Multimodal Data Fusion Using Source Separation: Two Effective Models Based on ICA and IVA and Their Properties
Fusion of information from multiple sets of data in order to extract a set of features that are most useful and relevant for the given task is inherent to many problems we deal with today. Since, usually, very little is known about the actual interaction among the data sets, it is highly desirable t...
Saved in:
| Published in | Proceedings of the IEEE Vol. 103; no. 9; pp. 1478 - 1493 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.09.2015
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Fusion of information from multiple sets of data in order to extract a set of features that are most useful and relevant for the given task is inherent to many problems we deal with today. Since, usually, very little is known about the actual interaction among the data sets, it is highly desirable to minimize the underlying assumptions. This has been the main reason for the growing importance of data-driven methods, and in particular of independent component analysis (ICA) as it provides useful decompositions with a simple generative model and using only the assumption of statistical independence. A recent extension of ICA, independent vector analysis (IVA), generalizes ICA to multiple data sets by exploiting the statistical dependence across the data sets, and hence, as we discuss in this paper, provides an attractive solution to fusion of data from multiple data sets along with ICA. In this paper, we focus on two multivariate solutions for multimodal data fusion that let multiple modalities fully interact for the estimation of underlying features that jointly report on all modalities. One solution is the joint ICA model that has found wide application in medical imaging, and the second one is the transposed IVA model introduced here as a generalization of an approach based on multiset canonical correlation analysis. In the discussion, we emphasize the role of diversity in the decompositions achieved by these two models, and present their properties and implementation details to enable the user make informed decisions on the selection of a model along with its associated parameters. Discussions are supported by simulation results to help highlight the main issues in the implementation of these methods. |
|---|---|
| AbstractList | Fusion of information from multiple sets of data in order to extract a set of features that are most useful and relevant for the given task is inherent to many problems we deal with today. Since, usually, very little is known about the actual interaction among the data sets, it is highly desirable to minimize the underlying assumptions. This has been the main reason for the growing importance of data-driven methods, and in particular of independent component analysis (ICA) as it provides useful decompositions with a simple generative model and using only the assumption of statistical independence. A recent extension of ICA, independent vector analysis (IVA), generalizes ICA to multiple data sets by exploiting the statistical dependence across the data sets, and hence, as we discuss in this paper, provides an attractive solution to fusion of data from multiple data sets along with ICA. In this paper, we focus on two multivariate solutions for multimodal data fusion that let multiple modalities fully interact for the estimation of underlying features that jointly report on all modalities. One solution is the joint ICA model that has found wide application in medical imaging, and the second one is the transposed IVA model introduced here as a generalization of an approach based on multiset canonical correlation analysis. In the discussion, we emphasize the role of diversity in the decompositions achieved by these two models, and present their properties and implementation details to enable the user make informed decisions on the selection of a model along with its associated parameters. Discussions are supported by simulation results to help highlight the main issues in the implementation of these methods. |
| Author | AdalI, Tulay Calhoun, Vince D. Levin-Schwartz, Yuri |
| Author_xml | – sequence: 1 givenname: Tulay surname: AdalI fullname: AdalI, Tulay email: adali@umbc.edu organization: Dept. of Comput. Sci. & Electr. Eng., Univ. of Maryland Baltimore County, Baltimore, MD, USA – sequence: 2 givenname: Yuri surname: Levin-Schwartz fullname: Levin-Schwartz, Yuri organization: Dept. of Comput. Sci. & Electr. Eng., Univ. of Maryland Baltimore County, Baltimore, MD, USA – sequence: 3 givenname: Vince D. surname: Calhoun fullname: Calhoun, Vince D. organization: Univ. of New Mexico, Albuquerque, NM, USA |
| BookMark | eNp9kcFu1DAQhi1UJLaFF4CLJS5csszYsZNwg6WFolat6MI1Ms4YXGXjxXZa8fb1disOPfQ0I-v7Rp75D9nBFCZi7DXCEhG6998uv1-slgJQLUWtUYv6GVugUm0lhNIHbAGAbdUJ7F6ww5SuAUAqLRdsOp_H7DdhMCP_bLLhJ3PyYeI_kp9-86swR0v8irYmmlzeP_D1beDHzpHN_ob4eRhoTPyTSTTwop2uPnIzDfz0576u_5CP_DKGLcXsKb1kz50ZE716qEdsfXK8Xn2tzi6-FPessgpFroz7pZQobQ0W7eA664zuoHVamtoSdEo2hA1K4VqhjLC2bpUAKQblpNXyiL3bj93G8HemlPuNT5bG0UwU5tRjo6QCXbdQ0LeP0Ouy9FQ-VyjRgkKsd1S7p2wMKUVyvfX5_iI5Gj_2CP0uh_4-h36XQ_-QQ1HFI3Ub_cbEf09Lb_aSJ6L_QiNAK2zkHST3k_E |
| CODEN | IEEPAD |
| CitedBy_id | crossref_primary_10_1007_s11265_016_1151_4 crossref_primary_10_1016_j_jneumeth_2017_01_017 crossref_primary_10_1109_TSP_2019_2955829 crossref_primary_10_1109_TSP_2021_3109375 crossref_primary_10_1016_j_inffus_2020_07_006 crossref_primary_10_3390_app11188382 crossref_primary_10_1002_epi4_12838 crossref_primary_10_1186_s12940_020_00683_x crossref_primary_10_1007_s12021_025_09716_7 crossref_primary_10_3390_s22197417 crossref_primary_10_3389_fnins_2019_00416 crossref_primary_10_3389_fnins_2018_00013 crossref_primary_10_1016_j_bspc_2021_102889 crossref_primary_10_1002_hbm_70037 crossref_primary_10_1109_LSENS_2018_2884775 crossref_primary_10_1109_ACCESS_2017_2695497 crossref_primary_10_1016_j_patcog_2023_109376 crossref_primary_10_1016_j_neuroimage_2016_03_058 crossref_primary_10_1063_1_5037882 crossref_primary_10_1016_j_envint_2021_106447 crossref_primary_10_1016_j_patter_2022_100602 crossref_primary_10_1093_psyrad_kkad026 crossref_primary_10_1109_JPROC_2015_2474704 crossref_primary_10_1109_TSP_2020_3022827 crossref_primary_10_1109_LSP_2016_2546687 crossref_primary_10_1109_JSEN_2022_3206225 crossref_primary_10_1109_MSP_2016_2521870 crossref_primary_10_1088_1742_6596_1345_3_032006 crossref_primary_10_1162_imag_a_00348 crossref_primary_10_1016_j_sigpro_2020_107957 crossref_primary_10_31887_DCNS_2018_20_2_vcalhoun crossref_primary_10_1093_scan_nsaa114 crossref_primary_10_1109_TMI_2017_2678483 crossref_primary_10_3390_s24165428 crossref_primary_10_1111_ejn_16674 crossref_primary_10_1002_nla_2291 crossref_primary_10_1109_JSYST_2020_2981366 crossref_primary_10_1016_j_csbj_2022_11_008 crossref_primary_10_1016_j_neuroimage_2020_116872 crossref_primary_10_1016_j_bspc_2020_101948 crossref_primary_10_1111_epi_17538 crossref_primary_10_1109_TSP_2021_3068626 crossref_primary_10_1016_j_oceaneng_2023_116421 crossref_primary_10_1016_j_envres_2020_109148 crossref_primary_10_1016_j_bspc_2021_102698 crossref_primary_10_1016_j_jneumeth_2021_109214 crossref_primary_10_3389_fnins_2021_724391 crossref_primary_10_1016_j_envres_2021_111553 crossref_primary_10_1051_matecconf_20165701021 crossref_primary_10_1002_hbm_25717 |
| Cites_doi | 10.1109/RBME.2012.2211076 10.1162/neco.1995.7.6.1129 10.1109/CISS.2015.7086864 10.1073/pnas.0903525106 10.1016/j.neuroimage.2009.06.011 10.1109/CISS.2015.7086842 10.1109/31.76486 10.1371/journal.pone.0028072 10.1109/72.761722 10.1109/TASSP.1985.1164557 10.1016/j.jneumeth.2015.03.019 10.1016/j.jneumeth.2011.10.031 10.1109/MSP.2014.2298045 10.1016/j.neuroimage.2013.12.063 10.1016/j.neuroimage.2011.10.010 10.1109/ACSSC.2004.1399288 10.1109/78.599941 10.3389/fnsys.2014.00106 10.1109/EMBC.2014.6944891 10.1109/ISBI.2011.5872574 10.1109/TSP.2009.2021636 10.1109/78.553476 10.1109/TBME.2015.2404300 10.1109/78.212737 10.1002/9781118579749 10.1002/hbm.20359 10.1109/TITB.2008.923773 10.2307/2334380 10.1109/TAC.1974.1100705 10.1109/97.847367 10.1016/j.neuroimage.2008.10.057 10.1109/TSP.2011.2181836 10.1109/JPROC.2015.2461601 10.2307/2333955 10.1002/0471221317 10.1016/j.neuroimage.2012.10.051 10.1109/CISS.2015.7086828 10.1109/TNN.2006.875991 10.1109/TNN.2003.820667 10.1002/hbm.1048 10.1016/j.sigpro.2011.04.016 10.1109/TSP.2012.2199985 10.1109/ICASSP.2013.6638257 10.1109/ACSSC.2006.354986 10.1109/TSP.2014.2333551 10.1109/TSP.2011.2162954 10.1109/ICASSP.1998.681443 10.1109/78.554307 10.1109/ICASSP.2012.6288271 10.1162/089976601750264992 10.1016/0165-1684(94)90029-9 10.1016/j.neuroimage.2005.08.060 10.1016/j.neuroimage.2014.12.040 10.1109/TMI.2014.2340816 10.1016/j.neuroimage.2013.11.032 10.1016/j.neuroimage.2007.11.019 10.1016/j.neuroimage.2011.05.055 10.1214/aos/1176344136 10.1371/journal.pone.0073309 10.1109/JSTSP.2008.2008265 10.1109/83.988962 10.1016/j.ijpsycho.2007.04.010 10.1007/978-3-642-15995-4_25 10.1109/TSP.2008.926104 10.1016/j.neuroimage.2012.01.063 10.1109/ICASSP.2010.5495311 10.1109/MSP.2014.2300511 10.1016/j.neuroimage.2010.09.073 10.1109/ICASSP.2015.7178612 10.1109/MSP.2010.936725 10.1016/j.neuroimage.2012.02.030 10.1002/9780470575758 10.1049/ip-f-2.1993.0054 10.1016/0005-1098(78)90005-5 10.1109/TSP.2010.2053362 10.1109/TSP.2014.2333563 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2015 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2015 |
| DBID | 97E RIA RIE AAYXX CITATION 7SP 8FD L7M 7U5 F28 FR3 |
| DOI | 10.1109/JPROC.2015.2461624 |
| 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 Solid State and Superconductivity Abstracts ANTE: Abstracts in New Technology & Engineering Engineering Research Database |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Engineering Research Database ANTE: Abstracts in New Technology & Engineering |
| DatabaseTitleList | Solid State and Superconductivity Abstracts Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2256 |
| EndPage | 1493 |
| ExternalDocumentID | 3850641571 10_1109_JPROC_2015_2461624 7206517 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: NIH COBRE under Grant P20GM103472 – fundername: NSF-IIS grantid: 1017718 – fundername: NSF-CCF grantid: 1117056 – fundername: National Institutes of Health grantid: 2R01EB000840 funderid: 10.13039/100000002 |
| GroupedDBID | -DZ -~X .DC 0R~ 123 1OL 29P 3EH 4.4 6IK 85S 97E 9M8 AAJGR AAWTH ABAZT ABFSI ABJNI ABQJQ ABVLG ACBEA ACGFS AENEX AETEA AETIX AFOGA AGNAY AGQYO AGSQL AHBIQ AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS AZLTO BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD FA8 HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MVM O9- OCL RIA RIE RIU RNS TAE TN5 TWZ UDY UHB UKR UQL VOH WHG XJT XOL YNT ZCA ZXP ZY4 ~02 AAYOK AAYXX CITATION RIG 7SP 8FD L7M 7U5 F28 FR3 |
| ID | FETCH-LOGICAL-c512t-afb55251240c1cdf9cfa6908f63a4ce09537e17132f825a2cc4852032d5f3c63 |
| IEDL.DBID | RIE |
| ISSN | 0018-9219 |
| IngestDate | Fri Jul 11 04:37:32 EDT 2025 Mon Jun 30 10:25:10 EDT 2025 Thu Apr 24 23:09:33 EDT 2025 Tue Jul 01 01:56:39 EDT 2025 Wed Aug 27 02:43:09 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| Keywords | Data fusion multimodality independent component analysis (ICA) independent vector analysis (IVA) (joint) blind source separation |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c512t-afb55251240c1cdf9cfa6908f63a4ce09537e17132f825a2cc4852032d5f3c63 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/4624202 |
| PQID | 1728051140 |
| PQPubID | 85453 |
| PageCount | 16 |
| ParticipantIDs | crossref_citationtrail_10_1109_JPROC_2015_2461624 ieee_primary_7206517 proquest_miscellaneous_1753506480 crossref_primary_10_1109_JPROC_2015_2461624 proquest_journals_1728051140 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2015-09-01 |
| PublicationDateYYYYMMDD | 2015-09-01 |
| PublicationDate_xml | – month: 09 year: 2015 text: 2015-09-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Proceedings of the IEEE |
| PublicationTitleAbbrev | JPROC |
| PublicationYear | 2015 |
| 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 | ref57 ref13 ref56 ref12 ref59 ref15 ref58 ref14 ref53 ref52 ref55 ref11 ref54 ref10 ref16 ref19 comon (ref4) 2010 ref51 ref46 ref45 ref48 ref47 ref42 borga (ref50) 2001 ref44 ref43 ref49 ref8 ref7 swinnen (ref17) 0 ref9 ref3 ref6 ref5 tichavský (ref75) 2006 ref82 ref81 ref40 ref84 ref83 anderson (ref41) 2013 ref79 ref35 ref78 ref34 ref37 ref36 ref31 ref74 ref30 ref77 ref33 ref32 ref2 amari (ref80) 1996; 8 ref1 ref39 ref38 (ref76) 0 ref71 ref70 ref73 ref72 ref68 ref24 ramezani (ref18) 2014 ref67 ref23 ref26 silva (ref85) 0 ref69 ref25 ref64 ref20 ref63 ref66 ref22 ref65 ref21 ref28 ref27 ref29 ref60 ref62 ref61 |
| References_xml | – ident: ref33 doi: 10.1109/RBME.2012.2211076 – ident: ref34 doi: 10.1162/neco.1995.7.6.1129 – ident: ref58 doi: 10.1109/CISS.2015.7086864 – ident: ref77 doi: 10.1073/pnas.0903525106 – ident: ref13 doi: 10.1016/j.neuroimage.2009.06.011 – ident: ref48 doi: 10.1109/CISS.2015.7086842 – ident: ref38 doi: 10.1109/31.76486 – start-page: 2864 year: 0 ident: ref85 article-title: Multidata set independent subspace analysis extends independent vector analysis publication-title: Proc IEEE Int Conf Image Process – ident: ref70 doi: 10.1371/journal.pone.0028072 – ident: ref35 doi: 10.1109/72.761722 – ident: ref62 doi: 10.1109/TASSP.1985.1164557 – year: 2001 ident: ref50 publication-title: Canonical correlation A tutorial – ident: ref55 doi: 10.1016/j.jneumeth.2015.03.019 – ident: ref5 doi: 10.1016/j.jneumeth.2011.10.031 – ident: ref29 doi: 10.1109/MSP.2014.2298045 – year: 2013 ident: ref41 publication-title: Independent vector analysis Theory algorithms applications – ident: ref57 doi: 10.1016/j.neuroimage.2013.12.063 – ident: ref52 doi: 10.1016/j.neuroimage.2011.10.010 – ident: ref71 doi: 10.1109/ACSSC.2004.1399288 – ident: ref37 doi: 10.1109/78.599941 – ident: ref56 doi: 10.3389/fnsys.2014.00106 – ident: ref16 doi: 10.1109/EMBC.2014.6944891 – ident: ref67 doi: 10.1109/ISBI.2011.5872574 – ident: ref23 doi: 10.1109/TSP.2009.2021636 – ident: ref81 doi: 10.1109/78.553476 – ident: ref19 doi: 10.1109/TBME.2015.2404300 – ident: ref69 doi: 10.1109/78.212737 – ident: ref26 doi: 10.1002/9781118579749 – year: 2010 ident: ref4 publication-title: Handbook of Blind Source Separation Independent Component Analysis and Applications – ident: ref66 doi: 10.1002/hbm.20359 – ident: ref1 doi: 10.1109/TITB.2008.923773 – ident: ref22 doi: 10.2307/2334380 – ident: ref63 doi: 10.1109/TAC.1974.1100705 – ident: ref40 doi: 10.1109/97.847367 – ident: ref11 doi: 10.1016/j.neuroimage.2008.10.057 – year: 0 ident: ref76 publication-title: Fusion ICA Toolbox – ident: ref9 doi: 10.1109/TSP.2011.2181836 – ident: ref21 doi: 10.1109/JPROC.2015.2461601 – ident: ref49 doi: 10.2307/2333955 – ident: ref7 doi: 10.1002/0471221317 – ident: ref60 doi: 10.1016/j.neuroimage.2012.10.051 – ident: ref47 doi: 10.1109/CISS.2015.7086828 – ident: ref42 doi: 10.1109/TNN.2006.875991 – ident: ref36 doi: 10.1109/TNN.2003.820667 – ident: ref51 doi: 10.1002/hbm.1048 – ident: ref28 doi: 10.1016/j.sigpro.2011.04.016 – ident: ref82 doi: 10.1109/TSP.2012.2199985 – year: 2006 ident: ref75 article-title: Blind signal separation by combining two ICA algorithms: HOS-based EFICA and time structure-based WASOBI publication-title: Eur Signal Process Conf – ident: ref46 doi: 10.1109/ICASSP.2013.6638257 – ident: ref8 doi: 10.1109/ACSSC.2006.354986 – ident: ref68 doi: 10.1109/TSP.2014.2333551 – ident: ref32 doi: 10.1109/TSP.2011.2162954 – ident: ref84 doi: 10.1109/ICASSP.1998.681443 – ident: ref39 doi: 10.1109/78.554307 – ident: ref61 doi: 10.1109/ICASSP.2012.6288271 – ident: ref83 doi: 10.1162/089976601750264992 – ident: ref3 doi: 10.1016/0165-1684(94)90029-9 – ident: ref2 doi: 10.1016/j.neuroimage.2005.08.060 – ident: ref73 doi: 10.1016/j.neuroimage.2014.12.040 – ident: ref79 doi: 10.1109/TMI.2014.2340816 – ident: ref53 doi: 10.1016/j.neuroimage.2013.11.032 – ident: ref54 doi: 10.1016/j.neuroimage.2007.11.019 – ident: ref74 doi: 10.1016/j.neuroimage.2011.05.055 – ident: ref64 doi: 10.1214/aos/1176344136 – ident: ref78 doi: 10.1371/journal.pone.0073309 – ident: ref20 doi: 10.1109/JSTSP.2008.2008265 – ident: ref25 doi: 10.1109/83.988962 – start-page: 121 year: 0 ident: ref17 article-title: Incorporating higher dimensionality in joint decomposition of EEG and fMRI publication-title: Proc Eur Signal Process Conf – ident: ref12 doi: 10.1016/j.ijpsycho.2007.04.010 – ident: ref30 doi: 10.1007/978-3-642-15995-4_25 – ident: ref31 doi: 10.1109/TSP.2008.926104 – ident: ref15 doi: 10.1016/j.neuroimage.2012.01.063 – ident: ref43 doi: 10.1109/ICASSP.2010.5495311 – ident: ref10 doi: 10.1109/MSP.2014.2300511 – start-page: 1 year: 2014 ident: ref18 article-title: Fusion analysis of functional MRI data for classification of individuals based on patterns of activation publication-title: Brain Imag Behav – ident: ref59 doi: 10.1016/j.neuroimage.2010.09.073 – ident: ref72 doi: 10.1109/ICASSP.2015.7178612 – volume: 8 start-page: 757 year: 1996 ident: ref80 article-title: A new learning algorithm for blind signal separation publication-title: Advances in neural information processing systems – ident: ref24 doi: 10.1109/MSP.2010.936725 – ident: ref14 doi: 10.1016/j.neuroimage.2012.02.030 – ident: ref6 doi: 10.1002/9780470575758 – ident: ref27 doi: 10.1049/ip-f-2.1993.0054 – ident: ref65 doi: 10.1016/0005-1098(78)90005-5 – ident: ref45 doi: 10.1109/TSP.2010.2053362 – ident: ref44 doi: 10.1109/TSP.2014.2333563 |
| SSID | ssj0003563 |
| Score | 2.450323 |
| Snippet | Fusion of information from multiple sets of data in order to extract a set of features that are most useful and relevant for the given task is inherent to many... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1478 |
| SubjectTerms | (joint) blind source separation Brain models Computer simulation Correlation Data fusion Data integration Data models Datasets Decomposition Feature extraction independent component analysis (ICA) independent vector analysis (IVA) Joints Mathematical models multimodality Source separation Tasks Vector analysis |
| Title | Multimodal Data Fusion Using Source Separation: Two Effective Models Based on ICA and IVA and Their Properties |
| URI | https://ieeexplore.ieee.org/document/7206517 https://www.proquest.com/docview/1728051140 https://www.proquest.com/docview/1753506480 |
| Volume | 103 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB4BJ3ooBVp1gSIjcWuzxImdR2-w7QqQoKhsK26RX7mUJggSVeqv74ydjehDFadEyiSx9HnsmfHMNwCHunBSaCcRAesiYWIdlYrrSHOjbKyTMiB9cZmdfhHnN_JmBd6NtTDOOZ985qZ068_ybWt6CpUd5QlumDxfhVV03EKt1rjqpnLomsZRgVENlwUycXl0fvX504yyuOSU2NOyRPy2CfmuKn8txX5_mW_AxXJkIa3k27Tv9NT8_IO08alDfwHPB0OTHYeZsQkrrtmCZ4_oB7eh8dW331uLch9Up9i8p9gZ82kE7NqH9dm1C-zgbfOeLX60LNAd4xrJqI3a7QM7wX3QMnztbHbMVGPZ2ddwXdAZBLuiaP890ba-hMX842J2Gg39FyKDZkAXqVpLSfaPiA03ti5NrdCZLuosVcI4YqrLHUcvN6nRz1SJMaKQ1JHdyjo1WfoK1pq2ca-B8cTZIi0KrnQu6sRoXJ5VJjLl4sTkNp4AX-JRmYGbnFpk3FbeR4nLymNYEYbVgOEE3o7v3AVmjv9KbxMoo-SAxwT2lrBXg_I-VL5lFxqiAsd1MD5GtaOzFNW4ticZmRLXXxHv_PvLu7BO_w_paHuw1t337g3aL53e9xP3F_3s6l8 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV1Lb9QwEB6VcgAOvApioYCR4ISyTRw7DyQO0LLa7YuKBtRb5FculAR1E1XwV_gr_DhmnGzES9wqcUqkjK3YM57xeMbfADzVmZNCO4kcsC4QJtRBriId6MgoG2qe95w-OEzm78XuiTxZg2_jXRjnnE8-c1N69bF825iOjsq2Uo4GM0qHFMo99-UcHbTly8UOcvMZ57M3xfY8GGoIBAZNWRuoSktJNlyEJjK2yk2l0CHMqiRWwjhCW0tdhJ4ar9BXUtwYkUmqKm5lFZskxm4vwWXcZkjeXw4b1XwshzJtEWoMXPerGzlhvrV79O7tNqWNySnBtSVc_GL1fBmXP3S_N2izG_B9NRV9HsvHadfqqfn6G0rkfzpXN-H6sJFmr3rJvwVrrr4N136CV9yA2t8u_tRYpNtRrWKzjs4GmU-TYMc-bMGOXY9-3tQvWHHesB7OGW0AozJxp0v2Gu28ZdgMx8BUbdniQ_8sKMbCjiiacUawtHeguIjx3oX1uqndPWARdzaLsyxSOhUVNxrNj0pEolzITWrDCUQr9pdmwF6nEiCnpffBwrz0IlOSyJSDyEzg-djmc4888k_qDZKBkXJg_wQ2V1JWDsppWfqSZLjRFvhfT8bPqFYoVqRq13REI2PCMszC-3_v-TFcmRcH--X-4nDvAVylf-lT7zZhvT3r3EPcq7X6kV8zDMoLlrsfTMNFpw |
| 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=Multimodal+Data+Fusion+Using+Source+Separation%3A+Two+Effective+Models+Based+on+ICA+and+IVA+and+Their+Properties&rft.jtitle=Proceedings+of+the+IEEE&rft.au=AdalI%2C+Tulay&rft.au=Levin-Schwartz%2C+Yuri&rft.au=Calhoun%2C+Vince+D.&rft.date=2015-09-01&rft.pub=IEEE&rft.issn=0018-9219&rft.volume=103&rft.issue=9&rft.spage=1478&rft.epage=1493&rft_id=info:doi/10.1109%2FJPROC.2015.2461624&rft.externalDocID=7206517 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon |