Abstract: In order to improve the rate of human identification based on ECG, a novel ECG human identification approach（IWT-ABC-SVM） is proposed based on wavelet analysis and Support Vector Machine. Wavelet threshold function is used to denoise the ECG, and the ECG features are extracted; the ECG features are input to Support Vector Machine to learn, and the parameters of Support Vector Machine are optimized by artificial bee colony algorithm; the human identification classifier is established and the simulation experiment is carried out by using MIT-BIH ECG data. The results show that compared with other identification methods, the proposed method has improved the identification accuracy and reliability.

Key words: Electrocardiography（ECG） signal, human identification, wavelet denoise, artificial bee colony algorithm, Support Vector Machine（SVM）

摘要： 为了提高心电图（ECG）信号的身份识别正确率，提出一种小波变换和支持向量机相融合的ECG身份识别方法（IWT-ABC-SVM）。采用一种小波阈值函数对ECG进行去噪处理，提取ECG特征，将ECG特征输入到支持向量机中进行学习，采用人工蜂群算法优化支持向量机参数，建立ECG的身份识别模型，采用MIT-BIH心电图数据进行仿真测试。仿真结果表明，相对于其他识别方法，IWT-ABC-SVM提高了ECG身份识别的正确率和可靠性。

关键词: 心电图信号, 身份识别, 小波去噪, 人工蜂群算法, 支持向量机