Method for exploratory cluster analysis and visualisation of single-trial ERP ensembles
The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data. We propose a complete pipeline for the cluster analysis of ERP...
Saved in:
| Published in | Journal of neuroscience methods Vol. 250; pp. 22 - 33 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Netherlands
30.07.2015
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data.
We propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA).
After validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.
Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation.
Given the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging. |
|---|---|
| AbstractList | The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data.
We propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA).
After validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.
Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation.
Given the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging. The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data.BACKGROUNDThe validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data.We propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA).NEW METHODWe propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA).After validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.RESULTSAfter validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation.COMPARISON WITH EXISTING METHOD(S)Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation.Given the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging.CONCLUSIONSGiven the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging. |
| Author | Nasuto, S.J. Williams, N.J. Saddy, J.D. |
| Author_xml | – sequence: 1 givenname: N.J. surname: Williams fullname: Williams, N.J. – sequence: 2 givenname: S.J. surname: Nasuto fullname: Nasuto, S.J. – sequence: 3 givenname: J.D. surname: Saddy fullname: Saddy, J.D. |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/25698176$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkMtO5DAQRS0EgubxC8jL2SRjO4kdS7NBiMdIjEAIBDvLsSuMW07cYzuI_nvSQG_YzKpqce4t1TlEu2MYAaFTSkpKKP-5LJcjTAPkvyUjtCkJKwkRO2hBW8EKLtrnXbSYwaYgTJADdJjSkhBSS8L30QFruGyp4Av09GeuCBb3IWJ4W_kQdQ5xjY2fUoaI9aj9Ork0Lxa_ujRp75LOLow49Di58cVDkaPTHl_c32EYEwydh3SM9nrtE5x8zSP0eHnxcH5d3Nxe_T4_uylMRWkuqqptOrC15rqrZc-tNqTpWttIW0nK6s4IBrITVtSWS1NZybQ0tmq57A0VpjpCPz57VzH8myBlNbhkwHs9QpiSorxtN2-LekZPv9CpG8CqVXSDjmu1lTEDvz4BE0NKEXplXP74NUftvKJEbdyrpdq6Vxv3ijA1u5_j_Ft8e-E_wXcrQ44m |
| CitedBy_id | crossref_primary_10_1049_htl_2017_0049 crossref_primary_10_1088_2057_1976_aaeeed crossref_primary_10_1016_j_cmpb_2018_06_011 crossref_primary_10_3389_fnins_2020_521595 crossref_primary_10_1016_j_neuroimage_2018_01_056 crossref_primary_10_1016_j_brainres_2018_09_004 crossref_primary_10_3389_fnhum_2019_00066 crossref_primary_10_1016_j_bbr_2020_113042 |
| Cites_doi | 10.1016/j.bandl.2005.05.001 10.1080/01969727408546059 10.1109/10.844236 10.1109/10.7271 10.1063/1.1505813 10.1055/s-0038-1634987 10.1016/S1388-2457(02)00365-6 10.1016/1350-4533(95)90380-T 10.1073/pnas.0505785103 10.1142/S0218001496000438 10.1016/S0168-5597(97)96681-8 10.1109/TBME.2004.826692 10.1111/1467-9868.00293 10.1038/scientificamerican0792-66 10.1016/S0031-3203(99)00137-5 10.1016/S0079-6123(06)59004-1 10.1016/0013-4694(95)98480-V 10.1109/72.554199 10.1109/TBME.1987.326024 10.1155/2011/965237 10.1109/10.605424 10.1016/0013-4694(88)90149-6 10.1016/j.clinph.2006.05.012 10.1007/s00422-004-0500-8 10.1207/s15516709cog0901_5 10.1109/T-C.1969.222678 10.1098/rspa.1998.0193 10.1162/089976699300016719 |
| ContentType | Journal Article |
| Copyright | Copyright © 2015 Elsevier B.V. All rights reserved. |
| Copyright_xml | – notice: Copyright © 2015 Elsevier B.V. All rights reserved. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.jneumeth.2015.02.007 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE 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 – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine Anatomy & Physiology |
| EISSN | 1872-678X |
| EndPage | 33 |
| ExternalDocumentID | 25698176 10_1016_j_jneumeth_2015_02_007 |
| Genre | Validation Studies Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- --K --M -~X .55 .GJ .~1 0R~ 1B1 1RT 1~. 1~5 29L 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXLA AAXUO AAYWO AAYXX ABCQJ ABFNM ABFRF ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFO ACGFS ACIUM ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO AEBSH AEFWE AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGWIK AGYEJ AHHHB AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CITATION CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HMQ HVGLF HZ~ IHE J1W K-O KOM L7B M2V M41 MO0 MOBAO N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SES SEW SNS SPCBC SSH SSN SSZ T5K WUQ X7M ZGI ~G- CGR CUY CVF ECM EFKBS EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c311t-3385bed4a6ab49f6dac05b8d59d39124bc72e9b7d74d69c3d92a9cd3869fc17c3 |
| ISSN | 0165-0270 1872-678X |
| IngestDate | Fri Jul 11 06:48:41 EDT 2025 Mon Jul 21 05:58:57 EDT 2025 Tue Jul 01 02:57:03 EDT 2025 Thu Apr 24 22:53:09 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Empirical Mode Decomposition k-means clustering Stability Index ERP cluster analysis Genetic Algorithms |
| Language | English |
| License | Copyright © 2015 Elsevier B.V. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c311t-3385bed4a6ab49f6dac05b8d59d39124bc72e9b7d74d69c3d92a9cd3869fc17c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3 |
| PMID | 25698176 |
| PQID | 1688004974 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | proquest_miscellaneous_1688004974 pubmed_primary_25698176 crossref_citationtrail_10_1016_j_jneumeth_2015_02_007 crossref_primary_10_1016_j_jneumeth_2015_02_007 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2015-07-30 |
| PublicationDateYYYYMMDD | 2015-07-30 |
| PublicationDate_xml | – month: 07 year: 2015 text: 2015-07-30 day: 30 |
| PublicationDecade | 2010 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Journal of neuroscience methods |
| PublicationTitleAlternate | J Neurosci Methods |
| PublicationYear | 2015 |
| References | Sammon (10.1016/j.jneumeth.2015.02.007_bib0170) 1969; C-18 Zouridakis (10.1016/j.jneumeth.2015.02.007_bib0210) 1997; 44 Flandrin (10.1016/j.jneumeth.2015.02.007_bib0060) 2004 Lee (10.1016/j.jneumeth.2015.02.007_bib0125) 1999; 11 Mazaheri (10.1016/j.jneumeth.2015.02.007_bib0135) 2006; 103 Huang (10.1016/j.jneumeth.2015.02.007_bib0090) 1998; 454 Flandrin (10.1016/j.jneumeth.2015.02.007_bib0065) 2007 Saddy (10.1016/j.jneumeth.2015.02.007_bib0160) 2004; 90 Rubin (10.1016/j.jneumeth.2015.02.007_bib0150) 2004; 91 Rumelhart (10.1016/j.jneumeth.2015.02.007_bib0155) 1985; 9 Bhandari (10.1016/j.jneumeth.2015.02.007_bib0015) 1996; 10 Quiroga (10.1016/j.jneumeth.2015.02.007_bib0140) 2003; 114 Thakor (10.1016/j.jneumeth.2015.02.007_bib0190) 1987; 34 Demartines (10.1016/j.jneumeth.2015.02.007_bib0040) 1997; 8 Lange (10.1016/j.jneumeth.2015.02.007_bib0115) 2000; 47 Boudraa (10.1016/j.jneumeth.2015.02.007_bib0025) 2007 Spencer (10.1016/j.jneumeth.2015.02.007_bib0175) 2005 Maulik (10.1016/j.jneumeth.2015.02.007_bib0130) 2000; 33 Başar (10.1016/j.jneumeth.2015.02.007_bib0005) 2006; 159 Ben-Hur (10.1016/j.jneumeth.2015.02.007_bib0010) 2002 Cerutti (10.1016/j.jneumeth.2015.02.007_bib0030) 1988; 35 Haig (10.1016/j.jneumeth.2015.02.007_bib0075) 1995; 94 Tseng (10.1016/j.jneumeth.2015.02.007_bib0200) 1995; 17 Farwell (10.1016/j.jneumeth.2015.02.007_bib0055) 1988; 70 Drenhaus (10.1016/j.jneumeth.2015.02.007_bib0045) 2006; 96 Tibshirani (10.1016/j.jneumeth.2015.02.007_bib0195) 2001; 63 Jansen (10.1016/j.jneumeth.2015.02.007_bib0100) 1994; 33 Tass (10.1016/j.jneumeth.2015.02.007_bib0185) 2003; 13 Curio (10.1016/j.jneumeth.2015.02.007_bib0035) 2004; 51 Jongsma (10.1016/j.jneumeth.2015.02.007_bib0105) 2006; 117 Blankertz (10.1016/j.jneumeth.2015.02.007_bib0020) 2004 Salvador (10.1016/j.jneumeth.2015.02.007_bib0165) 2004 Frisch (10.1016/j.jneumeth.2015.02.007_bib0070) 1929; 1 Holland (10.1016/j.jneumeth.2015.02.007_bib0085) 1992; 267 Tan (10.1016/j.jneumeth.2015.02.007_bib0180) 2006 Williams (10.1016/j.jneumeth.2015.02.007_bib0205) 2011; 2011 Hartigan (10.1016/j.jneumeth.2015.02.007_bib0080) 1992; 28 Dunn (10.1016/j.jneumeth.2015.02.007_bib0050) 1974; 4 Ihrke (10.1016/j.jneumeth.2015.02.007_bib0095) 2009 Laskaris (10.1016/j.jneumeth.2015.02.007_bib0120) 1997; 104 Rilling (10.1016/j.jneumeth.2015.02.007_bib0145) 2003 Kay (10.1016/j.jneumeth.2015.02.007_bib0110) 1988 |
| References_xml | – year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0020 – volume: 1 start-page: 36 year: 1929 ident: 10.1016/j.jneumeth.2015.02.007_bib0070 article-title: Correlation and scatter in statistical variables publication-title: Nordic Stat J – volume: 96 start-page: 255 issue: 3 year: 2006 ident: 10.1016/j.jneumeth.2015.02.007_bib0045 article-title: Diagnosis and repair of negative polarity constructions in the light of symbolic resonance analysis publication-title: Brain Lang doi: 10.1016/j.bandl.2005.05.001 – volume: 4 start-page: 95 year: 1974 ident: 10.1016/j.jneumeth.2015.02.007_bib0050 article-title: Well-separated clusters and optimal fuzzy partitions publication-title: J Cybern doi: 10.1080/01969727408546059 – volume: 47 start-page: 822 issue: 6 year: 2000 ident: 10.1016/j.jneumeth.2015.02.007_bib0115 article-title: Overcoming selective ensemble averaging: unsupervised identification of event-related brain potentials publication-title: IEEE Trans Biomed Eng doi: 10.1109/10.844236 – volume: 35 start-page: 701 issue: 9 year: 1988 ident: 10.1016/j.jneumeth.2015.02.007_bib0030 article-title: A parametric method of identification of single-trial event-related potentials in the brain publication-title: IEEE Trans Biomed Eng doi: 10.1109/10.7271 – year: 2009 ident: 10.1016/j.jneumeth.2015.02.007_bib0095 article-title: Denoising and averaging techniques for electrophysiological data – volume: 28 start-page: 100 issue: 1 year: 1992 ident: 10.1016/j.jneumeth.2015.02.007_bib0080 article-title: Algorithm as 136: a k-means clustering algorithm publication-title: J R Stat Soc Ser C: Appl Stat – year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0165 article-title: Determining the number of clusters/segments in hierarchical clustering/segmentation algorithms – volume: 13 start-page: 364 issue: 1 year: 2003 ident: 10.1016/j.jneumeth.2015.02.007_bib0185 article-title: Stochastic phase resetting of stimulus-locked responses of two coupled oscillators: transient response clustering, synchronisation and desynchronisation publication-title: Chaos doi: 10.1063/1.1505813 – volume: 33 start-page: 49 year: 1994 ident: 10.1016/j.jneumeth.2015.02.007_bib0100 article-title: Selective averaging of evoked potentials using trajectory-based clustering publication-title: Methods Inform Med doi: 10.1055/s-0038-1634987 – volume: 114 start-page: 376 year: 2003 ident: 10.1016/j.jneumeth.2015.02.007_bib0140 article-title: Single-trial event-related potentials with wavelet denoising publication-title: Clin Neurophysiol doi: 10.1016/S1388-2457(02)00365-6 – year: 2005 ident: 10.1016/j.jneumeth.2015.02.007_bib0175 article-title: Averaging, detection, and classification of single-trial ERPs – volume: 17 start-page: 71 issue: 1 year: 1995 ident: 10.1016/j.jneumeth.2015.02.007_bib0200 article-title: Evaluation of parametric methods in EEG signal analysis publication-title: Med Eng Phys doi: 10.1016/1350-4533(95)90380-T – volume: 103 start-page: 2948 issue: 8 year: 2006 ident: 10.1016/j.jneumeth.2015.02.007_bib0135 article-title: Posterior alpha activity is not phase-reset by visual stimuli publication-title: Proc Natl Acad Sci U S A doi: 10.1073/pnas.0505785103 – start-page: 6 year: 2002 ident: 10.1016/j.jneumeth.2015.02.007_bib0010 article-title: A stability based method for discovering structure in clustered data – volume: 10 start-page: 731 year: 1996 ident: 10.1016/j.jneumeth.2015.02.007_bib0015 article-title: Genetic algorithm with elitist model and its convergence publication-title: Int J Pattern Recogn Artif Intell doi: 10.1142/S0218001496000438 – volume: 90 start-page: 493 issue: 1–3 year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0160 article-title: Processing polarity items: contrastive licensing costs, brain and language publication-title: Brain Lang – volume: 104 start-page: 151 year: 1997 ident: 10.1016/j.jneumeth.2015.02.007_bib0120 article-title: Robust moving averages, with Hopfield neural network implementation, for monitoring evoked potential signals publication-title: Electroencephalogr Clin Neurophysiol doi: 10.1016/S0168-5597(97)96681-8 – year: 2006 ident: 10.1016/j.jneumeth.2015.02.007_bib0180 – volume: 51 start-page: 1044 issue: 6 year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0035 article-title: The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2004.826692 – volume: 63 start-page: 411 year: 2001 ident: 10.1016/j.jneumeth.2015.02.007_bib0195 article-title: Estimating the number of clusters in a data set via the gap statistic publication-title: J R Stat Soc: Ser B: Stat Methodol doi: 10.1111/1467-9868.00293 – volume: 267 start-page: 66 year: 1992 ident: 10.1016/j.jneumeth.2015.02.007_bib0085 article-title: Genetic algorithms publication-title: Sci Am doi: 10.1038/scientificamerican0792-66 – volume: 33 start-page: 1455 year: 2000 ident: 10.1016/j.jneumeth.2015.02.007_bib0130 article-title: Genetic algorithm-based clustering technique publication-title: Pattern Recogn doi: 10.1016/S0031-3203(99)00137-5 – year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0060 article-title: Detrending and denoising with empirical mode decompositions – volume: 159 start-page: 43 year: 2006 ident: 10.1016/j.jneumeth.2015.02.007_bib0005 article-title: Principles of oscillatory brain dynamics and a treatise of recognition of faces and facial expressions publication-title: Prog Brain Res doi: 10.1016/S0079-6123(06)59004-1 – volume: 94 start-page: 288 year: 1995 ident: 10.1016/j.jneumeth.2015.02.007_bib0075 article-title: Classification of single-trial ERP sub-types: application of globally optimal vector quantization using simulated annealing publication-title: Electroencephalogr Clin Neurophysiol doi: 10.1016/0013-4694(95)98480-V – year: 2003 ident: 10.1016/j.jneumeth.2015.02.007_bib0145 article-title: On empirical mode decomposition and its algorithms – volume: 8 start-page: 148 issue: 1 year: 1997 ident: 10.1016/j.jneumeth.2015.02.007_bib0040 article-title: Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets publication-title: IEEE Trans Neural Netw doi: 10.1109/72.554199 – volume: 34 start-page: 6 year: 1987 ident: 10.1016/j.jneumeth.2015.02.007_bib0190 article-title: Adaptive filtering of evoked potentials publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.1987.326024 – volume: 2011 start-page: 1 year: 2011 ident: 10.1016/j.jneumeth.2015.02.007_bib0205 article-title: Evaluation of empirical mode decomposition for event-related potential analysis publication-title: EURASIP J Adv Signal Process doi: 10.1155/2011/965237 – year: 2007 ident: 10.1016/j.jneumeth.2015.02.007_bib0065 – year: 1988 ident: 10.1016/j.jneumeth.2015.02.007_bib0110 – volume: 44 start-page: 673 year: 1997 ident: 10.1016/j.jneumeth.2015.02.007_bib0210 article-title: A fuzzy clustering approach to EP estimation publication-title: IEEE Trans Biomed Eng doi: 10.1109/10.605424 – volume: 70 start-page: 510 year: 1988 ident: 10.1016/j.jneumeth.2015.02.007_bib0055 article-title: Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials publication-title: Electroencephalogr Clin Neurophysiol doi: 10.1016/0013-4694(88)90149-6 – volume: 117 start-page: 1957 year: 2006 ident: 10.1016/j.jneumeth.2015.02.007_bib0105 article-title: Tracking pattern learning with single-trial event-related potentials publication-title: Clin Neurophysiol doi: 10.1016/j.clinph.2006.05.012 – volume: 91 start-page: 63 year: 2004 ident: 10.1016/j.jneumeth.2015.02.007_bib0150 article-title: An adaptive neuro-fuzzy method (ANFIS) for estimating single-trial movement-related potentials publication-title: Biol Cybern doi: 10.1007/s00422-004-0500-8 – volume: 9 start-page: 75 year: 1985 ident: 10.1016/j.jneumeth.2015.02.007_bib0155 article-title: Feature discovery by competitive learning publication-title: Cogn Sci doi: 10.1207/s15516709cog0901_5 – volume: C-18 start-page: 401 issue: 5 year: 1969 ident: 10.1016/j.jneumeth.2015.02.007_bib0170 article-title: A nonlinear mapping for data structure analysis publication-title: IEEE Trans Comput doi: 10.1109/T-C.1969.222678 – year: 2007 ident: 10.1016/j.jneumeth.2015.02.007_bib0025 – volume: 454 start-page: 903 year: 1998 ident: 10.1016/j.jneumeth.2015.02.007_bib0090 article-title: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis publication-title: Proc R Soc Lond A doi: 10.1098/rspa.1998.0193 – volume: 11 start-page: 417 issue: 2 year: 1999 ident: 10.1016/j.jneumeth.2015.02.007_bib0125 article-title: Independent component analysis using an extended infomax algorithm for mixed sub-Gaussian and super-Gaussian sources publication-title: Neural Comput doi: 10.1162/089976699300016719 |
| SSID | ssj0004906 |
| Score | 2.1868956 |
| Snippet | The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials.... |
| SourceID | proquest pubmed crossref |
| SourceType | Aggregation Database Index Database Enrichment Source |
| StartPage | 22 |
| SubjectTerms | Algorithms Brain - physiology Brain-Computer Interfaces Cluster Analysis Computer Simulation Datasets as Topic Electroencephalography - methods Evoked Potentials Humans Language Language Tests Models, Neurological Neuropsychological Tests Principal Component Analysis Signal Processing, Computer-Assisted Signal-To-Noise Ratio Visual Perception - physiology |
| Title | Method for exploratory cluster analysis and visualisation of single-trial ERP ensembles |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/25698176 https://www.proquest.com/docview/1688004974 |
| Volume | 250 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bi9QwFA7jCuKL6K6X9UYE8WXoOG2apHmSRVYWYQfRXZy3kivsMJfFmQr64G_35NJOV2fx8lJKS9LQ7-Pk5FwReskcF8xKX-GS8KxUlvhkZZI5IqSrTEm4DVG-E3ZyXr6f0ulg8KYXtdRs1Eh_35lX8j-owjPA1WfJ_gOy3aTwAO4BX7gCwnD9K4xPQ_vnWLU7xNJFl7meN778wVC2BUe8cfzrxdrnT647FdEbCeY2i207jj9-GMKB1i7UPAUV_q6w9kpf2tR5ulPI-2abydbVNJHrJvRpGn7q-Z9A2MU-ySncOBkdchqsmdF_YqOgrHiRwUY37UvSItaQbWVhsVNER2vBbDSDVfu1-vA6Guum8v4A-NWXiwAcaGWiyvkvFbPDHty-uoFuFnBO8C0sRj-2MT6lGLNeWvjuj_p60Gmaq8rJNSeOoHmc3UV3EgL4KOJ_Dw3sch8dHC0B7MU3_AqHIN7gHdlHt05TrMQB-hzZgYEduMcOnNiBW3bAjcFX2IFXDvfZgYEduGPHfXT-7vjs7UmW2mhkmuT5JiOkosqaUjKpSuGYkXpMVWWoMESAeqc0L6xQ3PDSMKGJEYUU2pCKCadzrskDtLdcLe0jhJ0yhXAFIVTr0lRGMsKpk6DRGKKoKw8Rbf9frVONed_qZF63wYSzuoWg9hDU46IGCA7R627cZayy8scRL1p4ahCI3ssll3bVrOucwZYEyHNYzcOIWzdni_Pja988Qbe3fH-K9jZfGvsM1M6Neh6o9RPc24VQ |
| linkProvider | Elsevier |
| 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=Method+for+exploratory+cluster+analysis+and+visualisation+of+single-trial+ERP+ensembles&rft.jtitle=Journal+of+neuroscience+methods&rft.au=Williams%2C+N+J&rft.au=Nasuto%2C+S+J&rft.au=Saddy%2C+J+D&rft.date=2015-07-30&rft.eissn=1872-678X&rft.volume=250&rft.spage=22&rft_id=info:doi/10.1016%2Fj.jneumeth.2015.02.007&rft_id=info%3Apmid%2F25698176&rft.externalDocID=25698176 |
| 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 |