Identification of stress incorporating gender differences and time of day effect based on race using photoplethysmogram (PPG) signal /
Stress plays an important role in people's daily life and can give various effects to the community. There are several methods to identify stress and the most common method is questionnaire. However, it is inefficient due to time consuming and may not be accessible at all times. Ironically, ide...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Engineering, International Islamic University Malaysia,
2019
|
| 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: | Stress plays an important role in people's daily life and can give various effects to the community. There are several methods to identify stress and the most common method is questionnaire. However, it is inefficient due to time consuming and may not be accessible at all times. Ironically, identifying stress using physiological signals such as electrocardiogram (ECG), electroencephalogram (EEG) and photoplethysmogram (PPG) are more reliable as subjects cannot hide their emotions on purpose. However, ECG and EEG are exposed to various kind of noise and not convenient in acquiring the signals. Thus, in this study, PPG signal is implemented because of its simplicity, low power consumption and convenient to use. Although there are many research works on stress identification, little has been laid out on gender differences and time of day effect based on race, affecting stress levels. Thus, stress recognition through bio-signals by incorporating gender differences and time of day effect based on race is proposed. The scope of this study only covers healthy subjects with different gender, time of day effect and race. PPG signals were acquired from 30 subjects (15 males and 15 females) with diverse races which are Malaysian, Bangladesh, African, Arab and Chinese. The subjects undergo two conditions which are normal and stress conditions. In order to compare the normal and stress conditions, discriminant features are extracted by detecting the peak and Cardioid area of PPG signals. The outcomes show that females experienced higher level of stress as compared to males. This is due to their average systolic peak and Cardioid area differences which are much higher than males with the values of 102.67mV and 9010.67〖unit〗^2, respectively. For time of day effect, subjects experienced higher level of stress in the morning as high as 105.25mV and 24257.5〖unit〗^2 for average systolic peak and Cardioid area differences, respectively, as compared to the evening time. Meanwhile, for race factor in general, Arab subjects reported the highest level of stress due to skin thickness and most of the signals were acquired in the morning. On the other hand, the outcomes based on race according to gender differences, male subjects show the same pattern with race factor regardless of gender differences. Furthermore, from the overall results, it is found that race gives the foremost variations of average percentage changes towards the systolic peak. Moreover, Arab subjects tend to give the highest percentage changes of systolic peak which is 21%. However, previous study did not cover the most significant factor for identification of stress which is race. Therefore, this study managed to improve the previous study and determining the most significant factor that leads to highest percentage changes of average systolic peak towards stress. This study also achieved almost similar range of systolic peak differences for normal and stress conditions with previous study which is 30mV to 160 mV. Based on these results, it shows that PPG signals are capable to detect stress incorporating gender differences and time of day effect based on race. Thus, PPG signal can be applied as an alternative method to recognize stress complimenting the existing stress detection techniques. |
|---|---|
| Physical Description: | xix, 96 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 92-94). |