EEG-based stress recognition using deep learning techniques
Electroencephalography is implemented in neural technology and biological science these years successfully and has been combined with deep learning and artificial neural network to classify and judge the information of electroencephalography signals. This project uses a deep learning model, Convolut...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/150207 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Electroencephalography is implemented in neural technology and biological science these years successfully and has been combined with deep learning and artificial neural network to classify and judge the information of electroencephalography signals. This project uses a deep learning model, Convolutional Block Attention Module, to judge the stress, which means mental pressure. Because of the feature of CBAM, The convolutional block attention module can be seamlessly combined or fused with any CNN model with the the negligible overhead. And it can be trained end-to-end together with the basic CNN, since its lightweight and general characteristics. Dataset provides two levels of stress and the stress is induced by arithmetic tasks and resting state. The accuracy achieves 89 percent in detecting three levels of stress, which contains high level, low level, and resting level. |
|---|