English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The spatial correlations and the temporal contexts are indispensable inElectroencephalogram (EEG)-based emotion recognition. However, the learning ofcomplex spatial correlations among several channels is a challenging problem.Besides, the temporal contexts learning is beneficial to emphasize the criticalEEG frames because the subjects only reach the prospective emotion during partof stimuli. Hence, we propose a novel Spatial-Temporal Information LearningNetwork (STILN) to extract the discriminative features by capturing the spatialcorrelations and temporal contexts. Specifically, the generated 2D powertopographic maps capture the dependencies among electrodes, and they are fed tothe CNN-based spatial feature extraction network. Furthermore, ConvolutionalBlock Attention Module (CBAM) recalibrates the weights of power topographicmaps to emphasize the crucial brain regions and frequency bands. Meanwhile,Batch Normalizations (BNs) and Instance Normalizations (INs) are appropriatelycombined to relieve the individual differences. In the temporal contextslearning, we adopt the Bidirectional Long Short-Term Memory Network (Bi-LSTM)network to capture the dependencies among the EEG frames. To validate theeffectiveness of the proposed method, subject-independent experiments areconducted on the public DEAP dataset. The proposed method has achieved theoutstanding performance, and the accuracies of arousal and valenceclassification have reached 0.6831 and 0.6752 respectively.

STILN: A Novel Spatial-Temporal Information Learning Network for EEG-based Emotion Recognition