The Automatic Classification of ECG Based on BP Neural Network
The classification and recognition of ECG are helpful to distinguish and diagnose heart diseases, which also have very important clinical application value for the automatic diagnoses of ECG. The traditional recognition methods need people to extract determinant rules and have no learning ability so that they are unable to simulate the intuition and fuzzy diagnoses function used by doctor very well. The neural network technology has strongpoint of self-organization, self-learning and strong tolerance for error. It provides a new method for the automatic classification of ECG. In this paper, we use BP neural network to do automatic classification for five kinds of ECG which are natural stylebook, paced heart beating, left branch block, right branch block and ventricular tachycardia. The average recognition level is 98.1%. Experiment results show that the neural networ k technology can greatly improve the recognition level of ECG. It has good clinical application value.
Donald C. Wunsch II, Honghua Tan, Dehuai Zeng, Qi Luo
L. L. Yu et al., "The Automatic Classification of ECG Based on BP Neural Network", Advanced Materials Research, Vols. 121-122, pp. 111-116, 2010