Independent Component Analysis and Blind Signal Separation [electronic resource] : Fifth International Conference, ICA 2004, Granada, Spain, September 22-24, 2004. Proceedings / edited by Carlos G. Puntonet, Alberto Prieto.

By: Puntonet, Carlos G [editor.]Contributor(s): Prieto, Alberto [editor.] | SpringerLink (Online service)Material type: TextTextLanguage: English Series: Lecture Notes in Computer Science: 3195Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg, 2004Description: XLVI, 1270 p. online resourceContent type: text Media type: computer Carrier type: online resourceISBN: 9783540301103Subject(s): Computer science | Software engineering | Coding theory | Computer software | Mathematical statistics | Computer Science | Special Purpose and Application-Based Systems | Algorithm Analysis and Problem Complexity | Computation by Abstract Devices | Coding and Information Theory | Statistics and Computing/Statistics Programs | Signal, Image and Speech ProcessingAdditional physical formats: Printed edition:: No titleDDC classification: 004.6 LOC classification: TK7874.6Online resources: Click here to access online
Contents:
Theory and Fundamentals -- Linear Mixture Models -- Convolutive Models -- Nonlinear ICA and BSS -- Speech Processing Applications -- Image Processing Applications -- Biomedical Applications -- Other Applications -- Invited Contributions.
In: Springer eBooksSummary: In many situations found both in Nature and in human-built systems, a set of mixed signalsisobserved(frequentlyalsowithnoise),anditisofgreatscienti?candtech- logicalrelevanceto beableto isolateor separatethemso thattheinformationin each ofthesignalscanbeutilized. Blind source separation (BSS) research is one of the more interesting emerging ?eldsnowadaysinthe?eldofsignalprocessing.Itdealswiththealgorithmsthatallow therecoveryoftheoriginalsourcesfromasetofmixturesonly.Theadjective“blind” is applied becausethe purposeis to estimate the originalsourceswithoutany a priori knowledgeabouteitherthesourcesorthemixingsystem.Mostofthemodelsemployed in BSS assume the hypothesisabout the independenceof the original sources. Under this hypothesis,a BSS problemcan be consideredas a particularcase of independent componentanalysis(ICA),alineartransformationtechniquethat,startingfromam- tivariate representation of the data, minimizes the statistical dependence between the componentsoftherepresentation.Itcan beclaimed thatmostoftheadvancesin ICA havebeenmotivatedbythesearchforsolutionstotheBSSproblemand,theotherway around,advancesinICAhavebeenimmediatelyappliedtoBSS. ICA and BSS algorithms start from a mixture model, whose parameters are - timated from the observed mixtures. Separation is achieved by applying the inverse mixturemodelto theobservedsignals(separatingorunmixingmodel).Mixturem- els usually fall into three broad categories: instantaneous linear models, convolutive modelsandnonlinearmodels,the?rstonebeingthesimplestbut,in general,notnear realisticapplications.Thedevelopmentandtestofthealgorithmscanbeaccomplished throughsyntheticdataorwithreal-worlddata.Obviously,themostimportantaim(and mostdif?cult)istheseparationofreal-worldmixtures.BSSandICAhavestrongre- tionsalso,apartfromsignalprocessing,withother?eldssuchasstatisticsandarti?cial neuralnetworks. As long as we can ?nd a system that emits signals propagated through a mean, andthosesignalsarereceivedbyasetofsensorsandthereisaninterestinrecovering the originalsources,we have a potential?eld ofapplication forBSS and ICA. Inside thatwiderangeofapplicationswecan?nd,forinstance:noisereductionapplications, biomedicalapplications,audiosystems,telecommunications,andmanyothers. This volume comes out just 20 years after the ?rst contributionsin ICA and BSS 1 appeared . Thereinafter,the numberof research groupsworking in ICA and BSS has been constantly growing, so that nowadays we can estimate that far more than 100 groupsareresearchinginthese?elds. Asproofoftherecognitionamongthescienti?ccommunityofICAandBSSdev- opmentstherehavebeennumerousspecialsessionsandspecialissuesinseveralwell- 1 J.Herault, B.Ans,“Circuits neuronaux à synapses modi?ables: décodage de messages c- posites para apprentissage non supervise”, C.R. de l’Académie des Sciences, vol. 299, no. III-13,pp.525–528,1984.
Tags from this library: No tags from this library for this title. Log in to add tags.
    Average rating: 0.0 (0 votes)
No physical items for this record

Theory and Fundamentals -- Linear Mixture Models -- Convolutive Models -- Nonlinear ICA and BSS -- Speech Processing Applications -- Image Processing Applications -- Biomedical Applications -- Other Applications -- Invited Contributions.

In many situations found both in Nature and in human-built systems, a set of mixed signalsisobserved(frequentlyalsowithnoise),anditisofgreatscienti?candtech- logicalrelevanceto beableto isolateor separatethemso thattheinformationin each ofthesignalscanbeutilized. Blind source separation (BSS) research is one of the more interesting emerging ?eldsnowadaysinthe?eldofsignalprocessing.Itdealswiththealgorithmsthatallow therecoveryoftheoriginalsourcesfromasetofmixturesonly.Theadjective“blind” is applied becausethe purposeis to estimate the originalsourceswithoutany a priori knowledgeabouteitherthesourcesorthemixingsystem.Mostofthemodelsemployed in BSS assume the hypothesisabout the independenceof the original sources. Under this hypothesis,a BSS problemcan be consideredas a particularcase of independent componentanalysis(ICA),alineartransformationtechniquethat,startingfromam- tivariate representation of the data, minimizes the statistical dependence between the componentsoftherepresentation.Itcan beclaimed thatmostoftheadvancesin ICA havebeenmotivatedbythesearchforsolutionstotheBSSproblemand,theotherway around,advancesinICAhavebeenimmediatelyappliedtoBSS. ICA and BSS algorithms start from a mixture model, whose parameters are - timated from the observed mixtures. Separation is achieved by applying the inverse mixturemodelto theobservedsignals(separatingorunmixingmodel).Mixturem- els usually fall into three broad categories: instantaneous linear models, convolutive modelsandnonlinearmodels,the?rstonebeingthesimplestbut,in general,notnear realisticapplications.Thedevelopmentandtestofthealgorithmscanbeaccomplished throughsyntheticdataorwithreal-worlddata.Obviously,themostimportantaim(and mostdif?cult)istheseparationofreal-worldmixtures.BSSandICAhavestrongre- tionsalso,apartfromsignalprocessing,withother?eldssuchasstatisticsandarti?cial neuralnetworks. As long as we can ?nd a system that emits signals propagated through a mean, andthosesignalsarereceivedbyasetofsensorsandthereisaninterestinrecovering the originalsources,we have a potential?eld ofapplication forBSS and ICA. Inside thatwiderangeofapplicationswecan?nd,forinstance:noisereductionapplications, biomedicalapplications,audiosystems,telecommunications,andmanyothers. This volume comes out just 20 years after the ?rst contributionsin ICA and BSS 1 appeared . Thereinafter,the numberof research groupsworking in ICA and BSS has been constantly growing, so that nowadays we can estimate that far more than 100 groupsareresearchinginthese?elds. Asproofoftherecognitionamongthescienti?ccommunityofICAandBSSdev- opmentstherehavebeennumerousspecialsessionsandspecialissuesinseveralwell- 1 J.Herault, B.Ans,“Circuits neuronaux à synapses modi?ables: décodage de messages c- posites para apprentissage non supervise”, C.R. de l’Académie des Sciences, vol. 299, no. III-13,pp.525–528,1984.

There are no comments on this title.

to post a comment.


Implemented and Maintained by Biju Patnaik Central Library.
For any Suggestions/Query Contact to library or Email: library@nitrkl.ac.in OR bpcl-cir@nitrkl.ac.in. Ph:91+6612462103
Website/OPAC best viewed in Mozilla Browser in 1366X768 Resolution.

Powered by Koha