ECG Beats Feature Extraction Based on Geometric Algebra

A novel method is proposed in this paper for the feature extraction of electrocardiogram (ECG). The shape characteristic of the QRS complex has been a diagnostic criterion of cardiac arrhythmia. In other words, geometric property of the QRS complex is a very important kind of feature. Different with other feature extraction algorithms, the proposed method utilizes geometric algebra (GA) to extract the geometric features of the QRS complex from the ECG data. The geometric features are fed into an artificial neural networks classifier. To validate the proposed method, we applied it to the MIT-BIH arrhythmia database. The experimental results have shown the effectiveness of the proposed method.