Photoplethysmogram based biometric identification incorporating age, gender and time variability /
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 Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2017
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| 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. For time variability analysis, a total of 5 PPG signals were collected from a publicly available online repository, which is MIMIC II Waveform Database, version 3, part 3 for two different periods and then undergoes pre-processing using a low pass filter. After that, the signals were segmented and later differentiated to produce APG signals and lastly the signals were classified using the classifiers mentioned. Based on the experimentation results, the accuracy obtained for PPG was up to 90% and for APG as high as 92.86%. To conclude, PPG and APG signals are capable to be used for biometric identification purposes as the results prove that even though the data were taken from different age, gender group and various time, the system is able to identify the person. |
|---|---|
| Physical Description: | xvii, 99 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 90-92). |