TSception: A Deep Learning Framework for Emotion Detection Using EEG
This work addresses emotion classification for applications in mental health or human-computer interaction, but it is incremental as it builds on existing deep learning approaches for EEG analysis.
The authors tackled emotion detection from EEG signals by proposing TSception, a deep learning framework with temporal and spatial convolutional layers, achieving a classification accuracy of 86.03% for low vs. high emotional arousal states, significantly outperforming prior methods like SVM, EEGNet, and LSTM.
In this paper, we propose a deep learning framework, TSception, for emotion detection from electroencephalogram (EEG). TSception consists of temporal and spatial convolutional layers, which learn discriminative representations in the time and channel domains simultaneously. The temporal learner consists of multi-scale 1D convolutional kernels whose lengths are related to the sampling rate of the EEG signal, which learns multiple temporal and frequency representations. The spatial learner takes advantage of the asymmetry property of emotion responses at the frontal brain area to learn the discriminative representations from the left and right hemispheres of the brain. In our study, a system is designed to study the emotional arousal in an immersive virtual reality (VR) environment. EEG data were collected from 18 healthy subjects using this system to evaluate the performance of the proposed deep learning network for the classification of low and high emotional arousal states. The proposed method is compared with SVM, EEGNet, and LSTM. TSception achieves a high classification accuracy of 86.03%, which outperforms the prior methods significantly (p<0.05). The code is available at https://github.com/deepBrains/TSception