratian, N
BackLink https://www.ncbi.nlm.nih.gov/pubmed/27153565$$D View this record in MEDLINE/PubMed
BookMark eNpNkEtLxDAUhYOMOA_9CUqWbmrzaB51p4OPgQE3ui5pclsibTI2reK_t-AIrs7h8J3L5azRIsQACF1SckOJ1jlVBc2YkCSnPOc54ZQQdoJWx1ywxT-_ROuU3skMqZKcoSVTVHAhxQrtd2GEdjCjDy3uTGgn0wLuo4MuYR_GiG1nUvKNhyHhJg74frvDNvb9FLydazHcYoMH-PTwdY5OG9MluDjqBr09Prxun7P9y9Nue7fPrOB8zIQrnSLOlEzy2jElDQhZU6EdrYUyWhpqpbKiJlI6WlgQRUM5V5xoTqV1bIOuf-8ehvgxQRqr3icL3fw_xClVVOmSFEpzOaNXR3Sqe3DVYfC9Gb6rvwXYD2_bX0A
CitedBy_id crossref_primary_10_1007_s11517_024_03070_7
crossref_primary_10_1186_s42490_024_00080_2
crossref_primary_10_1371_journal_pone_0218177
crossref_primary_10_1371_journal_pone_0175382
crossref_primary_10_1111_isj_12337
crossref_primary_10_1080_2326263X_2019_1697163
crossref_primary_10_1080_2326263X_2016_1252143
crossref_primary_10_1109_ACCESS_2021_3050545
crossref_primary_10_3389_fnhum_2017_00581
crossref_primary_10_3390_app15010392
crossref_primary_10_1109_TNSRE_2021_3137340
crossref_primary_10_1088_1741_2552_aa7525
crossref_primary_10_1080_2326263X_2018_1504662
crossref_primary_10_1002_adfm_202008936
crossref_primary_10_1038_s41467_024_48576_8
crossref_primary_10_3389_fnhum_2024_1305445
crossref_primary_10_1088_2057_1976_aa99f3
crossref_primary_10_1088_1741_2552_ab386d
crossref_primary_10_1080_17483107_2022_2146217
crossref_primary_10_1109_TNSRE_2018_2810332
crossref_primary_10_3390_computers8020033
crossref_primary_10_1016_j_neuroimage_2020_116999
crossref_primary_10_1080_2326263X_2024_2413214
crossref_primary_10_1016_j_neures_2024_06_003
crossref_primary_10_3390_s25133987
crossref_primary_10_1038_s41598_019_55166_y
crossref_primary_10_3390_brainsci8040057
crossref_primary_10_1145_3167902_3167904
crossref_primary_10_1080_13607863_2018_1426718
crossref_primary_10_1080_2326263X_2017_1330611
crossref_primary_10_1109_ACCESS_2019_2941642
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1088/1741-2560/13/3/031002
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Anatomy & Physiology
EISSN 1741-2552
ExternalDocumentID 27153565
Genre Journal Article
Review
GrantInformation_xml – fundername: NIBIB NIH HHS
  grantid: K23 EB014326
GroupedDBID ---
02O
1JI
1WK
4.4
53G
5B3
5GY
5VS
5ZH
7.M
7.Q
AAGCD
AAJIO
AAJKP
AALHV
AATNI
ABHWH
ABJNI
ABQJV
ABVAM
ACAFW
ACARI
ACGFS
ACHIP
ADEQX
AEFHF
AENEX
AERVB
AFYNE
AGQPQ
AHSEE
AKPSB
ALMA_UNASSIGNED_HOLDINGS
AOAED
ARNYC
ASPBG
ATQHT
AVWKF
AZFZN
BBWZM
CEBXE
CGR
CJUJL
CRLBU
CS3
CUY
CVF
DU5
EBS
ECM
EDWGO
EIF
EJD
EMSAF
EPQRW
EQZZN
F5P
FEDTE
HVGLF
IHE
IJHAN
IOP
IZVLO
JCGBZ
KOT
LAP
M45
N5L
N9A
NPM
NT-
NT.
P2P
PJBAE
Q02
RIN
RNS
RO9
ROL
RPA
S3P
SY9
W28
XPP
7X8
AEINN
ID FETCH-LOGICAL-c533t-5d9d70da9263bd276ae56b158d1b57a86a1c67c5b066d14ce54f1337308316cd2
IEDL.DBID 7X8
ISICitedReferencesCount 39
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000375701200002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1741-2552
IngestDate Thu Sep 04 17:50:48 EDT 2025
Mon Jul 21 05:47:18 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c533t-5d9d70da9263bd276ae56b158d1b57a86a1c67c5b066d14ce54f1337308316cd2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
OpenAccessLink http://doi.org/10.1088/1741-2560/13/3/031002
PMID 27153565
PQID 1789047836
PQPubID 23479
ParticipantIDs proquest_miscellaneous_1789047836
pubmed_primary_27153565
PublicationCentury 2000
PublicationDate 2016-06-01
PublicationDateYYYYMMDD 2016-06-01
PublicationDate_xml – month: 06
  year: 2016
  text: 2016-06-01
  day: 01
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Journal of neural engineering
PublicationTitleAlternate J Neural Eng
PublicationYear 2016
References 23674419 - IEEE Trans Biomed Eng. 2013 Oct;60(10):2696-705
24808413 - IEEE Trans Neural Syst Rehabil Eng. 2014 Jul;22(4):837-46
23465430 - Clin Neurophysiol. 2013 Jul;124(7):1321-8
22510955 - IEEE Trans Neural Syst Rehabil Eng. 2012 Jul;20(4):584-94
24760927 - IEEE Trans Neural Syst Rehabil Eng. 2014 May;22(3):678-84
25068464 - PLoS One. 2014 Jul 28;9(7):e102504
24167623 - PLoS One. 2013 Oct 22;8(10):e78432
23366267 - Conf Proc IEEE Eng Med Biol Soc. 2012;2012:1827-30
15813410 - IEEE Trans Neural Syst Rehabil Eng. 2005 Mar;13(1):89-98
23366432 - Conf Proc IEEE Eng Med Biol Soc. 2012;2012:2497-500
20457551 - IEEE Trans Neural Syst Rehabil Eng. 2011 Feb;19(1):6-14
24370570 - Neurorehabil Neural Repair. 2014 May;28(4):387-94
23369924 - J Neural Eng. 2013 Apr;10(2):026001
20071274 - IEEE Trans Neural Syst Rehabil Eng. 2010 Apr;18(2):127-33
22156110 - J Neural Eng. 2012 Feb;9(1):016004
26061188 - J Neural Eng. 2015 Aug;12(4):046018
25588137 - J Neural Eng. 2015 Feb;12(1):016013
20347387 - Clin Neurophysiol. 2010 Jul;121(7):1109-20
22833713 - Front Neurosci. 2012 May 23;6:72
25775495 - IEEE Trans Neural Syst Rehabil Eng. 2015 Sep;23(5):910-20
20921326 - Neurorehabil Neural Repair. 2011 May;25(4):323-31
15188880 - IEEE Trans Biomed Eng. 2004 Jun;51(6):1067-72
24500542 - Proc IEEE Int Conf Acoust Speech Signal Process. 2012;:null
21278858 - Int J Hum Comput Interact. 2011 Jan 1;27(1):69-84
21067970 - Clin Neurophysiol. 2011 Apr;122(4):731-7
23466266 - Clin Neurophysiol. 2013 May;124(5):901-8
23429035 - J Neural Eng. 2013 Apr;10(2):026012
21934188 - J Neural Eng. 2011 Oct;8(5):056016
15188881 - IEEE Trans Biomed Eng. 2004 Jun;51(6):1073-6
16860920 - Biol Psychol. 2006 Oct;73(3):242-52
24675760 - Sensors (Basel). 2014 Mar 26;14(4):5967-93
22016719 - Front Neurosci. 2011 Oct 14;5:112
17124334 - J Neural Eng. 2006 Dec;3(4):299-305
22496763 - PLoS One. 2012;7(4):e33758
22939456 - Clin Neurophysiol. 2013 Feb;124(2):306-14
17271271 - Conf Proc IEEE Eng Med Biol Soc. 2004;6:4363-6
24244070 - Comput Speech Lang. 2013 Sep 1;27(6):null
10896179 - IEEE Trans Rehabil Eng. 2000 Jun;8(2):174-9
21369351 - Front Neurosci. 2011 Feb 07;5:5
12048038 - Clin Neurophysiol. 2002 Jun;113(6):767-91
24099944 - J Neural Eng. 2013 Dec;10(6):066003
21534845 - Amyotroph Lateral Scler. 2011 Sep;12(5):318-24
20569051 - Biomed Tech (Berl). 2010 Aug;55(4):203-10
21909321 - Front Neurosci. 2011 Aug 22;5:99
25686293 - J Neural Eng. 2015 Apr;12(2):026007
2461285 - Electroencephalogr Clin Neurophysiol. 1988 Dec;70(6):510-23
9865889 - IEEE Trans Rehabil Eng. 1998 Dec;6(4):415-23
References_xml – reference: 22016719 - Front Neurosci. 2011 Oct 14;5:112
– reference: 21534845 - Amyotroph Lateral Scler. 2011 Sep;12(5):318-24
– reference: 23465430 - Clin Neurophysiol. 2013 Jul;124(7):1321-8
– reference: 2461285 - Electroencephalogr Clin Neurophysiol. 1988 Dec;70(6):510-23
– reference: 24244070 - Comput Speech Lang. 2013 Sep 1;27(6):null
– reference: 12048038 - Clin Neurophysiol. 2002 Jun;113(6):767-91
– reference: 20347387 - Clin Neurophysiol. 2010 Jul;121(7):1109-20
– reference: 24675760 - Sensors (Basel). 2014 Mar 26;14(4):5967-93
– reference: 23674419 - IEEE Trans Biomed Eng. 2013 Oct;60(10):2696-705
– reference: 16860920 - Biol Psychol. 2006 Oct;73(3):242-52
– reference: 20457551 - IEEE Trans Neural Syst Rehabil Eng. 2011 Feb;19(1):6-14
– reference: 17124334 - J Neural Eng. 2006 Dec;3(4):299-305
– reference: 20569051 - Biomed Tech (Berl). 2010 Aug;55(4):203-10
– reference: 21067970 - Clin Neurophysiol. 2011 Apr;122(4):731-7
– reference: 22156110 - J Neural Eng. 2012 Feb;9(1):016004
– reference: 9865889 - IEEE Trans Rehabil Eng. 1998 Dec;6(4):415-23
– reference: 21369351 - Front Neurosci. 2011 Feb 07;5:5
– reference: 24099944 - J Neural Eng. 2013 Dec;10(6):066003
– reference: 25588137 - J Neural Eng. 2015 Feb;12(1):016013
– reference: 22833713 - Front Neurosci. 2012 May 23;6:72
– reference: 23369924 - J Neural Eng. 2013 Apr;10(2):026001
– reference: 21934188 - J Neural Eng. 2011 Oct;8(5):056016
– reference: 24808413 - IEEE Trans Neural Syst Rehabil Eng. 2014 Jul;22(4):837-46
– reference: 23366432 - Conf Proc IEEE Eng Med Biol Soc. 2012;2012:2497-500
– reference: 15813410 - IEEE Trans Neural Syst Rehabil Eng. 2005 Mar;13(1):89-98
– reference: 15188881 - IEEE Trans Biomed Eng. 2004 Jun;51(6):1073-6
– reference: 15188880 - IEEE Trans Biomed Eng. 2004 Jun;51(6):1067-72
– reference: 23466266 - Clin Neurophysiol. 2013 May;124(5):901-8
– reference: 20071274 - IEEE Trans Neural Syst Rehabil Eng. 2010 Apr;18(2):127-33
– reference: 23366267 - Conf Proc IEEE Eng Med Biol Soc. 2012;2012:1827-30
– reference: 22496763 - PLoS One. 2012;7(4):e33758
– reference: 20921326 - Neurorehabil Neural Repair. 2011 May;25(4):323-31
– reference: 24370570 - Neurorehabil Neural Repair. 2014 May;28(4):387-94
– reference: 21909321 - Front Neurosci. 2011 Aug 22;5:99
– reference: 26061188 - J Neural Eng. 2015 Aug;12(4):046018
– reference: 25775495 - IEEE Trans Neural Syst Rehabil Eng. 2015 Sep;23(5):910-20
– reference: 25068464 - PLoS One. 2014 Jul 28;9(7):e102504
– reference: 17271271 - Conf Proc IEEE Eng Med Biol Soc. 2004;6:4363-6
– reference: 22939456 - Clin Neurophysiol. 2013 Feb;124(2):306-14
– reference: 24167623 - PLoS One. 2013 Oct 22;8(10):e78432
– reference: 10896179 - IEEE Trans Rehabil Eng. 2000 Jun;8(2):174-9
– reference: 24500542 - Proc IEEE Int Conf Acoust Speech Signal Process. 2012;:null
– reference: 21278858 - Int J Hum Comput Interact. 2011 Jan 1;27(1):69-84
– reference: 23429035 - J Neural Eng. 2013 Apr;10(2):026012
– reference: 24760927 - IEEE Trans Neural Syst Rehabil Eng. 2014 May;22(3):678-84
– reference: 22510955 - IEEE Trans Neural Syst Rehabil Eng. 2012 Jul;20(4):584-94
– reference: 25686293 - J Neural Eng. 2015 Apr;12(2):026007
SSID ssj0031790
Score 2.3459644
SecondaryResourceType review_article
Snippet The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 031002
SubjectTerms Algorithms
Brain-Computer Interfaces - classification
Communication Aids for Disabled
Electroencephalography
Humans
Language
Models, Theoretical
Natural Language Processing
Title Integrating language models into classifiers for BCI communication: a review
URI https://www.ncbi.nlm.nih.gov/pubmed/27153565
https://www.proquest.com/docview/1789047836
Volume 13
WOSCitedRecordID wos000375701200002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA7qevDia32sLyKIt9BNm6SpF1kXFxd02YPC3kqapLAH29Wugv_eSdqqF0Hw0kOhpQzTyTePbz6ELqjOZGL7hgjGDWHGQhykkSFhoizVfSNkrrzYRDyZyNksmTYFt6oZq2xjog_UptSuRh5Qx9hkjnNwvXghTjXKdVcbCY1V1IkAyjivjmdfXYTIbZ-qCZGUAHQOWwYPJH3NPdEPaBREgVuQ6Ssrv6BMf9qMtv77ndtos8GZeFA7xg5ascUu6g4KyLGfP_Al9pOfvqTeRffjZmcEHGO4LWBir5FT4XmxLLF2GHueO9lsDCgX3wzHWP-kllxhhWsWzB56Gt0-Du9Io7JANEC9JeEmMXHfqCQUUWbCWCjLRUa5NDTjsZJCUS1izTMAJ4YybTnLIbGFyCAjKrQJ99FaURb2EGGquMkTCi9hmlErpTUy1CZnUmVMJ6qHzlubpeDFrjWhClu-Vem31XrooDZ8uqjXbaRhDFEZcOfRH54-RhuAaEQ9y3WCOjn8w_YUrev35bx6PfPuAdfJ9OETq1TD4Q
linkProvider ProQuest
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=Integrating+language+models+into+classifiers+for+BCI+communication%3A+a+review&rft.jtitle=Journal+of+neural+engineering&rft.au=Speier%2C+W&rft.au=Arnold%2C+C&rft.au=Pouratian%2C+N&rft.date=2016-06-01&rft.eissn=1741-2552&rft.volume=13&rft.issue=3&rft.spage=031002&rft_id=info:doi/10.1088%2F1741-2560%2F13%2F3%2F031002&rft_id=info%3Apmid%2F27153565&rft_id=info%3Apmid%2F27153565&rft.externalDocID=27153565
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1741-2552&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1741-2552&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1741-2552&client=summon