Low-quality training data detection method of EEG signals for motor imagery BCI system
The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects’ physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG)...
Saved in:
| Published in | Journal of neuroscience methods Vol. 376; p. 109607 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Netherlands
Elsevier B.V
01.07.2022
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0165-0270 1872-678X 1872-678X |
| DOI | 10.1016/j.jneumeth.2022.109607 |
Cover
Loading…
| Abstract | The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects’ physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system.
In order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method.
In order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1).
This paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system.
•A low-quality data detection method is proposed to screen low-quality training samples caused by different factors.•The possibility of reusing low-quality samples is studied.•An online asynchronous MI-BCI system is designed and implemented. |
|---|---|
| AbstractList | The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects' physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system.
In order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method.
In order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1).
This paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system. The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects' physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system.BACKGROUNDThe design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects' physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system.In order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method.NEW METHODIn order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method.In order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1).RESULTIn order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1).This paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system.CONCLUSIONThis paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system. The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects’ physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system. In order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method. In order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1). This paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system. •A low-quality data detection method is proposed to screen low-quality training samples caused by different factors.•The possibility of reusing low-quality samples is studied.•An online asynchronous MI-BCI system is designed and implemented. |
| ArticleNumber | 109607 |
| Author | Ouyang, Rui Jin, Zihao Wu, Xiaopei Tang, Shuhao Fan, Cunhang |
| Author_xml | – sequence: 1 givenname: Rui surname: Ouyang fullname: Ouyang, Rui organization: Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601, China – sequence: 2 givenname: Zihao surname: Jin fullname: Jin, Zihao organization: Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601, China – sequence: 3 givenname: Shuhao surname: Tang fullname: Tang, Shuhao organization: Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601, China – sequence: 4 givenname: Cunhang surname: Fan fullname: Fan, Cunhang email: cunhang.fan@ahu.edu.cn organization: Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601, China – sequence: 5 givenname: Xiaopei surname: Wu fullname: Wu, Xiaopei email: wxp2001@ahu.edu.cn organization: Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei 230601, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35483505$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkcFuGyEQhlGVqnHSvkLEsZd1WfCyIPXQ1nKTSJZ6aaveEIbBxdqFBNhUfvuycnzJJZdBGn3_zOjjCl2EGAChm5YsW9LyT4flIcA0Qvm7pITS2pSc9G_QohU9bXgv_lygRQW7htCeXKKrnA-EkJUk_B26ZN1KsI50C_R7G_81j5MefDnikrQPPuyx1UVjCwVM8THgeU20ODq82dzi7PdBDxm7mPAYS61-1HtIR_xtfY_zMRcY36O3rjLw4fm9Rr--b36u75rtj9v79ddtYxgXpdm1TGrGGJVUM2251b0zjtN-JVnrOiuEcWBlL63gdmep1SBdy_oVM0QQ1rFr9PE09yHFxwlyUaPPBoZBB4hTVpR3glLJhazozTM67Uaw6iHVs9NRnV1U4PMJMCnmnMAp44ueBcxeBtUSNatXB3VWr2b16qS-xvmL-HnDq8EvpyBUUU8eksrGQzBgfaofoGz0r434D0OXoeQ |
| CitedBy_id | crossref_primary_10_1016_j_neuroimage_2024_120906 crossref_primary_10_3390_electronics13142767 crossref_primary_10_1016_j_jneumeth_2023_109806 crossref_primary_10_3390_s24010149 |
| Cites_doi | 10.1109/TIM.2019.2920186 10.1016/S0013-4694(97)00022-2 10.1109/MSP.2016.2521870 10.1109/TIM.2017.2759398 10.1109/TSMC.2019.2955478 10.1109/ACCESS.2019.2936434 10.1109/JSEN.2018.2872623 10.1016/j.eswa.2018.08.031 10.1016/0165-1684(94)90029-9 10.1109/TIM.2016.2608479 10.1109/TIM.2021.3051996 10.1109/TBME.2014.2358536 10.1016/j.neulet.2017.06.044 10.1088/1741-2552/aadea0 10.1109/JBHI.2019.2920381 10.1109/78.554307 10.1109/TNSRE.2022.3140772 10.1109/86.895946 10.1109/MCI.2015.2501545 10.3389/fnins.2012.00039 10.1109/TBME.2009.2032162 10.1109/TBME.2010.2082539 10.1088/1741-2552/ab0ab5 10.1109/TIM.2017.2775358 10.1109/TPAMI.2014.2330598 10.1016/j.neunet.2018.02.011 10.1016/S0893-6080(00)00026-5 10.1016/j.measurement.2021.109280 10.1162/089976699300016719 10.1088/1741-2552/aba162 10.1109/JBHI.2019.2922976 10.1016/j.jneumeth.2022.109502 10.1088/1741-2560/4/2/R03 10.1016/j.neuroimage.2005.05.032 10.1002/hbm.23730 10.1016/j.bspc.2020.102152 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. Copyright © 2022 Elsevier B.V. All rights reserved. |
| Copyright_xml | – notice: 2022 Elsevier B.V. – notice: Copyright © 2022 Elsevier B.V. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1016/j.jneumeth.2022.109607 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Anatomy & Physiology |
| EISSN | 1872-678X |
| ExternalDocumentID | 35483505 10_1016_j_jneumeth_2022_109607 S0165027022001340 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5RE 7-5 71M 8P~ 9JM AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAXLA AAXUO ABCQJ ABFNM ABFRF ABJNI ABMAC ABYKQ ACDAQ ACGFO ACGFS ACIUM ACRLP ADBBV ADEZE AEBSH AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGUBO AGWIK AGYEJ AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AXJTR BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IHE J1W K-O KOM L7B M2V M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SPCBC SSN SSZ T5K ~G- .55 .GJ 29L 53G 5VS AAQFI AAQXK AATTM AAXKI AAYWO AAYXX ABWVN ABXDB ACRPL ACVFH ADCNI ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGHFR AGQPQ AGRNS AHHHB AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BNPGV CITATION EJD FEDTE FGOYB G-2 HMQ HVGLF HZ~ R2- RIG SEW SNS SSH WUQ X7M ZGI NPM 7X8 |
| ID | FETCH-LOGICAL-c368t-b139a333292a3ad6da7fcf6274931f5d88cfed979d86dbd2dae9f13743c080353 |
| IEDL.DBID | .~1 |
| ISSN | 0165-0270 1872-678X |
| IngestDate | Thu Jul 10 23:36:09 EDT 2025 Thu Apr 03 07:06:54 EDT 2025 Thu Apr 24 22:57:49 EDT 2025 Tue Jul 01 02:57:16 EDT 2025 Fri Feb 23 02:39:01 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Motor imagery (MI) Electroencephalogram (EEG) Independent component analysis (ICA) Brain computer interface (BCI) |
| Language | English |
| License | Copyright © 2022 Elsevier B.V. All rights reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c368t-b139a333292a3ad6da7fcf6274931f5d88cfed979d86dbd2dae9f13743c080353 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 35483505 |
| PQID | 2658229689 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2658229689 pubmed_primary_35483505 crossref_citationtrail_10_1016_j_jneumeth_2022_109607 crossref_primary_10_1016_j_jneumeth_2022_109607 elsevier_sciencedirect_doi_10_1016_j_jneumeth_2022_109607 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-07-01 |
| PublicationDateYYYYMMDD | 2022-07-01 |
| PublicationDate_xml | – month: 07 year: 2022 text: 2022-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Journal of neuroscience methods |
| PublicationTitleAlternate | J Neurosci Methods |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Hyvarinen, Oja (bib20) 2000; 13 McFarland, McCane, David, Wolpaw (bib28) 1997; 103 Zhuang, Geng, Yin (bib47) 2019; 51 Saha, Sarker, Abdullah Al Shiam, Rahoman (bib35) 2020 Witteveen, Pradhapan, Mihajlović (bib38) 2019; 24 Bashashati, Fatourechi, Ward, Birch (bib4) 2007; 4 Dose, Moller, Iversen, Puthusserypady (bib13) 2018; 114 Chen, Liu, Tao, Li, Lee, Liu, Chen, Cheng, McKeown, Wang (bib7) 2019; 69 Wu, X., Lv, Z., 2022, Motor imagery eeg data set. [DB/OL]. 〈http://iiphci.ahu.edu.cn/toeeg/〉. Chen, Peng, Yu, Wang (bib8) 2017; 66 R. , Leeb , C. , Brunner , G. , MullerPutz , A. , Schlogl , G. , Pfurtscheller, Bci competition 2008 - graz data set b. [EB/OL].〈http://www.bbci.de/competition/iv/desc_2b.pdf/〉. Ravi, Lu, Pearce, Jiang (bib33) 2022; 30 Zhang, Wang, Gao, Hong, Gao (bib43) 2007 Lee, Girolami, Sejnowski (bib23) 1999; 11 Yijun Wang, Tzyyping (bib42) 2012; 7 Craik, He, Contrerasvidal (bib12) 2019; 16 Jayaram, Alamgir, Altun, Schlkopf, Grosse-Wentrup (bib21) 2015; 11 Anbarasan, GomezCarmona, Mahendran (bib1) 2022 Arpaia, De Benedetto, Duraccio (bib3) 2021; 177 Lotte, Guan (bib24) 2011; 58 Maddirala, Shaik (bib26) 2017; 67 Chen, Chen, Zhang, Wang (bib6) 2018; 19 Ma, Dong, Lin, Ma, Jia, Chen, Xiao, Qi (bib25) 2022 Chen, Xu, Liu, McKeown, Wang (bib10) 2017; 67 Belouchrani, Abedmeraim, Cardoso, Moulines (bib5) 1997; 45 Gubert, Costa, Silva, Trofino-Neto (bib19) 2020; 62 Jayaram, Barachant (bib22) 2018; 15 Ang, Chin, Wang, Guan, Zhang (bib2) 2012; 6 Chen, Wang, McKeown (bib9) 2016; 33 Zhou, Wu, Lv, Zhang, Guo (bib46) 2016; 11 Feng, Yin, Jin, Saab, Daly, Wang, Hu, Cichocki (bib15) 2018; 102 Ramoser, Muller-Gerking (bib32) 2000; 8 Wu, Zhou, Lv, Zhang (bib41) 2020; 24 Gaur, Gupta, Chowdhury, McCreadie, Pachori, Wang (bib17) 2021; 70 Parra, Spence, Gerson, Sajda (bib30) 2005; 28 Wu, Chen, Gao, Li, Brown, Gao (bib39) 2015; 37 Hu, zhang, Wu, X (bib29) 2017; 34 Safitri, Djamal, Nugraha (bib34) 2020 Comon (bib11) 1994; 36 Frolich, Winkler, Müller, Samek (bib16) 2015 Mane, Chouhan, Guan (bib27) 2020; 17 Fedosov, Levadniy, Dmitriev, Nikolaev (bib14) 2020 Schirrmeister, Springenberg, Fiederer, Glasstetter, Eggensperger, Tangermann, Hutter, Burgard, Ball (bib36) 2017; 38 Zhang, Zheng, Wang, Wang, Ma, Zhang, Xu, Li, Zhang (bib44) 2017; 655 Tomida, Tanaka, Ono, Yamagishi, Higashi (bib37) 2015; 62 Gouypailler, Congedo, Brunner, Jutten, Pfurtscheller (bib18) 2010; 57 Zheng, Zhang, Wang, Wang, Deng, Zhang, Li, Wang (bib45) 2019; 7 Zhuang (10.1016/j.jneumeth.2022.109607_bib47) 2019; 51 Lotte (10.1016/j.jneumeth.2022.109607_bib24) 2011; 58 Chen (10.1016/j.jneumeth.2022.109607_bib10) 2017; 67 Frolich (10.1016/j.jneumeth.2022.109607_bib16) 2015 Jayaram (10.1016/j.jneumeth.2022.109607_bib22) 2018; 15 Lee (10.1016/j.jneumeth.2022.109607_bib23) 1999; 11 Parra (10.1016/j.jneumeth.2022.109607_bib30) 2005; 28 Gubert (10.1016/j.jneumeth.2022.109607_bib19) 2020; 62 Feng (10.1016/j.jneumeth.2022.109607_bib15) 2018; 102 Zheng (10.1016/j.jneumeth.2022.109607_bib45) 2019; 7 Zhou (10.1016/j.jneumeth.2022.109607_bib46) 2016; 11 Anbarasan (10.1016/j.jneumeth.2022.109607_bib1) 2022 Ramoser (10.1016/j.jneumeth.2022.109607_bib32) 2000; 8 10.1016/j.jneumeth.2022.109607_bib31 Mane (10.1016/j.jneumeth.2022.109607_bib27) 2020; 17 Zhang (10.1016/j.jneumeth.2022.109607_bib43) 2007 Witteveen (10.1016/j.jneumeth.2022.109607_bib38) 2019; 24 Yijun Wang (10.1016/j.jneumeth.2022.109607_bib42) 2012; 7 Tomida (10.1016/j.jneumeth.2022.109607_bib37) 2015; 62 Belouchrani (10.1016/j.jneumeth.2022.109607_bib5) 1997; 45 Chen (10.1016/j.jneumeth.2022.109607_bib6) 2018; 19 Ma (10.1016/j.jneumeth.2022.109607_bib25) 2022 Schirrmeister (10.1016/j.jneumeth.2022.109607_bib36) 2017; 38 Arpaia (10.1016/j.jneumeth.2022.109607_bib3) 2021; 177 Wu (10.1016/j.jneumeth.2022.109607_bib39) 2015; 37 Chen (10.1016/j.jneumeth.2022.109607_bib7) 2019; 69 Saha (10.1016/j.jneumeth.2022.109607_bib35) 2020 McFarland (10.1016/j.jneumeth.2022.109607_bib28) 1997; 103 Chen (10.1016/j.jneumeth.2022.109607_bib9) 2016; 33 Gouypailler (10.1016/j.jneumeth.2022.109607_bib18) 2010; 57 Fedosov (10.1016/j.jneumeth.2022.109607_bib14) 2020 Safitri (10.1016/j.jneumeth.2022.109607_bib34) 2020 Ravi (10.1016/j.jneumeth.2022.109607_bib33) 2022; 30 Dose (10.1016/j.jneumeth.2022.109607_bib13) 2018; 114 Ang (10.1016/j.jneumeth.2022.109607_bib2) 2012; 6 Chen (10.1016/j.jneumeth.2022.109607_bib8) 2017; 66 Craik (10.1016/j.jneumeth.2022.109607_bib12) 2019; 16 Hyvarinen (10.1016/j.jneumeth.2022.109607_bib20) 2000; 13 Bashashati (10.1016/j.jneumeth.2022.109607_bib4) 2007; 4 Gaur (10.1016/j.jneumeth.2022.109607_bib17) 2021; 70 10.1016/j.jneumeth.2022.109607_bib40 Wu (10.1016/j.jneumeth.2022.109607_bib41) 2020; 24 Comon (10.1016/j.jneumeth.2022.109607_bib11) 1994; 36 Zhang (10.1016/j.jneumeth.2022.109607_bib44) 2017; 655 Hu (10.1016/j.jneumeth.2022.109607_bib29) 2017; 34 Maddirala (10.1016/j.jneumeth.2022.109607_bib26) 2017; 67 Jayaram (10.1016/j.jneumeth.2022.109607_bib21) 2015; 11 |
| References_xml | – volume: 58 start-page: 355 year: 2011 end-page: 362 ident: bib24 article-title: Regularizing common spatial patterns to improve bci designs: Unified theory and new algorithms publication-title: IEEE Trans. Biomed. Eng. – volume: 34 start-page: 106 year: 2017 end-page: 114 ident: bib29 article-title: Online brain computer interface system based on independent component analysis publication-title: J. Biomed. Eng. – volume: 16 year: 2019 ident: bib12 article-title: Deep learning for electroencephalogram (eeg) classification tasks: a review publication-title: J. Neural Eng. – volume: 28 start-page: 326 year: 2005 end-page: 341 ident: bib30 article-title: Recipes for the linear analysis of eeg publication-title: NeuroImage – volume: 4 start-page: R32 year: 2007 ident: bib4 article-title: A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals publication-title: J. Neural Eng. – volume: 69 start-page: 2105 year: 2019 end-page: 2119 ident: bib7 article-title: Remae: User-friendly toolbox for removing muscle artifacts from eeg publication-title: IEEE Trans. Instrum. Meas. – volume: 24 start-page: 775 year: 2020 end-page: 787 ident: bib41 article-title: To explore the potentials of independent component analysis in brain-computer interface of motor imagery publication-title: IEEE J. Biomed. Health Inform. – volume: 177 year: 2021 ident: bib3 article-title: Design, implementation, and metrological characterization of a wearable, integrated ar-bci hands-free system for health 4.0 monitoring publication-title: Measurement – volume: 103 start-page: 386 year: 1997 end-page: 394 ident: bib28 article-title: Spatial filter selection for eeg-based communication publication-title: Electroencephalogr. Clin. Neurophysiol. – volume: 33 start-page: 86 year: 2016 end-page: 107 ident: bib9 article-title: Joint blind source separation for neurophysiological data analysis: Multiset and multimodal methods publication-title: IEEE Signal Process. Mag. – start-page: 69 year: 2020 end-page: 72 ident: bib14 article-title: Independent component analysis for different movements detection in bci application based on sensorimotor rhythms publication-title: 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) – volume: 19 start-page: 8420 year: 2018 end-page: 8431 ident: bib6 article-title: A novel eemd-cca approach to removing muscle artifacts for pervasive eeg publication-title: IEEE Sens. J. – volume: 15 year: 2018 ident: bib22 article-title: Moabb: Trustworthy algorithm benchmarking for bcis publication-title: J. Neural Eng. – volume: 62 start-page: 258 year: 2015 end-page: 267 ident: bib37 article-title: Active data selection for motor imagery eeg classification publication-title: IEEE Trans. Bio-Med. Eng. – reference: Wu, X., Lv, Z., 2022, Motor imagery eeg data set. [DB/OL]. 〈http://iiphci.ahu.edu.cn/toeeg/〉. – volume: 37 start-page: 639 year: 2015 end-page: 653 ident: bib39 article-title: Probabilistic common spatial patterns for multichannel eeg analysis publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 66 start-page: 1770 year: 2017 end-page: 1779 ident: bib8 article-title: Independent vector analysis applied to remove muscle artifacts in eeg data publication-title: IEEE Trans. Instrum. Meas. – year: 2022 ident: bib25 article-title: A classification algorithm of an ssvep brain-computer interface based on cca fusion wavelet coefficients publication-title: J. Neurosci. Methods – reference: R. , Leeb , C. , Brunner , G. , MullerPutz , A. , Schlogl , G. , Pfurtscheller, Bci competition 2008 - graz data set b. [EB/OL].〈http://www.bbci.de/competition/iv/desc_2b.pdf/〉. – volume: 51 start-page: 5392 year: 2019 end-page: 5404 ident: bib47 article-title: Ensemble learning based brain-computer interface system for ground vehicle control publication-title: IEEE Trans. Syst., Man, Cybern.: Syst. – volume: 6 year: 2012 ident: bib2 article-title: Filter bank common spatial pattern algorithm on bci competition iv datasets 2a and 2b publication-title: Front. Neurosci. – volume: 57 start-page: 469 year: 2010 end-page: 478 ident: bib18 article-title: Nonstationary brain source separation for multiclass motor imagery publication-title: IEEE Trans. Biomed. Eng. – volume: 11 year: 2016 ident: bib46 article-title: A fully automated trial selection method for optimization of motor imagery based brain-computer interface publication-title: PloS One – volume: 45 start-page: 434 year: 1997 end-page: 444 ident: bib5 article-title: A blind source separation technique using second-order statistics publication-title: IEEE Trans. Signal Process. – volume: 114 start-page: 532 year: 2018 end-page: 542 ident: bib13 article-title: An end-to-end deep learning approach to mi-eeg signal classification for bcis publication-title: Expert Syst. Appl. – volume: 30 start-page: 85 year: 2022 end-page: 95 ident: bib33 article-title: Enhanced system robustness of asynchronous bci in augmented reality using steady-state motion visual evoked potential publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – start-page: 18 year: 2020 ident: bib35 article-title: Motor imagery eeg signal classification using mwt-csp for online bci implementation publication-title: Int. J. Comput. Sci. Inf. Secur. (IJCSIS) – volume: 62 year: 2020 ident: bib19 article-title: The performance impact of data augmentation in csp-based motor-imagery systems for bci applications publication-title: Biomed. Signal Process. Control – volume: 11 start-page: 417 year: 1999 end-page: 441 ident: bib23 article-title: Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources publication-title: Neural Comput. – volume: 36 start-page: 287 year: 1994 end-page: 314 ident: bib11 article-title: Independent component analysis, a new concept? publication-title: Signal Process. – volume: 11 start-page: 20 year: 2015 end-page: 31 ident: bib21 article-title: Transfer learning in brain-computer interfaces publication-title: IEEE Comput. Intell. Mag. – volume: 67 start-page: 359 year: 2017 end-page: 370 ident: bib10 article-title: The use of multivariate emd and cca for denoising muscle artifacts from few-channel eeg recordings publication-title: IEEE Trans. Instrum. Meas. – volume: 17 year: 2020 ident: bib27 article-title: Bci for stroke rehabilitation: motor and beyond publication-title: J. Neural Eng. – start-page: 118 year: 2020 end-page: 122 ident: bib34 article-title: Brain-computer interface of motor imagery using ica and recurrent neural networks publication-title: 2020 3rd International Conference on Computer and Informatics Engineering (IC2IE) – start-page: 1 year: 2022 end-page: 27 ident: bib1 article-title: Human taste-perception: Brain computer interface (bci) and its application as an engineering tool for taste-driven sensory studies publication-title: Food Eng. Rev. – start-page: 2007 year: 2007 ident: bib43 article-title: An algorithm for idle-state detection in motor-imagery-based brain-computer interface publication-title: Comput. Intell. Neurosci. – start-page: 1942 year: 2015 end-page: 1945 ident: bib16 article-title: Investigating effects of different artefact types on motor imagery bci publication-title: Eng. Med. Biol. Soc. – volume: 8 start-page: 441 year: 2000 end-page: 446 ident: bib32 article-title: Optimal spatial filtering of single trial eeg during imagined hand movement publication-title: IEEE Trans. Rehabil. Eng. – volume: 67 start-page: 382 year: 2017 end-page: 393 ident: bib26 article-title: Separation of sources from single-channel eeg signals using independent component analysis publication-title: IEEE Trans. Instrum. Meas. – volume: 38 start-page: 5391 year: 2017 end-page: 5420 ident: bib36 article-title: Deep learning with convolutional neural networks for eeg decoding and visualization publication-title: Hum. Brain Mapp. – volume: 24 start-page: 735 year: 2019 end-page: 746 ident: bib38 article-title: Comparison of a pragmatic and regression approach for wearable eeg signal quality assessment publication-title: IEEE J. Biomed. Health Inform. – volume: 70 start-page: 1 year: 2021 end-page: 9 ident: bib17 article-title: A sliding window common spatial pattern for enhancing motor imagery classification in eeg-bci publication-title: IEEE Trans. Instrum. Meas. – volume: 655 start-page: 35 year: 2017 end-page: 40 ident: bib44 article-title: Application of a common spatial pattern-based algorithm for an fnirs-based motor imagery brain-computer interface publication-title: Neurosci. Lett. – volume: 102 start-page: 87 year: 2018 end-page: 95 ident: bib15 article-title: Towards correlation-based time window selection method for motor imagery bcis publication-title: Neural Netw. – volume: 7 start-page: 120603 year: 2019 end-page: 120615 ident: bib45 article-title: Resting-state-based spatial filtering for an fnirs-based motor imagery brain-computer interface publication-title: IEEE Access – volume: 7 year: 2012 ident: bib42 article-title: Translation of eeg spatial filters from resting to motor imagery using independent component analysis publication-title: PLOS ONE – volume: 13 start-page: 411 year: 2000 end-page: 430 ident: bib20 article-title: Independent component analysis: algorithms and applications publication-title: Neural Netw. – start-page: 69 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib14 article-title: Independent component analysis for different movements detection in bci application based on sensorimotor rhythms – start-page: 18 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib35 article-title: Motor imagery eeg signal classification using mwt-csp for online bci implementation publication-title: Int. J. Comput. Sci. Inf. Secur. (IJCSIS) – volume: 69 start-page: 2105 year: 2019 ident: 10.1016/j.jneumeth.2022.109607_bib7 article-title: Remae: User-friendly toolbox for removing muscle artifacts from eeg publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2019.2920186 – volume: 103 start-page: 386 year: 1997 ident: 10.1016/j.jneumeth.2022.109607_bib28 article-title: Spatial filter selection for eeg-based communication publication-title: Electroencephalogr. Clin. Neurophysiol. doi: 10.1016/S0013-4694(97)00022-2 – volume: 33 start-page: 86 year: 2016 ident: 10.1016/j.jneumeth.2022.109607_bib9 article-title: Joint blind source separation for neurophysiological data analysis: Multiset and multimodal methods publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2016.2521870 – volume: 67 start-page: 359 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib10 article-title: The use of multivariate emd and cca for denoising muscle artifacts from few-channel eeg recordings publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2759398 – volume: 51 start-page: 5392 year: 2019 ident: 10.1016/j.jneumeth.2022.109607_bib47 article-title: Ensemble learning based brain-computer interface system for ground vehicle control publication-title: IEEE Trans. Syst., Man, Cybern.: Syst. doi: 10.1109/TSMC.2019.2955478 – volume: 7 start-page: 120603 year: 2019 ident: 10.1016/j.jneumeth.2022.109607_bib45 article-title: Resting-state-based spatial filtering for an fnirs-based motor imagery brain-computer interface publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2936434 – volume: 19 start-page: 8420 year: 2018 ident: 10.1016/j.jneumeth.2022.109607_bib6 article-title: A novel eemd-cca approach to removing muscle artifacts for pervasive eeg publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2018.2872623 – volume: 114 start-page: 532 year: 2018 ident: 10.1016/j.jneumeth.2022.109607_bib13 article-title: An end-to-end deep learning approach to mi-eeg signal classification for bcis publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2018.08.031 – volume: 36 start-page: 287 year: 1994 ident: 10.1016/j.jneumeth.2022.109607_bib11 article-title: Independent component analysis, a new concept? publication-title: Signal Process. doi: 10.1016/0165-1684(94)90029-9 – start-page: 2007 year: 2007 ident: 10.1016/j.jneumeth.2022.109607_bib43 article-title: An algorithm for idle-state detection in motor-imagery-based brain-computer interface publication-title: Comput. Intell. Neurosci. – volume: 34 start-page: 106 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib29 article-title: Online brain computer interface system based on independent component analysis publication-title: J. Biomed. Eng. – volume: 66 start-page: 1770 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib8 article-title: Independent vector analysis applied to remove muscle artifacts in eeg data publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2016.2608479 – volume: 70 start-page: 1 year: 2021 ident: 10.1016/j.jneumeth.2022.109607_bib17 article-title: A sliding window common spatial pattern for enhancing motor imagery classification in eeg-bci publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2021.3051996 – volume: 62 start-page: 258 year: 2015 ident: 10.1016/j.jneumeth.2022.109607_bib37 article-title: Active data selection for motor imagery eeg classification publication-title: IEEE Trans. Bio-Med. Eng. doi: 10.1109/TBME.2014.2358536 – volume: 655 start-page: 35 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib44 article-title: Application of a common spatial pattern-based algorithm for an fnirs-based motor imagery brain-computer interface publication-title: Neurosci. Lett. doi: 10.1016/j.neulet.2017.06.044 – volume: 15 year: 2018 ident: 10.1016/j.jneumeth.2022.109607_bib22 article-title: Moabb: Trustworthy algorithm benchmarking for bcis publication-title: J. Neural Eng. doi: 10.1088/1741-2552/aadea0 – volume: 24 start-page: 735 year: 2019 ident: 10.1016/j.jneumeth.2022.109607_bib38 article-title: Comparison of a pragmatic and regression approach for wearable eeg signal quality assessment publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2920381 – volume: 7 year: 2012 ident: 10.1016/j.jneumeth.2022.109607_bib42 article-title: Translation of eeg spatial filters from resting to motor imagery using independent component analysis publication-title: PLOS ONE – volume: 45 start-page: 434 year: 1997 ident: 10.1016/j.jneumeth.2022.109607_bib5 article-title: A blind source separation technique using second-order statistics publication-title: IEEE Trans. Signal Process. doi: 10.1109/78.554307 – volume: 30 start-page: 85 year: 2022 ident: 10.1016/j.jneumeth.2022.109607_bib33 article-title: Enhanced system robustness of asynchronous bci in augmented reality using steady-state motion visual evoked potential publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2022.3140772 – volume: 8 start-page: 441 year: 2000 ident: 10.1016/j.jneumeth.2022.109607_bib32 article-title: Optimal spatial filtering of single trial eeg during imagined hand movement publication-title: IEEE Trans. Rehabil. Eng. doi: 10.1109/86.895946 – volume: 11 start-page: 20 year: 2015 ident: 10.1016/j.jneumeth.2022.109607_bib21 article-title: Transfer learning in brain-computer interfaces publication-title: IEEE Comput. Intell. Mag. doi: 10.1109/MCI.2015.2501545 – start-page: 118 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib34 article-title: Brain-computer interface of motor imagery using ica and recurrent neural networks – volume: 6 year: 2012 ident: 10.1016/j.jneumeth.2022.109607_bib2 article-title: Filter bank common spatial pattern algorithm on bci competition iv datasets 2a and 2b publication-title: Front. Neurosci. doi: 10.3389/fnins.2012.00039 – volume: 57 start-page: 469 year: 2010 ident: 10.1016/j.jneumeth.2022.109607_bib18 article-title: Nonstationary brain source separation for multiclass motor imagery publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2009.2032162 – volume: 58 start-page: 355 year: 2011 ident: 10.1016/j.jneumeth.2022.109607_bib24 article-title: Regularizing common spatial patterns to improve bci designs: Unified theory and new algorithms publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2010.2082539 – volume: 16 year: 2019 ident: 10.1016/j.jneumeth.2022.109607_bib12 article-title: Deep learning for electroencephalogram (eeg) classification tasks: a review publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ab0ab5 – volume: 67 start-page: 382 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib26 article-title: Separation of sources from single-channel eeg signals using independent component analysis publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2017.2775358 – volume: 37 start-page: 639 year: 2015 ident: 10.1016/j.jneumeth.2022.109607_bib39 article-title: Probabilistic common spatial patterns for multichannel eeg analysis publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2014.2330598 – volume: 102 start-page: 87 year: 2018 ident: 10.1016/j.jneumeth.2022.109607_bib15 article-title: Towards correlation-based time window selection method for motor imagery bcis publication-title: Neural Netw. doi: 10.1016/j.neunet.2018.02.011 – volume: 13 start-page: 411 year: 2000 ident: 10.1016/j.jneumeth.2022.109607_bib20 article-title: Independent component analysis: algorithms and applications publication-title: Neural Netw. doi: 10.1016/S0893-6080(00)00026-5 – volume: 177 year: 2021 ident: 10.1016/j.jneumeth.2022.109607_bib3 article-title: Design, implementation, and metrological characterization of a wearable, integrated ar-bci hands-free system for health 4.0 monitoring publication-title: Measurement doi: 10.1016/j.measurement.2021.109280 – volume: 11 start-page: 417 year: 1999 ident: 10.1016/j.jneumeth.2022.109607_bib23 article-title: Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources publication-title: Neural Comput. doi: 10.1162/089976699300016719 – volume: 17 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib27 article-title: Bci for stroke rehabilitation: motor and beyond publication-title: J. Neural Eng. doi: 10.1088/1741-2552/aba162 – volume: 24 start-page: 775 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib41 article-title: To explore the potentials of independent component analysis in brain-computer interface of motor imagery publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2922976 – year: 2022 ident: 10.1016/j.jneumeth.2022.109607_bib25 article-title: A classification algorithm of an ssvep brain-computer interface based on cca fusion wavelet coefficients publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2022.109502 – volume: 4 start-page: R32 year: 2007 ident: 10.1016/j.jneumeth.2022.109607_bib4 article-title: A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals publication-title: J. Neural Eng. doi: 10.1088/1741-2560/4/2/R03 – volume: 28 start-page: 326 year: 2005 ident: 10.1016/j.jneumeth.2022.109607_bib30 article-title: Recipes for the linear analysis of eeg publication-title: NeuroImage doi: 10.1016/j.neuroimage.2005.05.032 – volume: 38 start-page: 5391 year: 2017 ident: 10.1016/j.jneumeth.2022.109607_bib36 article-title: Deep learning with convolutional neural networks for eeg decoding and visualization publication-title: Hum. Brain Mapp. doi: 10.1002/hbm.23730 – ident: 10.1016/j.jneumeth.2022.109607_bib31 – start-page: 1942 year: 2015 ident: 10.1016/j.jneumeth.2022.109607_bib16 article-title: Investigating effects of different artefact types on motor imagery bci publication-title: Eng. Med. Biol. Soc. – ident: 10.1016/j.jneumeth.2022.109607_bib40 – volume: 11 year: 2016 ident: 10.1016/j.jneumeth.2022.109607_bib46 article-title: A fully automated trial selection method for optimization of motor imagery based brain-computer interface publication-title: PloS One – start-page: 1 year: 2022 ident: 10.1016/j.jneumeth.2022.109607_bib1 article-title: Human taste-perception: Brain computer interface (bci) and its application as an engineering tool for taste-driven sensory studies publication-title: Food Eng. Rev. – volume: 62 year: 2020 ident: 10.1016/j.jneumeth.2022.109607_bib19 article-title: The performance impact of data augmentation in csp-based motor-imagery systems for bci applications publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2020.102152 |
| SSID | ssj0004906 |
| Score | 2.3939636 |
| Snippet | The design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However,... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 109607 |
| SubjectTerms | Brain computer interface (BCI) Electroencephalogram (EEG) Independent component analysis (ICA) Motor imagery (MI) |
| Title | Low-quality training data detection method of EEG signals for motor imagery BCI system |
| URI | https://dx.doi.org/10.1016/j.jneumeth.2022.109607 https://www.ncbi.nlm.nih.gov/pubmed/35483505 https://www.proquest.com/docview/2658229689 |
| Volume | 376 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT-MwEB4hVkJcEFtehV1kJMQtlNqpYx-7VaE8LzzEzUpiW2oFKYJWqJf97TsTJ12QQBy4REoUK46_if1N_M0MwL7ncZo4lUfS5j6KtfIRznkqUlYpL532qqwNeHklB7fx2X3nfgF6dSwMySqruT_M6eVsXV1pVaPZehoOW9cUiHNE4VQkCxIx-e2UvQ5t-vDvf5lHrMv6mnQz7VcevYkSHh2OCjelSs3oJ3JOmZUklZX9eIH6jICWC9HxKqxUDJJ1Qyd_woIrGrDWLdB7fpyxA1ZqOsuf5Q1Yuqy2ztfg7mL8GoUQyhmrC0MwEogy6yalIKtgoZ40G3vW758w0nagdTLktQwRxePwkVJezNif3ikLOaDX4fa4f9MbRFVRhSgXUk2iDClfKoTgmqcitdKmic89VeDRou07CFHundWJtkrazHKbImBtgUSDcpKLjtiAxWJcuC1gNpHOpegyJXkcZyrJMod00bfj3GUIS9aETj2SJq8yjtP7PZhaWjYyNQKGEDABgSa05u2eQs6NL1voGijzznoMLgxftt2rkTX4adF-SVq48fTFcGRnnGupdBM2A-Tz_gj09ASyx-1vPHkHluksiH9_weLkeep-I8WZZLulDe_Cj-7p-eDqH0dz-zs |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3PT9swFH5CRWJc0Pgx6MbAk9BuWamdOvaxVGXtaHsZTNysJLalVpAi1gr1v-e9OGEggTjskkMSK44_5_l78ffeAzjxPE4Tp_JI2txHsVY-QpunImWV8tJpr8ragOOJHFzFv64712vQq2NhSFZZ2f5g00trXZ1pVaPZuptOW78pEOeUwqlIFiRi9NvXKTtV3ID17vBiMPkXHqnLEpt0P21Znj4LFJ79mBVuScWa0VXknJIrSaos-_oa9RYHLdei84-wVZFI1g393IY1V-zAbrdAB_p2xb6zUtZZ_i_fgY1xtXu-C39G84coRFGuWF0bgpFGlFm3KDVZBQslpdncs37_JyN5B05QhtSWIah4nN5S1osVO-sNWUgDvQdX5_3L3iCq6ipEuZBqEWXI-lIhBNc8FamVNk187qkIjxZt30GUcu-sTrRV0maW2xQxawvkGpSWXHTEJ2gU88IdALOJdC5FrynJ4zhTSZY5ZIy-HecuQ2SyJnTqkTR5lXSc3u_G1OqymakRMISACQg0ofXU7i6k3Xi3ha6BMi8mkMG14d2232pkDX5dtGWSFm6-_Gs4EjTOtVS6CfsB8qf-CHT2BBLIz__x5GP4MLgcj8xoOLn4Apt0JWiBD6GxuF-6r8h4FtlRNaMfAeCJ_ew |
| 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=Low-quality+training+data+detection+method+of+EEG+signals+for+motor+imagery+BCI+system&rft.jtitle=Journal+of+neuroscience+methods&rft.au=Ouyang%2C+Rui&rft.au=Jin%2C+Zihao&rft.au=Tang%2C+Shuhao&rft.au=Fan%2C+Cunhang&rft.date=2022-07-01&rft.issn=1872-678X&rft.eissn=1872-678X&rft.volume=376&rft.spage=109607&rft_id=info:doi/10.1016%2Fj.jneumeth.2022.109607&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0165-0270&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0165-0270&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0165-0270&client=summon |