Evaluating the use of ECG signal in low frequencies as a biometry

• Published in: Expert systems with applications Vol. 41; no. 5; pp. 2309 - 2315
• Main Authors: Luz, Eduardo José da S., Menotti, David, Schwartz, William Robson
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.04.2014; Elsevier
• Subjects: Applied sciences; Biological and medical sciences; Biometrics; Classification; Computer science; control theory; systems; Data processing. List processing. Character string processing; ECG; Electrocardiography. Vectocardiography; Electrodiagnosis. Electric activity recording; Exact sciences and technology; Feature extraction; Fraud; Frequency sampling; Investigative techniques, diagnostic techniques (general aspects); Low frequencies; Majority voting scheme; Medical sciences; Memory organisation. Data processing; Software; Strategy; Support vector machines; Training; Biometrics; ECG; Frequency sampling; Majority voting scheme; Measurement; Computer vision; Scalability; Image processing; Face recognition; Pattern recognition; Fraud; Low frequency; Sampling frequency; Voting; Facies; Vector support machine; Electrocardiography; Selection criterion; Feature extraction; High frequency; Pattern extraction
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2013.09.028

•The viability of identification based on ECG signal sampled in low frequencies.•Evaluating the use of four feature representations for person identification.•Majority voting scheme of classified samples provides high accuracy.•Evaluating the impact of the number of samples for learning and identification.•Evaluating the biometry scalability when the number of subjects is increased. Traditional strategies, such as fingerprinting and face recognition, are becoming more and more fraud susceptible. As a consequence, new and more fraud proof biometrics modalities have been considered, one of them being the heartbeat pattern acquired by an electrocardiogram (ECG). While methods for subject identification based on ECG signal work with signals sampled in high frequencies (>100Hz), the main goal of this work is to evaluate the use of ECG signal in low frequencies for such aim. In this work, the ECG signal is sampled in low frequencies (30Hz and 60Hz) and represented by four feature extraction methods available in the literature, which are then feed to a Support Vector Machines (SVM) classifier to perform the identification. In addition, a classification approach based on majority voting using multiple samples per subject is employed and compared to the traditional classification based on the presentation of single samples per subject each time. Considering a database composed of 193 subjects, results show identification accuracies higher than 95% and near to optimality (i.e., 100%) when the ECG signal is sampled in 30Hz and 60Hz, respectively, being the last one very close to the ones obtained when the signal is sampled in 360Hz (the maximum frequency existing in our database). We also evaluate the impact of: (1) the number of training and testing samples for learning and identification, respectively; (2) the scalability of the biometry (i.e., increment on the number of subjects); and (3) the use of multiple samples for person identification.