1.
Military Medical Sciences
; (12): 829-832,838, 2016.
Article
de Chinois
| WPRIM
| ID: wpr-605268
RÉSUMÉ
Objective To develop a BP neural network to differentiate between ventricular fibrillation( VF) and non-VF rhythms.Methods Eighteen metrics were extracted from the ECG signals.Each of these metrics respectively characterized each aspect of the signals, such as morphology, gaussianity, spectra, variability, and complexity.These metrics were regarded as the input vector of the BP neural network.After training, a classifier used for VF and non-VF rhythm classification was obtained.Results and Conclusion The constructed BP neural network was tested with the databases of VFDB and CUDB, and the accuracy was 98.61%and 95.37%, respectively.