Photoplethysmogram (PPG) based biometric identification system for twins incorporating age and gender variability /
Traditional biometric system has been widely implemented in most of the countries as a security mechanism that can be found almost everywhere either in the government or private sector due to its capability to identify a person correctly in any condition whether a person is having a twin or not. How...
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: | Traditional biometric system has been widely implemented in most of the countries as a security mechanism that can be found almost everywhere either in the government or private sector due to its capability to identify a person correctly in any condition whether a person is having a twin or not. However, due to its limitation which can be duplicated and stolen, a recent biometric modality involving biomedical signals such as PPG was introduced. This study has been motivated by the new research area using PPG signal to identify twins incorporating age and gender variability. In the first phase of the study, it focused on the PPG based biometric identification for twins as an alternative to the traditional methods to identify twins that are being used nowadays. Then, in the second phase of the study, age and gender variability will be incorporated in this research as to analyze the implications of including these aspects. There are numerous researches and study about the PPG based biometric identification system and twin recognition where some of them showed positive results. However, to the best of our knowledge, biometric identification system for twins by using PPG signal and incorporating age and gender variability are still under-researched. Therefore, these issues will be the main focus of the study. A range of 8 to 21 numbers of subjects were used for experimentation purposes and a lowpass filter is applied to remove unwanted noise from the signal. Distinctive features which are the systolic, diastolitic peak and dicrotic notch were extracted from the filtered PPG signals. Later, Bayes Network (BN), Naïve Bayes (NB), Radial Basis Function (RBF) and Multilayer Perceptron (MLP) were used to classify the subjects using the discriminant features. Based on the experimentation results, classification accuracies ranging from 87.5% to 100% were achieved from the studies. The result proves that using PPG signals incorporating age variability can be used as an alternative mechanism to identify twins besides using the traditional methods. |
|---|---|
| Physical Description: | xvii, 109 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 91-95). |