ECG Identification Based on PCA and Adaboost Algorithm

Electrocardiogram (ECG) is a weak electrical signal that reflects the process of heart activity, and has multiple excellent features such as uniqueness, stability, versatility, non-repeatability, easy collection and so on. As a new type of biometric authentication technology, the feature extraction and classification of ECG have become a hot research topic. However, there still exists some problems such as poor timeliness and low recognition accuracy. In order to solve these problems, in this paper, we propose an identification method based on Principal Component Analysis (PCA) and Adaboost algorithm. In this method, firstly, we remove the noise from the ECG signal and segment the ECG signal into multiple single heart beats based on detected R points. Then, PCA is used to process heart beat data to reduce feature dimension. Finally, the Adaboost algorithm is used to ensemble weak classifiers to construct a stronger classifier with higher accuracy. In order to validate the effectiveness of the proposed method, we tested our algorithm on 89 healthy subjects of the ECG-ID database. Experimental results show that the proposed method can achieve accuracy rate of 98.88% within 7 s, which demonstrates that the proposed method can provide an effective and practical way for ECG identification.