 Partially Supervised Approach in Signal RecognitionCatalina Cocianu (), Luminita State (), Doru Constantin () and Corina Sararu () Informatica Economica, 2009, vol. 13, issue 3, 153-164 Abstract: The paper focuses on the potential of principal directions based approaches in signal classification and recognition. In probabilistic models, the classes are represented in terms of multivariate density functions, and an object coming from a certain class is modeled as a random vector whose repartition has the density function corresponding to this class. In cases when there is no statistical information concerning the set of density functions corresponding to the classes involved in the recognition process, usually estimates based on the information extracted from available data are used instead. In the proposed methodology, the characteristics of a class are given by a set of eigen vectors of the sample covariance matrix. The overall dissimilarity of an object X with a given class C is computed as the disturbance of the structure of C, when X is allotted to C. A series of tests concerning the behavior of the proposed recognition algorithm are reported in the final section of the paper. Keywords: signal processing; classification; pattern recognition; compression/decompression (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:aes:infoec:v:13:y:2009:i:3:p:153-164 Access Statistics for this article Informatica Economica is currently edited by Ion Ivan More articles in Informatica Economica from Academy of Economic Studies - Bucharest, Romania Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.