.png){kind=icon}
返回
Cognitive Workload Estimation Using Variational Autoencoder and Attention-Based Deep Model
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2022.3163020.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The estimation of cognitive workload using electroencephalogram (EEG) is an emerging research area. However, due to poor spatial resolution issues, features obtained from EEG signals often lead to poor classification results. As a good generative model, the variational autoencoder (VAE) extracts the noise-free robust features from the latent space that lead to better classification performance. The spatial attention-based method [convolutional block attention module (CBAM)] can improve the spatial resolution of EEG signals. In this article, we propose an effective VAE-CBAM-based deep model for estimating cognitive states from topographical videos. Topographical videos of four different conditions [baseline (BL), low workload (LW), medium workload (MW), and high workload (HW)] of the mental arithmetic task are taken for the experiment. Initially, the VAE extracts localized features from input images (extracted from topographical video), and CBAM infers the spatial-channel-level's attention features from those localized features. Finally, the deep CNN-BLSTM model effectively learns those attention-based spatial features in a timely distributed manner to classify the cognitive state. For four-class and two-class classifications, the proposed model achieves 83.13% and 92.09% classification accuracy, respectively. The proposed model enhances the future research scope of attention-based studies in EEG applications.
Keyword:
Convolutional block attention module (CBAM)
convolutional neural network (CNN)
electroencephalogram (EEG)
long short-term memory (LSTM)
variational autoen-coder (VAE)
期刊
IF:
4.9
论文数:
1.0K
被引数:
3.5K
机构
引用论文
Conodontos carboníferos de la sección del río Cares (Unidad de Picos de Europa, Zona Cantábrica, NO de España).png)
Geobios
OAAI
GeobiosIF0
OAAI分享收藏Machine Learning Framework for the Detection of Mental Stress at Multiple LevelsIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏
查看更多内容