Ventricular Fibrillation Detection Based on Empirical Mode Decomposition

Automatic detection of ventricular fibrillation (VF) is of great important for automated external defibrillators (AEDs). However, it is a difficult issue due to the similarity between ventricular fibrillation and ventricular tachycardia (VF). In this paper, a novel scheme based on empirical mode decomposition (EMD) is proposed to disclosure the underlying information of VF, VF and normal electrocardiogram (ECG). The intrinsic mode functions (IMFs), especially the first IMF, may demonstrate distinct properties of different types of ECG signals. Two efficient features derived from IMFs are used for discrimination, namely Frequency Spectrum Entropy (SpEn) and Energy Rate ER_IMF. Data from the standard database of MIF-BIH and AHA are used to evaluate the method. With Bayes theory classifier, our method can successfully differentiate VF, VF and normal ECG with the accuracy of 99.78%, 99.78% and 100% respectively. Thus it may provide a new vision for understanding mechanism of cardiac activity and an effective method for VF detection.