Electrocardiogram (ECG) is a practical medical test to diagnose arrhythmia. As a crucial computational application in clinical practice, ECG automatic classification can effectively detect the possible occurrence of cardiovascular disease. At present, the main problems in the automated classification of ECG are due to (1) the complexity of algorithms to capture heartbeats, (2) the complex changes of irregular heartbeats in rhythm or morphology leading to difficulties in the ECG feature recognition, and (3) the needs of large training samples and training time for a machine learning to achieve the ideal recognition accuracy. Given the problems in ECG automatic classification, this study proposes an effective automated classification approach for arrhythmia based on a representative convolution neural network that can decode ECG source files and identify heartbeats accurately based on the detection of QRS waveform from the ECG records. A one-dimensional convolutional neural ne.....

909 hits