Improving Performance of Devanagari Script Input-Based P300 Speller Using Deep Learning

The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowdi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on biomedical engineering Jg. 66; H. 11; S. 2992 - 3005
Hauptverfasser:	Kshirsagar, G. B., Londhe, N. D.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.11.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Adult Algorithms Artificial intelligence Artificial neural networks Brain modeling Brain-computer interface (BCI) Brain-Computer Interfaces Character recognition Communication Aids for Disabled Convolution Data acquisition deep convolution neural network (DCNN) Deep Learning Devanagari script (DS) EEG Electroencephalography Electroencephalography - methods Event-related potentials Event-Related Potentials, P300 - physiology Female Humans Information transfer Learning algorithms Machine learning Machine learning algorithms Male Middle Aged Neural networks P300 speller Signal Processing, Computer-Assisted stacked autoencoder (SAE) Support vector machines Target detection Training Young Adult
ISSN:	0018-9294, 1558-2531, 1558-2531
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques.
AbstractList	The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques.The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques. The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques.
Author	Londhe, N. D. Kshirsagar, G. B.
Author_xml	– sequence: 1 givenname: G. B. orcidid: 0000-0003-4388-8436 surname: Kshirsagar fullname: Kshirsagar, G. B. organization: National Institute of Technology Raipur – sequence: 2 givenname: N. D. orcidid: 0000-0002-6320-5746 surname: Londhe fullname: Londhe, N. D. email: nlondhe.ele@nitrr.ac.in organization: National Institute of Technology Raipur, Raipur, India
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/30307853$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1LJDEQhsOirKO7P2ARJOBlLz1WvrqTo1_rDowoqOwxZLqrJTKdbpNuYf_9ZpjRg4eFFKEqz5tU6j0ke6EPSMgPBnPGwJw9XtxezzkwPee6UsDlFzJjSumCK8H2yAzyUWG4kQfkMKWXnEoty6_kQICASisxI38W3RD7Nx-e6T3Gto-dCzXSvqVX-OaCe3bR04c6-mGkizBMY3HhEjb0XgDQhwHXa4z0KW30V4gDXaKLIWffyH7r1gm_7_Yj8vTr-vHyd7G8u1lcni-LWjI1FhKMNsCcqSSUHBoFrVmVoslRN7mErTKApnRNqQFqiUozx7BSK1CiraQ4Ij-39-ZfvE6YRtv5VOe2XMB-SpYzZowQXLGMnn5CX_ophtyd5XkceUFZZepkR02rDhs7RN-5-Ne-jywDbAvUsU8pYvuBMLAbW-zGFruxxe5syZrqk6b2oxt9H8bo_Pq_yuOt0iPix0ta6rKUWvwD4MWWbw
CODEN	IEBEAX
CitedBy_id	crossref_primary_10_1109_ACCESS_2020_2968717 crossref_primary_10_3390_s20040969 crossref_primary_10_1109_ACCESS_2023_3347336 crossref_primary_10_1109_LSP_2025_3597875 crossref_primary_10_1109_TCDS_2019_2942437 crossref_primary_10_1016_j_cmpb_2022_107324 crossref_primary_10_1109_TCDS_2021_3079712 crossref_primary_10_1109_TIM_2020_3011762 crossref_primary_10_1109_TSMC_2021_3051136 crossref_primary_10_1016_j_jneumeth_2021_109300 crossref_primary_10_4018_IJACI_300796 crossref_primary_10_1016_j_bspc_2023_104924 crossref_primary_10_1016_j_epsr_2020_106914 crossref_primary_10_1007_s00521_022_07518_5 crossref_primary_10_1007_s11220_023_00421_w crossref_primary_10_1109_TSMC_2022_3156861 crossref_primary_10_3389_fncom_2022_909553 crossref_primary_10_3390_app10051605 crossref_primary_10_1016_j_eswa_2020_113911 crossref_primary_10_1016_j_cmpb_2021_106487 crossref_primary_10_1177_1071181320641224 crossref_primary_10_1134_S0362119723600479 crossref_primary_10_3389_fnhum_2021_772837 crossref_primary_10_1038_s41598_024_77923_4 crossref_primary_10_1007_s11571_021_09768_w crossref_primary_10_1088_1741_2552_ab848b crossref_primary_10_1109_ACCESS_2023_3313260 crossref_primary_10_1109_ACCESS_2021_3051685
Cites_doi	10.1016/j.neucom.2015.02.057 10.1155/2016/2029791 10.1016/j.neulet.2009.06.045 10.1109/TBME.2004.827072 10.1016/j.neucom.2017.08.039 10.1109/TNSRE.2005.862695 10.1109/FUZZ-IEEE.2017.8015660 10.1016/j.jneumeth.2007.07.017 10.1109/ICEECCOT.2017.8284557 10.1109/ICABME.2015.7323272 10.1016/j.clinph.2010.01.030 10.1088/1741-2560/6/2/026003 10.1080/10447318.2011.622970 10.1016/j.neucom.2016.12.027 10.1109/TBME.2008.915728 10.1016/j.bspc.2014.12.007 10.1109/TPAMI.2016.2644615 10.1016/j.jneumeth.2014.04.009 10.1109/NER.2011.5910579 10.1111/j.1469-8986.1993.tb03209.x 10.1515/jaiscr-2015-0030 10.1016/j.bbe.2017.04.006 10.1109/ACCESS.2016.2614494 10.1016/j.clinph.2014.09.021 10.3389/fnins.2017.00302 10.1109/TPAMI.2010.125 10.1109/ICCV.2015.123 10.1109/TPAMI.2016.2577031 10.1080/10447318.2016.1203047 10.1109/IEMBS.2008.4649364 10.1038/nature14539 10.1016/j.ins.2017.04.012 10.1109/ICASSP.2013.6638312 10.1016/0013-4694(88)90149-6
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
DOI	10.1109/TBME.2018.2875024
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE Materials Research Database
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: RIE name: IEEE Electronic Library (IEL) - NZ 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	Medicine Engineering
EISSN	1558-2531
EndPage	3005
ExternalDocumentID	30307853 10_1109_TBME_2018_2875024 8486648
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: Department of Science and Technology grantid: SR/CSRI/38/2015 (G) funderid: 10.13039/501100010218 – fundername: Cognitive Science Research Initiative (CSRI)
GroupedDBID	--- -~X .55 .DC .GJ 0R~ 29I 4.4 53G 5GY 5RE 5VS 6IF 6IK 6IL 6IN 85S 97E AAJGR AARMG AASAJ AAWTH AAYJJ ABAZT ABJNI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT ACPRK ADZIZ AENEX AETIX AFFNX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CHZPO CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IEGSK IFIPE IFJZH IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RIL RNS TAE TN5 VH1 VJK X7M ZGI ZXP AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
ID	FETCH-LOGICAL-c415t-4098901a9740620d50f9b63db63cd406ef590e96ad6800c4e581a1e75b053f743
IEDL.DBID	RIE
ISICitedReferencesCount	40
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000502102200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9294 1558-2531
IngestDate	Sun Nov 09 10:39:15 EST 2025 Mon Jun 30 08:40:01 EDT 2025 Mon Jul 21 06:04:55 EDT 2025 Sat Nov 29 05:34:22 EST 2025 Tue Nov 18 21:27:19 EST 2025 Wed Aug 27 02:43:05 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	11
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c415t-4098901a9740620d50f9b63db63cd406ef590e96ad6800c4e581a1e75b053f743
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-4388-8436 0000-0002-6320-5746
PMID	30307853
PQID	2307307067
PQPubID	85474
PageCount	14
ParticipantIDs	proquest_journals_2307307067 crossref_primary_10_1109_TBME_2018_2875024 crossref_citationtrail_10_1109_TBME_2018_2875024 proquest_miscellaneous_2119933251 pubmed_primary_30307853 ieee_primary_8486648
PublicationCentury	2000
PublicationDate	2019-11-01
PublicationDateYYYYMMDD	2019-11-01
PublicationDate_xml	– month: 11 year: 2019 text: 2019-11-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on biomedical engineering
PublicationTitleAbbrev	TBME
PublicationTitleAlternate	IEEE Trans Biomed Eng
PublicationYear	2019
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	ref13 ref12 ref37 ref15 townsend (ref31) 2010; 121 ref36 ref14 rajpurkar (ref39) 2017 ref30 ref33 ref11 ref32 ref10 bengio (ref35) 2007 ref2 ref1 ref17 ref38 ref16 ref19 ref18 srivastava (ref42) 2014; 15 turnip (ref21) 2013; 2 ref23 ref20 ref22 dal (ref25) 0 li (ref24) 0 ref28 ref27 maddula (ref41) 0 ref29 nair (ref26) 0 ref8 ref7 ref9 ref3 ref6 ref5 ref40 abadi (ref44) 0; 16 vareka (ref4) 2017; 11 chollet (ref43) 2015 lecun (ref34) 2015; 521
References_xml	– start-page: 153 year: 2007 ident: ref35 article-title: Greedy layer wise training of deep networks publication-title: Advances in Neural Information Processing Systems 19 – ident: ref15 doi: 10.1016/j.neucom.2015.02.057 – ident: ref20 doi: 10.1155/2016/2029791 – ident: ref19 doi: 10.1016/j.neulet.2009.06.045 – ident: ref29 doi: 10.1109/TBME.2004.827072 – ident: ref1 doi: 10.1016/j.neucom.2017.08.039 – ident: ref22 doi: 10.1109/TNSRE.2005.862695 – year: 2015 ident: ref43 – ident: ref5 doi: 10.1109/FUZZ-IEEE.2017.8015660 – ident: ref13 doi: 10.1016/j.jneumeth.2007.07.017 – ident: ref2 doi: 10.1109/ICEECCOT.2017.8284557 – ident: ref9 doi: 10.1109/ICABME.2015.7323272 – volume: 121 start-page: 1109 year: 2010 ident: ref31 article-title: A novel P300-based brain-computer interface stimulus presentation paradigm: Moving beyond rows and columns publication-title: Clin Neurophysiol doi: 10.1016/j.clinph.2010.01.030 – ident: ref32 doi: 10.1088/1741-2560/6/2/026003 – ident: ref7 doi: 10.1080/10447318.2011.622970 – ident: ref36 doi: 10.1016/j.neucom.2016.12.027 – ident: ref23 doi: 10.1109/TBME.2008.915728 – ident: ref18 doi: 10.1016/j.bspc.2014.12.007 – volume: 2 start-page: 63 year: 2013 ident: ref21 article-title: P300 detection using a multilayer neural network classifier based on adaptive feature extraction publication-title: Int J Brain Cogn Sci – ident: ref37 doi: 10.1109/TPAMI.2016.2644615 – start-page: 18 year: 0 ident: ref41 article-title: Deep recurrent convolutional neural networks for classifying P300 BCI signals publication-title: Proc 7th Graz Brain-Comput Interface Conf – ident: ref16 doi: 10.1016/j.jneumeth.2014.04.009 – start-page: 807 year: 0 ident: ref26 article-title: Rectified linear units improve restricted Boltzmann machines publication-title: Proc 27th Int Conf Mach Learn – ident: ref14 doi: 10.1109/NER.2011.5910579 – ident: ref33 doi: 10.1111/j.1469-8986.1993.tb03209.x – volume: 15 start-page: 1929 year: 2014 ident: ref42 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – ident: ref8 doi: 10.1515/jaiscr-2015-0030 – ident: ref11 doi: 10.1016/j.bbe.2017.04.006 – ident: ref12 doi: 10.1109/ACCESS.2016.2614494 – ident: ref17 doi: 10.1016/j.clinph.2014.09.021 – volume: 11 start-page: 1 year: 2017 ident: ref4 article-title: Stacked autoencoders for the P300 component detection publication-title: Front Neurosci doi: 10.3389/fnins.2017.00302 – ident: ref3 doi: 10.1109/TPAMI.2010.125 – ident: ref27 doi: 10.1109/ICCV.2015.123 – ident: ref38 doi: 10.1109/TPAMI.2016.2577031 – year: 2017 ident: ref39 article-title: Cardiologist-level arrhythmia detection with convolutional neural networks – start-page: 4035 year: 0 ident: ref24 article-title: Single trial independent component analysis for P300 BCI system publication-title: Proc 31st Annu Int Conf IEEE EMBS – ident: ref10 doi: 10.1080/10447318.2016.1203047 – ident: ref30 doi: 10.1109/IEMBS.2008.4649364 – volume: 16 start-page: 265 year: 0 ident: ref44 article-title: TensorFlow: A system for large-scale machine learning publication-title: Proc USENIX Symp on Operating System Design and Implementation – start-page: 3145 year: 0 ident: ref25 article-title: A genetic algorithm for automatic feature extraction in P300 detection publication-title: Proc Int Joint Conf Neural Netw – volume: 521 start-page: 436 year: 2015 ident: ref34 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: ref40 doi: 10.1016/j.ins.2017.04.012 – ident: ref28 doi: 10.1109/ICASSP.2013.6638312 – ident: ref6 doi: 10.1016/0013-4694(88)90149-6
SSID	ssj0014846
Score	2.4736502
Snippet	The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	2992
SubjectTerms	Adult Algorithms Artificial intelligence Artificial neural networks Brain modeling Brain-computer interface (BCI) Brain-Computer Interfaces Character recognition Communication Aids for Disabled Convolution Data acquisition deep convolution neural network (DCNN) Deep Learning Devanagari script (DS) EEG Electroencephalography Electroencephalography - methods Event-related potentials Event-Related Potentials, P300 - physiology Female Humans Information transfer Learning algorithms Machine learning Machine learning algorithms Male Middle Aged Neural networks P300 speller Signal Processing, Computer-Assisted stacked autoencoder (SAE) Support vector machines Target detection Training Young Adult
Title	Improving Performance of Devanagari Script Input-Based P300 Speller Using Deep Learning
URI	https://ieeexplore.ieee.org/document/8486648 https://www.ncbi.nlm.nih.gov/pubmed/30307853 https://www.proquest.com/docview/2307307067 https://www.proquest.com/docview/2119933251
Volume	66
WOSCitedRecordID	wos000502102200001&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) - NZ customDbUrl: eissn: 1558-2531 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014846 issn: 0018-9294 databaseCode: RIE dateStart: 19640101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ZS8QwEB5URPTB-6gXEXwSV9NtmiaPHisKKgte-1a66VQE6S7rrr_fSZqtCir4UCht2obOTOabzAWwL5oZmthGtqIWtqh22NAZWa0iJJvZlpwzLr_i8Tq5vVWdjm5PwGGdC4OILvgMj-yp8-XnPTOyW2XHSigphZqEySRJqlyt2mMgVJWUw0MS4KYW3oMZcn18f3rTskFc6ojMA5qX-KaDXFOV3_Gl0zMXC_-b4SLMezzJTioGWIIJLJdh7kuVwWWYufH-8xV4qvcQWPszY4D1CnaOtrvyM1nO7M4tJOyq7I-GjVPScjlrR5yzO-uowQFzUQb0APaZr876vAoPF637s8uGb63QMKSxh2Q1akVIICNrgssmz2Ne6K6McjpMTpewiDVRT2a5JERpBMYqzEJM4i4JbUGoYw2myl6JG8CKrsxV1A25seXSpFEyE3EUC0HAEnWWB8DHPzs1vu64bX_xmjr7g-vU0ie19Ek9fQI4qB_pV0U3_hq8YulQD_QkCGB7TNHUi-Vb2nQrWkIaOoC9-jYJlPWSZCX2RjQmtDGNEeG-ANYrTqjfHdklkQDO5s_f3IJZmpmuUhW3YWo4GOEOTJv34cvbYJe4tqN2Hdd-AAdB40c
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT9swFD6CbhrsYeMyWDYGnsTTtIKdOK79ODYQiLaqRGG8RalzgpBQWvXC7-fYMRlI2yQeIkWJk1j5bJ_v-NwA9mWco02dZysa6ZJqi7bJSWuVgnRml3LO-viKq26n39fX12awBN-bWBhE9M5neOBOvS2_GNuF2yo71FIrJfUyvEqljEUdrdXYDKSuw3K4oCkcGxlsmIKbw-FR79i5cekDUhCoZ_KZFPJlVf7NML2kOXn_sj6uwbvAKNmPegiswxJWG_D2SZ7BDXjTCxb0Tfjd7CKwwZ-YATYu2S909ZVvSHdmF34pYWfVZDFvH5GcK9gg4ZxdOFMNTpn3M6AHcMJCftabD3B5cjz8edoOxRXalmT2nPRGo4kL5KRPcBXzIuWlGamkoMMWdAnL1BB-Ki8UcUorMdUiF9hJRzRtS-IdW9CqxhV-BFaOVKGTkeDWJUxTVqtcpglBRNQSTV5EwB9_dmZD5nFXAOMu8xoIN5nDJ3P4ZAGfCL41j0zqtBv_a7zpcGgaBggi2HlENAsTc5bFfk3rkIyO4Gtzm6aUs5PkFY4X1EY4r8aEmF8E2_VIaN6duEWRKM6nv39zD1ZOh71u1j3rn3-GVeqlqQMXd6A1ny7wC7y29_Pb2XTXj90HpdTlpg
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=Improving+Performance+of+Devanagari+Script+Input-Based+P300+Speller+Using+Deep+Learning&rft.jtitle=IEEE+transactions+on+biomedical+engineering&rft.au=Kshirsagar%2C+G.+B.&rft.au=Londhe%2C+N.+D.&rft.date=2019-11-01&rft.pub=IEEE&rft.issn=0018-9294&rft.volume=66&rft.issue=11&rft.spage=2992&rft.epage=3005&rft_id=info:doi/10.1109%2FTBME.2018.2875024&rft.externalDocID=8486648
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9294&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9294&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9294&client=summon