MCF-SCA: A Multi-Scale Spatio-Temporal Convolution and Multi-Order Gated Spatial-Channel Aggregation Networks for Cross-Subject EEG-Based Emotion Recognition

Abstract

Cross-subject emotion recognition using EEG remains challenging due to substantial inter-individual variability. To address this, we propose a Multi-scale Spatio-Temporal Convolution and Multi-order Gated Spatial-Channel Aggregation Network (MCF-SCA). The model leverages multi-scale spatio-temporal convolution to capture rich temporal and spatial features and applies Fast Fourier Transform to transform EEG signals into the frequency domain, enhancing emotion-related representations. A multi-order spatial-channel aggregation module is then introduced, which adaptively integrates features across spatial and channel dimensions through a gating mechanism, enabling dynamic feature weighting and more expressive emotional representations. Experiments on the DEAP dataset show accuracy gains of up to 11–30% for arousal and 12–31% for valence compared with TSception, CNN, LSTM, EEGNet, and MLP. On the DREAMER dataset, improvements reach 5–33% and 3.7–34%, respectively. These results confirm that MCF-SCA achieves superior accuracy and cross-subject adaptability, providing strong support for emotion-based brain–computer interface applications.

Key findings

• ▸MCF-SCA achieves accuracy gains of up to 11-30% for arousal and 12-31% for valence on the DEAP dataset
• ▸MCF-SCA outperforms existing methods, including TSception, CNN, LSTM, EEGNet, and MLP, on both DEAP and DREAMER datasets
• ▸The multi-order spatial-channel aggregation module enables dynamic feature weighting and more expressive emotional representations

Keywords

Identifiers

DOI

10.3390/info17030257

Journal

Information

Year

2026