Cross-Subject EEG Emotion Recognition With Self-Organized Graph Neural Network
Open Access
- 9 June 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neuroscience
Abstract
As a physiological process and high-level cognitive behavior, emotion is an important subarea in neuroscience research. Emotion recognition across subjects based on brain signals has attracted much attention. Due to individual differences across subjects and the low signal-to-noise ratio of EEG signals, the performance of conventional emotion recognition methods is relatively poor. In this paper, we propose a self-organized graph neural network (SOGNN) for cross-subject EEG emotion recognition. Unlike the previous studies based on pre-constructed and fixed graph structure, the graph structure of SOGNN are dynamically constructed by self-organized module for each signal. To evaluate the cross-subject EEG emotion recognition performance of our model, leave-one-subject-out experiments are conducted on two public emotion recognition datasets, SEED and SEED-IV. The SOGNN is able to achieve state-of-the-art emotion recognition performance. Moreover, we investigated the performance variances of the models with different graph construction techniques or features in different frequency bands. Furthermore, we visualized the graph structure learned by the proposed model and found that part of the structure coincided with previous neuroscience research. The experiments demonstrated the effectiveness of the proposed model for cross-subject EEG emotion recognition.Keywords
Funding Information
- National Natural Science Foundation of China (62006082)
This publication has 39 references indexed in Scilit:
- Trait anger modulates neural activity in the fronto-parietal attention networkPLOS ONE, 2018
- Emotions Recognition Using EEG Signals: A SurveyIEEE Transactions on Affective Computing, 2017
- Emotion Recognition based on EEG using LSTM Recurrent Neural NetworkInternational Journal of Advanced Computer Science and Applications, 2017
- Differential entropy feature for EEG-based emotion classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Graph AlgorithmsPublished by Cambridge University Press (CUP) ,2011
- Functional neural network analysis in frontotemporal dementia and Alzheimer's disease using EEG and graph theoryBMC Neuroscience, 2009
- Frontal EEG asymmetry as a moderator and mediator of emotionBiological Psychology, 2004
- Analysis of emotion recognition using facial expressions, speech and multimodal informationPublished by Association for Computing Machinery (ACM) ,2004
- Emotion recognition in human-computer interactionIEEE Signal Processing Magazine, 2001
- Regional brain function, emotion and disorders of emotionCurrent Opinion in Neurobiology, 1999