May 11, 2020IEEE Transactions on Affective ComputingOpen Access

EEG-Based Emotion Recognition Using Regularized Graph Neural Networks

View Full Paper

Ask AI

Bookmark

Why the study?

Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels.

Population

Two public datasets, SEED and SEED-IV

Comparison

Regularized graph neural network vs state-of-the-art models

Authors

PZPeixiang ZhongBC Research (Canada)DWDi WangNanyang Technological University CMChunyan MiaoNational University of Singapore

Discussion

Member takes

Implication

Supports advanced EEG emotion modeling; leaves open clinical translation pending prospective validation.

Structured PICO

Population

EEG data from two public datasets (SEED and SEED-IV) for emotion recognition

Intervention

Regularized graph neural network (RGNN) with node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL)

Comparator

State-of-the-art models

Outcome

Emotion recognition performance

A novel regularized graph neural network (RGNN) improves EEG-based emotion recognition by incorporating biological brain topology and specialized regularizers for cross-subject variations and noisy labels.

Cite This Study

Zhong et al. (2020) studied this question.

synapsesocial.com/papers/69dbaee950e1971baba3c37c https://doi.org/10.1109/taffc.2020.2994159

View Full Paper

Ask AI

Bookmark

May 11, 2020IEEE Transactions on Affective ComputingOpen Access

EEG-Based Emotion Recognition Using Regularized Graph Neural Networks

View Full Paper

Ask AI

Bookmark

Why the study?

Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels.

Population

Two public datasets, SEED and SEED-IV

Comparison

Regularized graph neural network vs state-of-the-art models

Authors

PZPeixiang ZhongBC Research (Canada)DWDi WangNanyang Technological University CMChunyan MiaoNational University of Singapore

Discussion

Member takes

Implication

Supports advanced EEG emotion modeling; leaves open clinical translation pending prospective validation.

Structured PICO

Population

EEG data from two public datasets (SEED and SEED-IV) for emotion recognition

Intervention

Regularized graph neural network (RGNN) with node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL)

Comparator

State-of-the-art models

Outcome

Emotion recognition performance

Cite This Study

Zhong et al. (2020) studied this question.

synapsesocial.com/papers/69dbaee950e1971baba3c37c https://doi.org/10.1109/taffc.2020.2994159

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark