Please use this identifier to cite or link to this item:
Title: EEG-based stress recognition using deep learning techniques
Authors: Lu, Jinduo
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Lu, J. (2021). EEG-based stress recognition using deep learning techniques. Master's thesis, Nanyang Technological University, Singapore.
Abstract: 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.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
LU_JINDUO G2002027F.pdf
  Restricted Access
2.15 MBAdobe PDFView/Open

Page view(s)

Updated on May 14, 2022


Updated on May 14, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.