Emotion recognition by using photoplethysmogram (PPG) signal integrating gender differences and age variability /
Emotion plays a significant role in our life and cannot be consciously controlled. It can be expressed by using facial expression, speech and behaviour. Recently, human biological signals are used to recognize emotions. Photoplethysmogram (PPG) is one of the commonly used biological signal due to it...
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: | Emotion plays a significant role in our life and cannot be consciously controlled. It can be expressed by using facial expression, speech and behaviour. Recently, human biological signals are used to recognize emotions. Photoplethysmogram (PPG) is one of the commonly used biological signal due to its advantages that are portable, easy to handle and low power consumption. Therefore, this study is proposed to investigate the strength and reliability of PPG signal to classify emotions in consideration of gender differences and age variability. The reason is because different age and gender may have different reactions toward emotions. Moreover, based on previous literature, little has been said on detecting emotions based on gender and age differences. In this study, a total of 30 subjects were involved which consist of 15 males and 15 females. All subjects were divided into five age groups where each group comprises of three males and three females. In order to acquire the PPG data, Easy Pulse sensor is used to measure the oxygen saturation through the fingertip with the help of Arduino microcontroller. The data is then being captured and converted to text data by using CoolTerm software. During the signal acquisition, subjects were required to watch four videos in order to evoke four types of basic emotions which are calm, happy, fear and sad. Then, the data collected were extracted and classified using three statistical techniques which are standard deviation (SD), maximum amplitudes and Cardioid area graph calculation. Based on our experimentation result, happy is the most notable emotion as compared to other emotions regardless of age and gender factors. It demonstrates the highest SD, maximum amplitudes and Cardioid area calculation irrespective of related conditions. The result is in line with the past research where heart will absorb more oxygen when the person is in a happy state. In terms of gender factor, the outcome showed that females tend to have higher sensitivity towards emotions as compared to males. On the other hand, in terms of age variability analysis, middle age subjects ranged between 21 to 40 years old (which are Group B and Group C) illustrated the highest values of the classification techniques involved in this study as compared to other age groups for all emotions. In contrast, subjects in the age range of 20 years old and below obtained the least. Therefore, based on the overall experimentation results, PPG signals are proven to have great potential in recognising emotions integrating gender differences and age variability. Thus, this study could become an alternative approach to identify emotions as compared to traditional methods. |
|---|---|
| Physical Description: | xxi, 89 leaves : colour illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 80-83). |