ECG-Based Advanced Personal Identification Study With Adjusted (Qi Si)

• Published in: IEEE access 2019, Vol.7, p.40078-40084
• Main Authors: Ko, Hoon, Ogiela, Marek R., Ogiela, Lidia, Mesicek, Libor, Lee, Myoungwon, Choi, Junho, Kim, Pankoo
• Format: Article
• Language: English
• Subjects: Adjusted (Q<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">ᵢ S<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">ᵢ ); Algorithms; Biometrics; electrocardiogram (ECG); Electrocardiography; Feature extraction; Heuristic algorithms; personal identification; QRS complex; Security; Security systems; Silicon; Time-domain analysis; Training
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2903575

Although many security systems with biometric information have appeared, they only have been used the static bio-information, e.g., a fingerprint, ris, and so on. However, because these values are permanent, the attackers can modify and abuse that. To overcome this problem, many researchers would like to use dynamic bio-information, e.g., electrocardiograms (ECG), in security systems. In this case, a sensor in the system must measure the dynamic bio-information instead. The difficulty is that usually, the measured data is different whenever it measures. Therefore if the data is applied to existing algorithms, the results will not be matched and the user will be rejected to pass. This is because an unstable base point, which are Q and S values in the ECG, is used to calculate. To solve this, it suggests an adjusted (Q i * S i ) algorithm that defines a specific distance from the location of R-peak to obtain the Q i and S i values. The algorithm can use balanced input data to determine the features, thereby enabling a highly accurate dynamic biometric system.