基于心电信号的身份验证方法  

Study of authentication based on electrocardiogram

作　　者：祝宝文 戴敏[1] 张晓丹[1] DAI Min ZHU Bao-wen ZHANG Xiao-dan(School of Computer and Communication Engineering, Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, Chin)

机构地区：[1]天津理工大学计算机与通信工程学院天津市智能计算与软件新技术重点实验室,天津300384

出　　处：《天津理工大学学报》2017年第1期16-19,共4页Journal of Tianjin University of Technology

基　　金：天津市自然科学基金(15JCYBJC15800)

摘　　要：本文提出一种基于加权相关系数的心电信号(ECG)身份验证方法,该方法根据心电波形的贡献率排序,运用二阶差分的阈值确定个体心电模板的数目,并选取出具有代表性的心电模板,再依据贡献率排序采用加权相关系数方法进行基于ECG的身份验证.该方法可以解决基于相关系数身份验证中选取模板数量和模板不合理对身份验证正确接受率(TPR)影响.在MIT-BIH数据集和真实环境下大量实验表明,与传统的相关系数方法相比,本文方法在上述数据中身份验证的平均TPR分别提高了5.66%和6.75%.In this paper, a template selection method is proposed based on contribution rate of each electrocardiogram（ECG） waveform in the data set, and the second-order differential threshold value is used to determine the number of templates and select representative ECG templates for each individual. The weighted correlation coefficient method is proposed for ECG authentication, and weights are calculated by the sorted sequence of contribution rate. The method is used to solve the influence of determine of template number and template is not reasonable on the true positive rate （TPR） of authentication. The performance of the presented method is tested on the MIT-BIH ECG data set and the hand ECG data collected in real scenery. Comparing with the traditional correlation coefficient method, experimental results show that the average TPR are increased 5.66% and 6.75% respectively when using the presented method.

关 键 词：身份验证 心电模板 相关系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]