Performance Bounds for Complex-Valued Independent Vector Analysis
Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on signal processing 2020, Vol.68, p.4258-4267 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4267 |
|---|---|
| container_issue | |
| container_start_page | 4258 |
| container_title | IEEE transactions on signal processing |
| container_volume | 68 |
| creator | Kautsky, Vaclav Tichavsky, Petr Koldovsky, Zbynek Adal, Tulay |
| description | Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy are derived for the complex-valued case involving circular and non-circular signals and correlated and uncorrelated datasets. The identification conditions describe when independent sources can be separated from their linear mixture in the statistically consistent manner. The CRLB shows how non-Gaussianty, non-circularity of sources and statistical dependence between datasets influence the attainable separation accuracy. Examples presented in the experimental part confirm the validity of the CRLB. Also, they show certain gap between the attainable accuracy and performance of state-of-the-art algorithms, especially, in case of highly non-circular signals. Hence, there is a room for possible improvements. |
| doi_str_mv | 10.1109/TSP.2020.3009507 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9141450</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9141450</ieee_id><sourcerecordid>2431086084</sourcerecordid><originalsourceid>FETCH-LOGICAL-c361t-bda3948887d57e0fdaeca8689def0cfbdb85acd08918f9907646fa20838183023</originalsourceid><addsrcrecordid>eNo9kE1LAzEQhoMoWKt3wcuC562TTTabHGvxo1CwYC3eQppMoGW7uya7YP-9KS1e5gOedxgeQu4pTCgF9bT6XE4KKGDCAFQJ1QUZUcVpDrwSl2mGkuWlrL6vyU2MOwDKuRIjMl1i8G3Ym8Zi9twOjYtZ2rNZu-9q_M3Xph7QZfPGYYepNH22RtsnYtqY-hC38ZZceVNHvDv3Mfl6fVnN3vPFx9t8Nl3klgna5xtnmOJSysqVFYJ3Bq2RQiqHHqzfuI0sjXUgFZVeKagEF94UIJmkkkHBxuTxdLcL7c-Asde7dgjpiagLzihIAZInCk6UDW2MAb3uwnZvwkFT0EdROonSR1H6LCpFHk6RLSL-44pyyktgf8C1Y9A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2431086084</pqid></control><display><type>article</type><title>Performance Bounds for Complex-Valued Independent Vector Analysis</title><source>IEEE Electronic Library (IEL)</source><creator>Kautsky, Vaclav ; Tichavsky, Petr ; Koldovsky, Zbynek ; Adal, Tulay</creator><creatorcontrib>Kautsky, Vaclav ; Tichavsky, Petr ; Koldovsky, Zbynek ; Adal, Tulay</creatorcontrib><description>Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy are derived for the complex-valued case involving circular and non-circular signals and correlated and uncorrelated datasets. The identification conditions describe when independent sources can be separated from their linear mixture in the statistically consistent manner. The CRLB shows how non-Gaussianty, non-circularity of sources and statistical dependence between datasets influence the attainable separation accuracy. Examples presented in the experimental part confirm the validity of the CRLB. Also, they show certain gap between the attainable accuracy and performance of state-of-the-art algorithms, especially, in case of highly non-circular signals. Hence, there is a room for possible improvements.</description><identifier>ISSN: 1053-587X</identifier><identifier>EISSN: 1941-0476</identifier><identifier>DOI: 10.1109/TSP.2020.3009507</identifier><identifier>CODEN: ITPRED</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Accuracy ; Algorithms ; Audio data ; Biomedical data ; Blind source separation ; Circularity ; complex-valued signal processing ; Covariance matrices ; Cramér-Rao lower bound ; Data analysis ; Datasets ; Electroencephalography ; Frequency-domain analysis ; Functional magnetic resonance imaging ; independent component/vector analysis ; Lower bounds ; non-circular sources ; Probability density function ; Separation ; Signal processing ; Signal processing algorithms ; Vector analysis</subject><ispartof>IEEE transactions on signal processing, 2020, Vol.68, p.4258-4267</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c361t-bda3948887d57e0fdaeca8689def0cfbdb85acd08918f9907646fa20838183023</citedby><cites>FETCH-LOGICAL-c361t-bda3948887d57e0fdaeca8689def0cfbdb85acd08918f9907646fa20838183023</cites><orcidid>0000-0003-0594-2796 ; 0000-0003-0621-4766 ; 0000-0002-1791-5675 ; 0000-0002-7042-0858</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9141450$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4022,27922,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9141450$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kautsky, Vaclav</creatorcontrib><creatorcontrib>Tichavsky, Petr</creatorcontrib><creatorcontrib>Koldovsky, Zbynek</creatorcontrib><creatorcontrib>Adal, Tulay</creatorcontrib><title>Performance Bounds for Complex-Valued Independent Vector Analysis</title><title>IEEE transactions on signal processing</title><addtitle>TSP</addtitle><description>Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy are derived for the complex-valued case involving circular and non-circular signals and correlated and uncorrelated datasets. The identification conditions describe when independent sources can be separated from their linear mixture in the statistically consistent manner. The CRLB shows how non-Gaussianty, non-circularity of sources and statistical dependence between datasets influence the attainable separation accuracy. Examples presented in the experimental part confirm the validity of the CRLB. Also, they show certain gap between the attainable accuracy and performance of state-of-the-art algorithms, especially, in case of highly non-circular signals. Hence, there is a room for possible improvements.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Audio data</subject><subject>Biomedical data</subject><subject>Blind source separation</subject><subject>Circularity</subject><subject>complex-valued signal processing</subject><subject>Covariance matrices</subject><subject>Cramér-Rao lower bound</subject><subject>Data analysis</subject><subject>Datasets</subject><subject>Electroencephalography</subject><subject>Frequency-domain analysis</subject><subject>Functional magnetic resonance imaging</subject><subject>independent component/vector analysis</subject><subject>Lower bounds</subject><subject>non-circular sources</subject><subject>Probability density function</subject><subject>Separation</subject><subject>Signal processing</subject><subject>Signal processing algorithms</subject><subject>Vector analysis</subject><issn>1053-587X</issn><issn>1941-0476</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE1LAzEQhoMoWKt3wcuC562TTTabHGvxo1CwYC3eQppMoGW7uya7YP-9KS1e5gOedxgeQu4pTCgF9bT6XE4KKGDCAFQJ1QUZUcVpDrwSl2mGkuWlrL6vyU2MOwDKuRIjMl1i8G3Ym8Zi9twOjYtZ2rNZu-9q_M3Xph7QZfPGYYepNH22RtsnYtqY-hC38ZZceVNHvDv3Mfl6fVnN3vPFx9t8Nl3klgna5xtnmOJSysqVFYJ3Bq2RQiqHHqzfuI0sjXUgFZVeKagEF94UIJmkkkHBxuTxdLcL7c-Asde7dgjpiagLzihIAZInCk6UDW2MAb3uwnZvwkFT0EdROonSR1H6LCpFHk6RLSL-44pyyktgf8C1Y9A</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Kautsky, Vaclav</creator><creator>Tichavsky, Petr</creator><creator>Koldovsky, Zbynek</creator><creator>Adal, Tulay</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-0594-2796</orcidid><orcidid>https://orcid.org/0000-0003-0621-4766</orcidid><orcidid>https://orcid.org/0000-0002-1791-5675</orcidid><orcidid>https://orcid.org/0000-0002-7042-0858</orcidid></search><sort><creationdate>2020</creationdate><title>Performance Bounds for Complex-Valued Independent Vector Analysis</title><author>Kautsky, Vaclav ; Tichavsky, Petr ; Koldovsky, Zbynek ; Adal, Tulay</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c361t-bda3948887d57e0fdaeca8689def0cfbdb85acd08918f9907646fa20838183023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Audio data</topic><topic>Biomedical data</topic><topic>Blind source separation</topic><topic>Circularity</topic><topic>complex-valued signal processing</topic><topic>Covariance matrices</topic><topic>Cramér-Rao lower bound</topic><topic>Data analysis</topic><topic>Datasets</topic><topic>Electroencephalography</topic><topic>Frequency-domain analysis</topic><topic>Functional magnetic resonance imaging</topic><topic>independent component/vector analysis</topic><topic>Lower bounds</topic><topic>non-circular sources</topic><topic>Probability density function</topic><topic>Separation</topic><topic>Signal processing</topic><topic>Signal processing algorithms</topic><topic>Vector analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kautsky, Vaclav</creatorcontrib><creatorcontrib>Tichavsky, Petr</creatorcontrib><creatorcontrib>Koldovsky, Zbynek</creatorcontrib><creatorcontrib>Adal, Tulay</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kautsky, Vaclav</au><au>Tichavsky, Petr</au><au>Koldovsky, Zbynek</au><au>Adal, Tulay</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Performance Bounds for Complex-Valued Independent Vector Analysis</atitle><jtitle>IEEE transactions on signal processing</jtitle><stitle>TSP</stitle><date>2020</date><risdate>2020</risdate><volume>68</volume><spage>4258</spage><epage>4267</epage><pages>4258-4267</pages><issn>1053-587X</issn><eissn>1941-0476</eissn><coden>ITPRED</coden><abstract>Independent Vector Analysis (IVA) is a method for joint Blind Source Separation of multiple datasets with wide area of applications including audio source separation, biomedical data analysis, etc. In this paper, identification conditions and Cramér-Rao Lower Bound (CRLB) on the achievable accuracy are derived for the complex-valued case involving circular and non-circular signals and correlated and uncorrelated datasets. The identification conditions describe when independent sources can be separated from their linear mixture in the statistically consistent manner. The CRLB shows how non-Gaussianty, non-circularity of sources and statistical dependence between datasets influence the attainable separation accuracy. Examples presented in the experimental part confirm the validity of the CRLB. Also, they show certain gap between the attainable accuracy and performance of state-of-the-art algorithms, especially, in case of highly non-circular signals. Hence, there is a room for possible improvements.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TSP.2020.3009507</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-0594-2796</orcidid><orcidid>https://orcid.org/0000-0003-0621-4766</orcidid><orcidid>https://orcid.org/0000-0002-1791-5675</orcidid><orcidid>https://orcid.org/0000-0002-7042-0858</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1053-587X |
| ispartof | IEEE transactions on signal processing, 2020, Vol.68, p.4258-4267 |
| issn | 1053-587X 1941-0476 |
| language | eng |
| recordid | cdi_ieee_primary_9141450 |
| source | IEEE Electronic Library (IEL) |
| subjects | Accuracy Algorithms Audio data Biomedical data Blind source separation Circularity complex-valued signal processing Covariance matrices Cramér-Rao lower bound Data analysis Datasets Electroencephalography Frequency-domain analysis Functional magnetic resonance imaging independent component/vector analysis Lower bounds non-circular sources Probability density function Separation Signal processing Signal processing algorithms Vector analysis |
| title | Performance Bounds for Complex-Valued Independent Vector Analysis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T02%3A26%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Performance%20Bounds%20for%20Complex-Valued%20Independent%20Vector%20Analysis&rft.jtitle=IEEE%20transactions%20on%20signal%20processing&rft.au=Kautsky,%20Vaclav&rft.date=2020&rft.volume=68&rft.spage=4258&rft.epage=4267&rft.pages=4258-4267&rft.issn=1053-587X&rft.eissn=1941-0476&rft.coden=ITPRED&rft_id=info:doi/10.1109/TSP.2020.3009507&rft_dat=%3Cproquest_RIE%3E2431086084%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2431086084&rft_id=info:pmid/&rft_ieee_id=9141450&rfr_iscdi=true |