Photoplethysmogram based lie detection incorporating race differences /
This research investigates the feasibility of a lie detector system based on photoplethysmogram (PPG) signal. Lie detector notes physiological changes of a subject commonly under Guilty Knowledge Test (GKT). The proposed research methodology consists of Easy Pulse sensor that captures PPG signal whe...
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: | This research investigates the feasibility of a lie detector system based on photoplethysmogram (PPG) signal. Lie detector notes physiological changes of a subject commonly under Guilty Knowledge Test (GKT). The proposed research methodology consists of Easy Pulse sensor that captures PPG signal where oxygen saturation is measured with the help of Arduino microcontroller and a software named CoolTerm which converts the captured data in a text data. Under GKT, the subject has to answer with a YES or NO. Analyzing the data with the help of MATLAB software shows that, the PPG data decision making techniques show lower results of standard deviation, systolic peak differences and Cardiod area calculations corresponding to lie condition where normal conditions for these three parameters are higher. In the first part of the research, PPG data were collected from 6 subjects and classification performances show lower results of the 3 parameter calculations corresponding to lie condition. Whereas, the second part of the research was performed to investigate the robustness of the system where 15 subjects were taken from people of different races. Completing analysis of the PPG data, results of standard deviation, systolic peaks differences and Cardiod area calculations were lower for lie condition. The proposed system can detect lie in different subject's physical condition such as subject is sweating, different body temperature, skin problem where most of the current system is unable to detect lie. The implementation of the proposed method system is very cheap and very easy to apply as compared to other current systems. Therefore, based on the experimentation results, PPG signals have great potential for lie detection, and the capability to detect lie regardless of race opens up to new research areas in the future. |
|---|---|
| Physical Description: | xiv, 60 leaves : colour illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 54-58). |