Title :
A system of biometric authentication based on ECG signal segmentation
Author :
Keshishzadeh, Sarineh ; Rashidi, Saeid
Author_Institution :
Biomed. Eng., Islamic Azad Univ., Tehran, Iran
Abstract :
One of the fundamental difficulties of ECG (Electrocardiogram) based biometric systems is intrabeat variation. In order to decrease these variations and increase the performance of the biometric system, we have proposed a new convolution based method for beat extraction and a waveshape based method for beat segmentation. In the feature extraction stage, thirty spatial and interval features are extracted and they are categorized in six groups using Feature Forward Selection (FFS) method. Feature classification is done by using four classifiers: Nearest Neighbor, Gaussian, Principal Component and Parzen Window data description. The experiment is done on MIT-BIH normal sinus rhythm database and the proposed method is achieved to %2.34±0.19 Equal Error Rate (EER) and %99.73±0.04 Area Under the ROC Curve (AUC) using Parzen Window classifier.
Keywords :
Gaussian processes; biometrics (access control); convolution; electrocardiography; feature extraction; feature selection; medical signal processing; principal component analysis; sensitivity analysis; signal classification; AUC; Area Under the ROC Curve; ECG signal segmentation; EER; Equal Error Rate; FFS; Feature Forward Selection method; Gaussian description; MIT-BIH normal sinus rhythm database; Nearest Neighbor description; Parzen Window classifier; Parzen Window data description; Principal Component description; beat extraction; beat segmentation; biometric authentication; biometric system performance; convolution based method; electrocardiogram; feature classification; feature extraction stage; interval features; intrabeat variation; spatial features; waveshape based method; Biometrics (access control); Conferences; Convolution; Databases; Electrocardiography; Feature extraction; Heart beat; beat extraction; beat segmentation; biometrics; classifier; feature extraction;
Conference_Titel :
Electrical Engineering (ICEE), 2014 22nd Iranian Conference on
Conference_Location :
Tehran
DOI :
10.1109/IranianCEE.2014.6999845