Comparison of Parallel and Single Neural Networks in Heart Arrhythmia Detection by Using ECG Signal Analysis

In this study, we have presented a method for detecting four common arrhythmias by using wavelet analysis along with the neural network algorithms. The method firstly includes the extraction of feature vectors with wavelet analysis. Then, the vectors will be categorized by means of the neural network into four classes. Input signals are recorded from two different leads. In addition, we have used both continuous and discrete wavelet analyses simultaneously for feature extraction. This results into increasing the accuracy of feature vectors extraction. Also, using the continuous wavelet in a specific scale can lead to better extraction of coefficients as well as more accurate data. In order to decrease the computational efforts and increase the training speed, the dimensions of the feature vectors have been reduced by substituting the wavelet coefficients with their statistical parameters. Furthermore, two approaches are introduced in classification of feature vectors. The first approach comprises four neural networks in the parallel form for detection of four classes, while the second approach makes use of one network for four classes. Numerical simulation results show that in comparison with the previous studies, the proposed methods are more accurate and faster. In addition, it is observed that the second approach has better capabilities in classification of data than the first one. On the other hand, the first approach is believed to have a good function for complicated data spaces.