Deep learning-based self-induced emotion recognition using EEG

Abstract

Emotion recognition from electroencephalogram (EEG) signals requires accurate and efficient signal processing and feature extraction. Deep learning technology has enabled the automatic extraction of raw EEG signal features that contribute to classifying emotions more accurately. Despite such advances, classification of emotions from EEG signals, especially recorded during recalling specific memories or imagining emotional situations has not yet been investigated. In addition, high-density EEG signal classification using deep neural networks faces challenges, such as high computational complexity, redundant channels, and low accuracy. To address these problems, we evaluate the effects of using a simple channel selection method for classifying self-induced emotions based on deep learning. The experiments demonstrate that selecting key channels based on signal statistics can reduce the computational complexity by 89% without decreasing the classification accuracy. The channel selection method with the highest accuracy was the kurtosis-based method, which achieved accuracies of 79.03% and 79.36% for the valence and arousal scales, respectively. The experimental results show that the proposed framework outperforms conventional methods, even though it uses fewer channels. Our proposed method can be beneficial for the effective use of EEG signals in practical applications.

Exploring Brain Dynamics via EEG and Steady-State Activation Map Networks in Music Composition

“…Although the direct connection to music might not be as apparent as in other brain areas, it is still worth further exploration. In our study, the results of the ECA module revealed the importance of high-frequency bands (beta and gamma) in distinguishing music composition states, similar to findings in emotional recognition research [ 45 , 49 , 50 ], where high-frequency bands performed slightly better than low-frequency bands (theta and alpha). This result emphasizes the close association between music and emotions, as well as the significant driving role of emotions in music composition and experience.…”

An innovative EEG-based emotion recognition using a single channel-specific feature from the brain rhythm code method

“…Recent studies (Ji and Dong, 2022;Li Z. et al, 2022;Xiao et al, 2022) have highlighted the neural networks in emotion recognition. These networks are capable of learning high-level features from raw EEG data in an incremental manner, which eliminates the requirement for feature extraction.…”

Optimal channel dynamic selection for Constructing lightweight Data EEG-based emotion recognition

“…With the development of technology, deep learning techniques were also heavily applied to EEG signal emotion recognition [ [19] , [20] , [21] ]. Zhong P et al [ 22 ] proposed a method based on regularized graph neural networks (RGNN) for emotion recognition of EEG, which accuracy was 94.24 % on the SEED dataset.…”