基于遗传算法优化BP神经网络在心电图身份识别中的应用

Human identification using electrocardiograms based on generic algorithm-back propagation neural network

背景:近年来的医学研究表明心电图具有稳定性和惟一性,且易于采集,不能仿造和复制,符合用于身份识别的生物特征所具备的条件。心电图身份识别技术具有重要的现实意义和广泛的应用前景。目的:观察基于遗传算法优化的BP神经网络在心电图身份识别中的应用效果。方法:将基于遗传算法优化的BP神经网络用于心电图身份识别。首先,采用小波技术消除噪声干扰并提取Ⅱ导联P波、QRS波、T波特征点;其次,选择包含个体身份信息的幅值、间期特征作为输入向量,设计BP神经网络分类器;然后,采用遗传算法对BP网络的权值和阈值进行优化,实现身份识别;最后采用临床数据检验该方法的有效性。结果与结论:以30个人为实验样本,平均识别准确率达到96.3%。提示基于遗传算法优化的BP神经网络身份识别算法识别准确率高,可以有效应用于心电图身份识别。

BACKGROUND：Electrocardiogram（ECG） is stable and simple to collect,and prevents reproduction or replication.Therefore,ECG identification technology has important realistic meaning and broad application prospect.OBJECTIVE：To observe the application of ECG human identification based on generic algorithm（GA） BP neural network.METHODS：A novel approach using ECG based on GA for human identification was investigated.First,the noise was reduced in preprocessing and features of P,QRS complex and T waves from lead II were extracted using wavelet transform.Second,the features of the amplitude and the interval related to human identification were selected.Then,the BP neural network classifier with optimization of GA for human identification was designed.Finally,the validity of the proposed method was verified using the clinical data.RESULTS AND CONCLUSION：A total of 30 people served as samples and the average identification accuracy was 96.3%.Results showed that ECG human identification based on generic algorithm（GA） BP neural network has high accuracy and can be effectively used in ECG human identification.