Enhancing Emotion Recognition Using Region-Specific Electroencephalogram Data and Dynamic Functional Connectivity

Abstract

Recognizing the emotional states of humans through EEG signals are of great significance to the progress of human-computer interaction. The present study aimed to perform automatic recognition of music-evoked emotions through region-specific information and dynamic functional connectivity of EEG signals and a deep learning neural network. EEG signals of 15 healthy volunteers were collected when different emotions (high-valence-arousal vs. low-valence-arousal) were induced by a musical experimental paradigm. Then a sequential backward selection algorithm combining with deep neural network called Xception was proposed to evaluate the effect of different channel combinations on emotion recognition. In addition, we also assessed whether dynamic functional network of frontal cortex, constructed through different trial number, may affect the performance of emotion cognition. Results showed that the binary classification accuracy based on all 30 channels was 70.19%, the accuracy based on all channels located in the frontal region was 71.05%, and the accuracy based on the best channel combination in the frontal region was 76.84%. In addition, we found that the classification performance increased as longer temporal functional network of frontal cortex was constructed as input features. In sum, emotions induced by different musical stimuli can be recognized by our proposed approach though region-specific EEG signals and time-varying functional network of frontal cortex. Our findings could provide a new perspective for the development of EEG-based emotional recognition systems and advance our understanding of the neural mechanism underlying emotion processing.

Assessment of Different Feature Extraction Methods for Discriminating Expressed Emotions during Music Performance towards BCMI Application

“…It contrasts the outcomes of GC results in the current study and earlier reports where brain entropy/signal complexity [ 39 ]/Granger Causality [ 12 ] within beta and gamma bands showed the most effects during improvised/emotional playing. Importantly, the classification of GC-based features while performing music resulted in accuracies very similar to those reported by Liu et al while classifying music-induced emotions [ 40 ], and Guo et al while detecting induced emotions in the data from the DEAP and SEED datasets using neural networks on GC features [ 41 ]. The summary of accuracies obtained in the above mentioned works is presented as Supplementary Material, Table S1 .…”

Music-evoked emotions classification using vision transformer in EEG signals

“…In their investigations, Ekman ( 1999 ) and Gilda et al ( 2017 ) introduced six distinct and quantifiable emotional states, namely happiness, sadness, anger, fear, surprise, and disgust, as the basis for implementing emotion identification. Over time, other emotional states have been included in this collection, such as neutrality, arousal, and relaxation (Bong et al, 2012 ; Selvaraj et al, 2013 ; Goshvarpour et al, 2017 ; Minhad et al, 2017 ; Wei et al, 2018 ; Sheykhivand et al, 2020 ; Liu et al, 2022 ). In the context of machine learning, the establishment of distinct states for emotions serves as a significant framework for effectively addressing the challenge of emotion recognition.…”

“…Over time, other emotional states have been included in this collection, such as neutrality, arousal, and relaxation (Bong et al, 2012;Selvaraj et al, 2013;Goshvarpour et al, 2017;Minhad et al, 2017;Wei et al, 2018;Sheykhivand et al, 2020;Liu et al, 2022). In the context of machine learning, the establishment of distinct states for emotions serves as a significant framework for effectively addressing the challenge of emotion recognition.…”

A review: Music-emotion recognition and analysis based on EEG signals

“…Convolution Neuron Network (CNN) is well-suited to processing image data with the bias of transitional invariance. Thus, the power spectrogram generated by the EEG frequency signal was adopted reasonably (Er et al, 2021 ; Liu et al, 2022 ). LSTM was born for time series data since it can keep track of arbitrary long-term dependencies in the input sequences.…”