The TSception deep learning framework achieved a classification accuracy of 86.03% for emotion detection from EEG, significantly outperforming SVM, EEGNet, and LSTM (p<0.05).
Does the TSception deep learning framework improve classification accuracy of emotional arousal states from EEG compared to SVM, EEGNet, and LSTM in healthy subjects?
The TSception deep learning framework provides highly accurate emotion detection from EEG signals, outperforming existing methods.
p-value: p=<0.05
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).
Ding et al. (Wed,) conducted a other in Emotion detection (low and high emotional arousal states) (n=18). TSception (deep learning framework) vs. SVM, EEGNet, and LSTM was evaluated on Classification accuracy of low and high emotional arousal states (p=<0.05). The TSception deep learning framework achieved a classification accuracy of 86.03% for emotion detection from EEG, significantly outperforming SVM, EEGNet, and LSTM (p<0.05).