A short-time multifractal approach for arrhythmia detection based on fuzzyneural network

We have proposed the notion of short-time multifractality and used it to de velop a novel approach for arrhythmia detection. Cardiac rhythms are charac terized by short-time generalized dimensions (STGDs), and different kinds o f arrhythmias are discriminated using a neural network. To advance the accu racy of classification, a new fuzzy Kohonen network, which overcomes the sh ortcomings of the classical algorithm, is presented. In our paper, the pote ntial of our method for clinical uses and real-time detection was examined using 180 electrocardiogram records [60 atrial fibrillation, 60 ventricular fibrillation, and 60 ventricular tachycardial. The proposed algorithm has achieved high accuracy (more than 97%) and is computationally fast in detec tion.