Identification of cardiac arrhythmias using a damped exponential-predominant frequency algorithm
暂无分享,去创建一个
The authors describe a new approach for the discrimination of ventricular fibrillation (VF) from ventricular tachycardia (VT) based on a damped exponential (DE) modeling algorithm. Classification is achieved by simple linear separation applied to a novel feature, dubbed predominant frequency (PF), derived from the DE model. Tests conducted using 70 episodes drawn from the MIT-BIH malignant arrhythmia database produced total predictive accuracy exceeding 98%.
[1] P. M. Clarkson,et al. A robust sequential detection algorithm for cardiac arrhythmia classification , 1996 .
[2] Peter M. Clarkson,et al. Prony residual analysis for the identification of cardiac arrhythmias , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.
[3] Kai-Bor Yu,et al. Total least squares approach for frequency estimation using linear prediction , 1987, IEEE Trans. Acoust. Speech Signal Process..