Deep Gaussian Mixture-Hidden Markov Model for Classification of EEG Signals
Electroencephalography (EEG) signals are complex dynamic phenomena that exhibit nonlinear and nonstationary behaviors. These characteristics tend to undermine the reliability of existing hand-crafted EEG features that ignore time-varying information and impair the performances of classification mode...
Uloženo v:
| Vydáno v: | IEEE transactions on emerging topics in computational intelligence Ročník 2; číslo 4; s. 278 - 287 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Piscataway
IEEE
01.08.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 2471-285X, 2471-285X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Electroencephalography (EEG) signals are complex dynamic phenomena that exhibit nonlinear and nonstationary behaviors. These characteristics tend to undermine the reliability of existing hand-crafted EEG features that ignore time-varying information and impair the performances of classification models. In this paper, we propose a novel method that can automatically capture the nonstationary dynamics of EEG signals for diverse classification tasks. It consists of two components. The first component uses an autoregressive-deep variational autoencoder model for automatic feature extraction, and the second component uses a Gaussian mixture-hidden Markov model for EEG classification with the extracted features. We compare the performance of our proposed method and the state-of-the-art methods in two EEG classification tasks, subject, and event classification. Results show that our approach outperforms the others by averages of <inline-formula><tex-math notation="LaTeX">\text{15}\%\pm \text{6.3}</tex-math> </inline-formula> (p-value <inline-formula><tex-math notation="LaTeX"><\text{0.05}</tex-math></inline-formula>) and <inline-formula><tex-math notation="LaTeX">\text{22}\%\pm \text{5.7}</tex-math></inline-formula> (p-value <inline-formula><tex-math notation="LaTeX"><\text{0.05}</tex-math></inline-formula>) for subject and event classifications, respectively. |
|---|---|
| AbstractList | Electroencephalography (EEG) signals are complex dynamic phenomena that exhibit nonlinear and nonstationary behaviors. These characteristics tend to undermine the reliability of existing hand-crafted EEG features that ignore time-varying information and impair the performances of classification models. In this paper, we propose a novel method that can automatically capture the nonstationary dynamics of EEG signals for diverse classification tasks. It consists of two components. The first component uses an autoregressive-deep variational autoencoder model for automatic feature extraction, and the second component uses a Gaussian mixture-hidden Markov model for EEG classification with the extracted features. We compare the performance of our proposed method and the state-of-the-art methods in two EEG classification tasks, subject, and event classification. Results show that our approach outperforms the others by averages of 15% ± 6.3 (p-value <; 0.05) and 22% ± 5.7 (p-value <; 0.05) for subject and event classifications, respectively. Electroencephalography (EEG) signals are complex dynamic phenomena that exhibit nonlinear and nonstationary behaviors. These characteristics tend to undermine the reliability of existing hand-crafted EEG features that ignore time-varying information and impair the performances of classification models. In this paper, we propose a novel method that can automatically capture the nonstationary dynamics of EEG signals for diverse classification tasks. It consists of two components. The first component uses an autoregressive-deep variational autoencoder model for automatic feature extraction, and the second component uses a Gaussian mixture-hidden Markov model for EEG classification with the extracted features. We compare the performance of our proposed method and the state-of-the-art methods in two EEG classification tasks, subject, and event classification. Results show that our approach outperforms the others by averages of <inline-formula><tex-math notation="LaTeX">\text{15}\%\pm \text{6.3}</tex-math> </inline-formula> (p-value <inline-formula><tex-math notation="LaTeX"><\text{0.05}</tex-math></inline-formula>) and <inline-formula><tex-math notation="LaTeX">\text{22}\%\pm \text{5.7}</tex-math></inline-formula> (p-value <inline-formula><tex-math notation="LaTeX"><\text{0.05}</tex-math></inline-formula>) for subject and event classifications, respectively. |
| Author | Abdelfattah, Sherif Moustafa, Nour Wang, Min Hu, Jiankun |
| Author_xml | – sequence: 1 givenname: Min orcidid: 0000-0002-1580-6387 surname: Wang fullname: Wang, Min email: min.wang@student.adfa.edu.au organization: School of Engineering and Information Technology, University of New South Wales Canberra at ADFA, Campbell, ACT, Australia – sequence: 2 givenname: Sherif surname: Abdelfattah fullname: Abdelfattah, Sherif email: Sherif.Abdelfattah@student.adfa.edu.au organization: School of Engineering and Information Technology, University of New South Wales Canberra at ADFA, Campbell, ACT, Australia – sequence: 3 givenname: Nour orcidid: 0000-0001-6127-9349 surname: Moustafa fullname: Moustafa, Nour email: nour.moustafa@unsw.edu.au organization: School of Engineering and Information Technology, University of New South Wales Canberra at ADFA, Campbell, ACT, Australia – sequence: 4 givenname: Jiankun orcidid: 0000-0003-0230-1432 surname: Hu fullname: Hu, Jiankun email: J.Hu@adfa.edu.au organization: School of Engineering and Information Technology, University of New South Wales Canberra at ADFA, Campbell, ACT, Australia |
| BookMark | eNp9UE1PAjEUbAwmIvIH9NLE82K_drc9GkQgQjyIibembFtTXLfY7hr99xYwxnjwNO8lM-_NzCnoNb4xAJxjNMIYiavVZDWejwjCfEQ4EYLjI9AnrMQZ4flT79d8AoYxbhBCROSY5qwP7m6M2cKp6mJ0qoFL99F2wWQzp7VJqwov_h0uvTY1tD7Aca0S0bpKtc430Fs4mUzhg3tuVB3PwLFNYIbfOACPt8naLFvcT-fj60VWpbdtZgTTvGTlmmnNMCW0UAhpTS02hBXaEkKrPGdizRXPacEYxrbkjBpCrcXU0AG4PNzdBv_WmdjKje_CzoEkKT7OBSlYYpEDqwo-xmCs3Ab3qsKnxEjuepP73uSuN_ndWxLxP6LKtfusbVCu_l96cZA6Y8zPL85wUYqCfgGQ1HtF |
| CODEN | ITETCU |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2019_2919143 crossref_primary_10_1109_JSEN_2022_3194699 crossref_primary_10_3390_s23031390 crossref_primary_10_1109_TBME_2021_3137184 crossref_primary_10_1080_10447318_2022_2091561 crossref_primary_10_1109_ACCESS_2020_3016481 crossref_primary_10_3390_s21175746 crossref_primary_10_1016_j_enbuild_2021_111594 crossref_primary_10_1109_TETCI_2019_2907718 crossref_primary_10_3390_s21134391 crossref_primary_10_1007_s13721_020_00283_2 crossref_primary_10_3390_s23010062 crossref_primary_10_1109_TITS_2022_3189981 crossref_primary_10_1007_s00779_019_01250_z crossref_primary_10_3390_act11060161 crossref_primary_10_3390_s25113389 crossref_primary_10_1049_iet_ipr_2020_0709 crossref_primary_10_1109_TETCI_2022_3189385 crossref_primary_10_1007_s13042_023_01910_w crossref_primary_10_1016_j_future_2021_01_011 crossref_primary_10_1016_j_rcim_2023_102610 crossref_primary_10_1016_j_compbiomed_2021_104684 crossref_primary_10_1109_TNSRE_2020_3013429 crossref_primary_10_1007_s00521_020_05549_4 crossref_primary_10_3390_s22145111 crossref_primary_10_1080_21681163_2023_2250872 crossref_primary_10_1109_IOTM_003_2100061 crossref_primary_10_1109_JSEN_2022_3201015 crossref_primary_10_1155_2021_7568460 crossref_primary_10_1016_j_cmpb_2019_04_004 crossref_primary_10_1109_TIFS_2019_2916403 |
| Cites_doi | 10.1109/TAMD.2015.2431497 10.1111/j.2517-6161.1977.tb01600.x 10.1109/JBHI.2013.2294692 10.1198/106186001317243403 10.1088/1741-2560/11/3/035013 10.1016/j.neucom.2014.08.092 10.1109/TETCI.2017.2750761 10.1016/S0167-8655(01)00075-7 10.1109/ICACT.2015.7224883 10.1007/s12559-015-9365-5 10.1098/rspa.1998.0193 10.1136/jnnp.2005.069245 10.1109/TBME.2014.2317881 10.1515/9780691218632 10.1109/SMC.2016.7844773 10.1161/01.CIR.101.23.e215 10.1109/TPAMI.2010.125 10.1214/aoms/1177729694 10.1109/TBME.2004.827076 10.1017/CBO9780511984679 10.1109/TBME.2004.827072 10.1109/MCI.2015.2501545 10.1109/IJCNN.2002.1007657 10.1109/34.990138 10.1109/ICPR.2010.36 10.1109/SMC.2016.7844987 10.18637/jss.v032.i06 10.1109/TRE.2000.847807 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 8FD L7M |
| DOI | 10.1109/TETCI.2018.2829981 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2471-285X |
| EndPage | 287 |
| ExternalDocumentID | 10_1109_TETCI_2018_2829981 8416796 |
| Genre | orig-research |
| GroupedDBID | 0R~ 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE JAVBF OCL RIA RIE AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c295t-e94d8747b4dd413236a00dd3f1e246df223c5549b8a85364411f7843e23ff13e3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 36 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000679686500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2471-285X |
| IngestDate | Sun Sep 07 03:26:55 EDT 2025 Tue Nov 18 21:43:01 EST 2025 Sat Nov 29 05:12:06 EST 2025 Wed Aug 27 02:48:39 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c295t-e94d8747b4dd413236a00dd3f1e246df223c5549b8a85364411f7843e23ff13e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-6127-9349 0000-0003-0230-1432 0000-0002-1580-6387 |
| PQID | 2299159264 |
| PQPubID | 4437216 |
| PageCount | 10 |
| ParticipantIDs | crossref_primary_10_1109_TETCI_2018_2829981 ieee_primary_8416796 crossref_citationtrail_10_1109_TETCI_2018_2829981 proquest_journals_2299159264 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-08-01 |
| PublicationDateYYYYMMDD | 2018-08-01 |
| PublicationDate_xml | – month: 08 year: 2018 text: 2018-08-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on emerging topics in computational intelligence |
| PublicationTitleAbbrev | TETCI |
| PublicationYear | 2018 |
| 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 | ref35 hamilton (ref22) 1994; 2 ref34 ref12 ref37 ref15 ref14 ref31 ref11 ref10 viola (ref36) 2010 ref2 ref1 ref16 ref19 kingma (ref24) 0 bilmes (ref30) 1998; 4 chiappa (ref18) 2003 ref23 ref26 manning (ref27) 1999; 999 huang (ref5) 1998; 454 ref25 dempster (ref29) 1977; 39 ref21 goldberger (ref33) 2000; 101 ref28 (ref32) 0 ref8 ref7 ref9 ref4 ref3 ref6 sanei (ref20) 2013 solhjoo (ref17) 2005 bashivan (ref13) 0 |
| References_xml | – start-page: 1 year: 2005 ident: ref17 article-title: Classification of chaotic signals using HMM classifiers: EEG-based mental task classification publication-title: Proc 13th Eur IEEE Signal Process Conf – ident: ref11 doi: 10.1109/TAMD.2015.2431497 – volume: 39 start-page: 1 year: 1977 ident: ref29 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J Royal Statistical Society Series B (Methodological) doi: 10.1111/j.2517-6161.1977.tb01600.x – start-page: 121 year: 2010 ident: ref36 article-title: Using ICA for the analysis of multi-channel EEG data publication-title: Simultaneous EEG and fMRI Recording Analysis and Application Recording Analysis and Application – ident: ref28 doi: 10.1109/JBHI.2013.2294692 – ident: ref31 doi: 10.1198/106186001317243403 – ident: ref35 doi: 10.1088/1741-2560/11/3/035013 – ident: ref10 doi: 10.1016/j.neucom.2014.08.092 – ident: ref3 doi: 10.1109/TETCI.2017.2750761 – ident: ref15 doi: 10.1016/S0167-8655(01)00075-7 – ident: ref7 doi: 10.1109/ICACT.2015.7224883 – ident: ref4 doi: 10.1007/s12559-015-9365-5 – volume: 454 start-page: 703 year: 1998 ident: ref5 article-title: The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series publication-title: Proc Roy Soc London doi: 10.1098/rspa.1998.0193 – ident: ref1 doi: 10.1136/jnnp.2005.069245 – year: 0 ident: ref32 – year: 2003 ident: ref18 article-title: HMM and IOHMM modeling of EEG rhythms for asynchronous BCI systems – ident: ref8 doi: 10.1109/TBME.2014.2317881 – volume: 4 start-page: 126 year: 1998 ident: ref30 article-title: A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models publication-title: Int Comput Sci Inst – volume: 2 year: 1994 ident: ref22 publication-title: Time Series Analysis doi: 10.1515/9780691218632 – volume: 999 year: 1999 ident: ref27 publication-title: Foundations of Statistical Natural Language Processing – year: 0 ident: ref13 article-title: Learning representations from EEG with deep recurrent-convolutional neural networks publication-title: Proc Int Conf Learn Represent – ident: ref6 doi: 10.1109/SMC.2016.7844773 – volume: 101 start-page: 215e year: 2000 ident: ref33 article-title: Physiobank, physiotoolkit, and physionet publication-title: Circulation doi: 10.1161/01.CIR.101.23.e215 – ident: ref12 doi: 10.1109/TPAMI.2010.125 – ident: ref23 doi: 10.1214/aoms/1177729694 – ident: ref14 doi: 10.1109/TBME.2004.827076 – ident: ref21 doi: 10.1017/CBO9780511984679 – ident: ref34 doi: 10.1109/TBME.2004.827072 – year: 2013 ident: ref20 publication-title: EEG Signal Processing – ident: ref37 doi: 10.1109/MCI.2015.2501545 – ident: ref19 doi: 10.1109/IJCNN.2002.1007657 – ident: ref25 doi: 10.1109/34.990138 – ident: ref16 doi: 10.1109/ICPR.2010.36 – ident: ref9 doi: 10.1109/SMC.2016.7844987 – ident: ref26 doi: 10.18637/jss.v032.i06 – ident: ref2 doi: 10.1109/TRE.2000.847807 – year: 0 ident: ref24 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent |
| SSID | ssj0002951354 |
| Score | 2.2382324 |
| Snippet | Electroencephalography (EEG) signals are complex dynamic phenomena that exhibit nonlinear and nonstationary behaviors. These characteristics tend to undermine... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 278 |
| SubjectTerms | autoencoder Autoregressive models Brain modeling Classification deep learning EEG classification Electroencephalography Feature extraction Gaussian mixture model hidden Markov model Hidden Markov models Indexing Machine learning Markov analysis Markov chains Markov processes Signal classification Task analysis time-series |
| Title | Deep Gaussian Mixture-Hidden Markov Model for Classification of EEG Signals |
| URI | https://ieeexplore.ieee.org/document/8416796 https://www.proquest.com/docview/2299159264 |
| Volume | 2 |
| WOSCitedRecordID | wos000679686500005&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) customDbUrl: eissn: 2471-285X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002951354 issn: 2471-285X databaseCode: RIE dateStart: 20170101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF7a4sGLD6pYrbIHb5o22byPoq0VtQhW6C1ssrNSLE3pC3--M5s0IIrgLQm7YXcm2fnmzdgluBqBt5SWTrVreUo6Vgp-ZGW-sh08lH0NpmT-UzgcRuNx_FJj11UuDACY4DPo0KXx5as8W5OprEsusjAO6qwehkGRq1XZUwRCBdf3tnkxdtwd9Ua3DxS8FXXIXRhHzjfZY5qp_DiBjVjp7_9vQQdsr4SP_Kbg9yGrwazJHu8A5vxerpeUEcmfJ5_kFrAGVB0Eb-XiI99wano25QhRuemDSRFChik817zXu-evk3cqpXzE3vq4o4FVNkmwMtzyyoLYUxHqBKmnFAok4QbStpVytQPCC5RG8Z8hZIjTSKJkJvTj6DDyXBCu1mQCPWaNWT6DE8YVSLAF6CBGlCRIb1Yi8zQ-E4EErVrM2ZIvycoK4tTIYpoYTcKOE0PyhEielCRvsatqzryon_Hn6CYRuRpZ0rfF2lsuJeUvtkwEzkAshks9_X3WGduldxfRem3WWC3WcM52ss1qslxcmK_nCw_uwvY |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB58gV58UMVq1T1409Rks0mTo2gfYi2CFXoL2-ysFKWVPsSf78w2LYgieEvCLtmdSXa-eQOcY2gJeGvt2b4NPWV04PUxSrw8Mn5Ah3Jk0ZXMb9c6naTXSx9X4HKZC4OILvgMq3zpfPlmlM_YVHbFLrJaGq_CeqSU9OfZWkuLiiSwEEZqkRnjp1fdevfmjsO3kio7DNMk-CZ9XDuVH2ewEyyNnf8taRe2CwAprucc34MVHJbg_hbxXTT1bMI5keJh8MmOAa_F9UHoVo9fRx-C2569CQKpwnXC5BghxxYxsqJeb4qnwQsXU96H5wbtqOUVbRK8nLY89TBVJiGtoK-MIZEkw1j7vjGhDVCq2FgCADmBhrSfaJLNjH8CW0tUiDK0lo2gB7A2HA3xEIRBjb5EG6eEkyRrzkbmytIzGWu0pgzBgnxZXtQQ51YWb5nTJfw0cyTPmORZQfIyXCznvM8raPw5usREXo4s6FuGyoJLWfGTTTJJMwiN0VKPfp91Bput7kM7a9917o9hi98zj92rwNp0PMMT2Mg_poPJ-NR9SV9gsMY9 |
| 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=Deep+Gaussian+Mixture-Hidden+Markov+Model+for+Classification+of+EEG+Signals&rft.jtitle=IEEE+transactions+on+emerging+topics+in+computational+intelligence&rft.au=Wang%2C+Min&rft.au=Abdelfattah%2C+Sherif&rft.au=Moustafa%2C+Nour&rft.au=Hu%2C+Jiankun&rft.date=2018-08-01&rft.issn=2471-285X&rft.eissn=2471-285X&rft.volume=2&rft.issue=4&rft.spage=278&rft.epage=287&rft_id=info:doi/10.1109%2FTETCI.2018.2829981&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TETCI_2018_2829981 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2471-285X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2471-285X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2471-285X&client=summon |