Mostra el registre d'ítem simple
Dimensionality reduction oriented toward the feature visualization for ischemia detection
dc.contributor.author | Delgado-Tejos, Edilson |
dc.contributor.author | Perera Lluna, Alexandre |
dc.contributor.author | Vallverdú Ferrer, Montserrat |
dc.contributor.author | Caminal Magrans, Pere |
dc.contributor.author | Castellanos Dominguez, German |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial |
dc.date.accessioned | 2010-10-15T09:08:42Z |
dc.date.available | 2010-10-15T09:08:42Z |
dc.date.created | 2009-03-16 |
dc.date.issued | 2009-03-16 |
dc.identifier.citation | Delgado-Tejos, E. [et al.]. Dimensionality reduction oriented toward the feature visualization for ischemia detection. "IEEE transactions on information technology in biomedicine", 16 Març 2009, vol. 13, núm. 4, p. 590-598. |
dc.identifier.issn | 1089-7771 |
dc.identifier.uri | http://hdl.handle.net/2117/9713 |
dc.description.abstract | An effective data representation methodology on high-dimension feature spaces is presented, which allows a better interpretation of subjacent physiological phenomena (namely, cardiac behavior related to cardiovascular diseases), and is based on search criteria over a feature set resulting in an increase in the detection capability of ischemic pathologies, but also connecting these features with the physiologic representation of the ECG. The proposed dimension reduction scheme consists of three levels: projection, interpretation, and visualization. First, a hybrid algorithm is described that projects the multidimensional data to a lower dimension space, gathering the features that contribute similarly in the meaning of the covariance reconstruction in order to find information of clinical relevance over the initial training space. Next, an algorithm of variable selection is provided that further reduces the dimension, taking into account only the variables that offer greater class separability, and finally, the selected feature set is projected to a 2-D space in order to verify the performance of the suggested dimension reduction algorithm in terms of the discrimination capability for ischemia detection. The ECG recordings used in this study are fromthe European ST–T database and from the Universidad Nacional de Colombia database. In both cases, over 99% feature reduction was obtained, and classification precision was over 99% using a five-nearest-neighbor classifier (5-NN). |
dc.format.extent | 9 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica |
dc.subject.lcsh | Ischemia -- diagnosis |
dc.subject.lcsh | Heart -- Diseases -- Diagnosis -- Data processing |
dc.subject.lcsh | Wavelet transform |
dc.subject.lcsh | Multidimensional analysi |
dc.title | Dimensionality reduction oriented toward the feature visualization for ischemia detection |
dc.type | Article |
dc.subject.lemac | Cor -- Malalties |
dc.subject.lemac | Isquèmia -- Investigació -- Programes informàtics |
dc.contributor.group | Universitat Politècnica de Catalunya. SISBIO - Senyals i Sistemes Biomèdics |
dc.identifier.doi | 10.1109/TITB.2009.2016654 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4801963&tag=1 |
dc.rights.access | Open Access |
local.identifier.drac | 3257449 |
dc.description.version | Postprint (published version) |
local.citation.author | Delgado-Tejos, E.; Perera, A.; Vallverdú, M.; Caminal, P.; Castellanos Dominguez, G. |
local.citation.publicationName | IEEE transactions on information technology in biomedicine |
local.citation.volume | 13 |
local.citation.number | 4 |
local.citation.startingPage | 590 |
local.citation.endingPage | 598 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [1.391]
-
Articles de revista [70]