Photoplethysmogram based biometric identification incorporating different age and gender group
Biometric is the authentication and identification of a person by measuring or estimating their physiological characteristics. First generation biometric such as fingerprint, signature and voice have drawback and easily can be duplicated which lead to serious identity theft crime. Therefore, second...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Faculty of Electronic and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM)
2018
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/63236/7/63236%20%20Photoplethysmogram%20based%20biometric%20identification%20incorporating%20different%20age%20and%20gender%20group%20SCOPUS.pdf http://irep.iium.edu.my/63236/13/63236%20%20Photoplethysmogram%20based%20biometric%20identification%20incorporating%20different%20age%20and%20gender%20group_article.pdf http://irep.iium.edu.my/63236/ http://journal.utem.edu.my/index.php/jtec/article/view/3639/2634 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Islam Antarabangsa Malaysia |
| Language: | English English |
| Summary: | Biometric is the authentication and identification of a person by measuring or estimating their physiological characteristics. First generation biometric such as fingerprint, signature and voice have drawback and easily can be duplicated which lead to serious identity theft crime. Therefore, second generation of biometric was introduced by using bio-signal. This study evaluates the possibility of applying PPG as biometric identification system incorporating different age, gender group, and time variability. A total of 36 subjects were involved in this study consists of 18 males and 18 females for age difference and gender analysis. The PPG signals were taken in resting state by using pulse oximeter. The PPG signal was differentiated twice in order to form APG signal. These signals then undergo pre-processing and the segmentation process was done by using MATLAB. The highest peaks from the signal was used as reference point to determine the appropriate distance for one cycle of both signal. Then, the signals were classified by four commonly used classifiers which are Bayes Network, Naïve Bayes, Multilayer Perceptron, and Radial Basis Function. The outcome from this study suggested the accuracy up to 100% for different age group, 91.11% for female subjects and 95% for male subjects. |
|---|