Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Abstract

Emotion recognition plays an important role in the field of human-computer interaction (HCI). Automatic emotion recognition based on EEG is an important topic in brain-computer interface (BCI) applications. Currently, deep learning has been widely used in the field of EEG emotion recognition and has achieved remarkable results. However, due to the cost of data collection, most EEG datasets have only a small amount of EEG data, and the sample categories are unbalanced in these datasets. These problems will make it difficult for the deep learning model to predict the emotional state. In this paper, we propose a new sample generation method using generative adversarial networks to solve the problem of EEG sample shortage and sample category imbalance. In experiments, we explore the performance of emotion recognition with the frequency band correlation and frequency band separation computational models before and after data augmentation on standard EEG-based emotion datasets. Our experimental results show that the method of generative adversarial networks for data augmentation can effectively improve the performance of emotion recognition based on the deep learning model. And we find that the frequency band correlation deep learning model is more conducive to emotion recognition.

EEG Emotion Recognition Based on Temporal and Spatial Features of Sensitive signals

“…Te CNN has the advantages of local connectivity and shared weights and has the ability to mine and integrate the local information of matrix signals [21], so it is suitable for analyzing the spatial connection of each channel in 2D matrix signals in this paper. In recent years, some scholars have tried to use the CNN to analyze the internal spatial connections of EEG signals, but most of them combine shallow multidomain features of single channels, then merge these features into matrix signals as input, and fnally further mine spatial information from the merged features [22].…”

Enhancement of Hybrid Deep Neural Network Using Activation Function for EEG based Emotion Recognition

“…Very few articles have used tanh, linear and sigmoid function in the middle layers. But when the activation function was changed to Leaky ReLU, there was a signi cant improvement in the performance of accuracy [19]. It was also inferred that softmax function was mostly used in the output layer of the model for multiclass classi cation.…”

“…The accuracy was estimated as 90%for arousal and 89% for valence. Pan et al[19] have used Power spectral density-Generative adversarial network to overcome the imbalance between the samples. In the rst model network, they have used two ReLU function and one tanh function.…”

Identification of emotions evoked by music via spatial-temporal transformer in multi-channel EEG signals

“…To evaluate the performance of the proposed approach in a fair fashion, we further evaluated the performance of the proposed approach and the state-of-the-art algorithms (Shawky et al, 2018;Yang et al, 2018Yang et al, , 2019Xing et al, 2019;Shen et al, 2020;Pan and Zheng, 2021;Rudakov, 2021;Kan et al, 2022;Zhang et al, 2022) on the DEAP dataset (as shown in Table 5). Accordingly, we used the DEAP dataset during the training phase of the proposed approach in this stage.…”