Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system
Autore:
Wieben, O; Afonso, VX; Tompkins, WJ;
Indirizzi:
Univ Wisconsin, Dept Elect & Comp Engn, Madison, WI 53706 USA Univ Wisconsin Madison WI USA 53706 ct & Comp Engn, Madison, WI 53706 USA Endocardial Solut Inc, St Paul, MN 55108 USA Endocardial Solut Inc St Paul MN USA 55108 lut Inc, St Paul, MN 55108 USA
Titolo Testata:
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
fascicolo: 5, volume: 37, anno: 1999,
pagine: 560 - 565
SICI:
0140-0118(199909)37:5<560:COPVCU>2.0.ZU;2-E
Fonte:
ISI
Lingua:
ENG
Soggetto:
ELECTROCARDIOGRAM; TACHYARRHYTHMIAS; ARRHYTHMIAS; ALGORITHMS;
Keywords:
beat classification; ECG analysis; fuzzy logic; filter bank; time-frequency analysis;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Engineering, Computing & Technology
Citazioni:
26
Recensione:
Indirizzi per estratti:
Indirizzo: Tompkins, WJ Univ Wisconsin, Dept Elect & Comp Engn, 1415 Johnson Dr, Madison, WI 53706USA Univ Wisconsin 1415 Johnson Dr Madison WI USA 53706 53706USA
Citazione:
O. Wieben et al., "Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system", MED BIO E C, 37(5), 1999, pp. 560-565

Abstract

The classification of heart beats is important for automated arrhythmia monitoring devices. The study describes two different classifiers for the identification of premature ventricular complexes (PVCs) in surface ECGs. A decision-tree algorithm based on inductive learning from a training set and afuzzy rule-based classifier are explained in detail. Traditional features for the classification task are extracted by analysing the heart rate and morphology of the heart beats from a single lead. In addition, a novel set of features based on the use of a filter bank is presented. Filter banks allow for time-frequency-dependent signal processing with low computational effort. The performance of the classifiers is evaluated on the MIT-BIH database following the AAMI recommendations. The decision-tree algorithm has a gross sensitivity of 85.3% and a positive predictivity of 85.2%, whereas the gross sensitivity of the fuzzy rule-based system is 81.3%, and the positivepredictivity is 80.6%.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 09/07/20 alle ore 13:57:33