The Research of Arrhythmia Algorithm Based on Fuzzy Neural Network

This paper presents a wavelet-based algorithm for arrhythmia discrimination. The algorithm analyses the Electrocardiograph (ECG) signal by using the continuous wavelet transform and its rule in different scales of variation and it can automatically distinguish arrhythmia. The correct detection rate of the ventricular contraction and a trial premature beats are above 90%. Then, a method based on Fuzzy neural network (FNN) is developed to create fuzzy membership functions for classification of cardiac arrhythmia in this paper. The FNN of Takagi-Sugeno type is constructed firstly. The R-R interval and QRS complex are used as the inputs of the FNN. Then Cam Delta learning algorithm is used to train the FNN through which the membership functions can be gotten. The fuzzy recognition using these membership functions can discriminate cardiac arrhythmia. The verification result shows that this method is effective.