On node selection for classification in correlated data sets

R. Cristescu

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    Samenvatting

    Consider a system which can be in a finite number of states. Given a large number of characteristics which are measured, representing the system, we are concerned with the selection of a subset of characteristics of (small) given cardinality, for which the classification of the system according to one of the states in the state set is optimal according to the Rayleigh quotient criterion. This problem is relevant in various scenarios where a few explanatory variables have to be selected from a large set of candidates, including sensor selection in sensor networks, classification in image processing, and feature selection in data mining for bioinformatics applications. We show that the optimization amounts to finding the submatrix of the features covariance matrix for which the sum of elements of the inverse is maximized, and we present bounds which relate this optimization to a similar metric based on elements of the original covariance matrix.
    Originele taal-2Engels
    Titel42nd Annual Conference on Proceedings of Information Sciences and Systems, 2008. CISS 2008
    Plaats van productiePiscataway
    UitgeverijInstitute of Electrical and Electronics Engineers
    Pagina's1064-1068
    ISBN van geprinte versie978-1-4244-2246-3
    DOI's
    StatusGepubliceerd - 2008
    Evenement42nd Annual Conference on Information Sciences and Systems (CISS 2008), March 19-21, 2008, Princeton, NJ, USA - Princeton, NJ, Verenigde Staten van Amerika
    Duur: 19 mrt. 200821 mrt. 2008

    Congres

    Congres42nd Annual Conference on Information Sciences and Systems (CISS 2008), March 19-21, 2008, Princeton, NJ, USA
    Verkorte titelCISS 2008
    Land/RegioVerenigde Staten van Amerika
    StadPrinceton, NJ
    Periode19/03/0821/03/08
    Ander42nd Annual Conference on Information Sciences and Systems, 2008. CISS 2008

    Vingerafdruk

    Duik in de onderzoeksthema's van 'On node selection for classification in correlated data sets'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit