EEG-based emotional stress recognition using deep learning techniques
In this fast-paced world, one must be able to multi-task with jobs in hand and this generates stress. Stress come in different forms and everyone experiences it differently. Stress may not be bad as stress can be the motivation factor of pushing us to get work done daily. However, negative stress ca...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/75408 |
| _version_ | 1824454038560702464 |
|---|---|
| author | Lai, Michelle Wei Ting |
| author2 | Wang Lipo |
| author_facet | Wang Lipo Lai, Michelle Wei Ting |
| author_sort | Lai, Michelle Wei Ting |
| collection | NTU |
| description | In this fast-paced world, one must be able to multi-task with jobs in hand and this generates stress. Stress come in different forms and everyone experiences it differently. Stress may not be bad as stress can be the motivation factor of pushing us to get work done daily. However, negative stress can cause mental and physical distress, causing serious health problems. Therefore, research has been done to measure stress with a stress recognition system so that the risk of stress causing health problems can be reduced. In this study, we will be using Electroencephalograph (EEG) as an indicator to evaluate stress. This indicator has been used in many previous research studies by scientists and researchers. It has also been proven that EEG can be used to identify stress due to the significant correlation between stress and EEG power. There have been many different types of EEG classifiers used in the past studies. However, not much research has been done in using convolutional neural networks (CNN) to classify EEG signals. In this study, we will be investigating if using a deep learning model as an emotion stress classifier be effective. We will be comparing the accuracies of Support Vector Machine (SVM) subject dependent and CNN subject dependent. We will also be comparing CNN subject dependent and CNN subject independent methods. |
| first_indexed | 2025-02-19T03:15:58Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/75408 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:15:58Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/754082023-07-07T17:31:18Z EEG-based emotional stress recognition using deep learning techniques Lai, Michelle Wei Ting Wang Lipo School of Electrical and Electronic Engineering Fraunhofer Singapore DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing In this fast-paced world, one must be able to multi-task with jobs in hand and this generates stress. Stress come in different forms and everyone experiences it differently. Stress may not be bad as stress can be the motivation factor of pushing us to get work done daily. However, negative stress can cause mental and physical distress, causing serious health problems. Therefore, research has been done to measure stress with a stress recognition system so that the risk of stress causing health problems can be reduced. In this study, we will be using Electroencephalograph (EEG) as an indicator to evaluate stress. This indicator has been used in many previous research studies by scientists and researchers. It has also been proven that EEG can be used to identify stress due to the significant correlation between stress and EEG power. There have been many different types of EEG classifiers used in the past studies. However, not much research has been done in using convolutional neural networks (CNN) to classify EEG signals. In this study, we will be investigating if using a deep learning model as an emotion stress classifier be effective. We will be comparing the accuracies of Support Vector Machine (SVM) subject dependent and CNN subject dependent. We will also be comparing CNN subject dependent and CNN subject independent methods. Bachelor of Engineering 2018-05-31T03:57:28Z 2018-05-31T03:57:28Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/75408 en Nanyang Technological University 47 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Lai, Michelle Wei Ting EEG-based emotional stress recognition using deep learning techniques |
| title | EEG-based emotional stress recognition using deep learning techniques |
| title_full | EEG-based emotional stress recognition using deep learning techniques |
| title_fullStr | EEG-based emotional stress recognition using deep learning techniques |
| title_full_unstemmed | EEG-based emotional stress recognition using deep learning techniques |
| title_short | EEG-based emotional stress recognition using deep learning techniques |
| title_sort | eeg based emotional stress recognition using deep learning techniques |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
| url | http://hdl.handle.net/10356/75408 |
| work_keys_str_mv | AT laimichelleweiting eegbasedemotionalstressrecognitionusingdeeplearningtechniques |