Driver emotion recognition based on attentional convolutional network

Unstable emotions, particularly anger, have been identified as significant contributors to traffic accidents. To address this issue, driver emotion recognition emerges as a promising solution within the realm of cyber-physical-social systems (CPSS). In this paper, we introduce SVGG, an emotion recognition model that leverages the attention mechanism. We validate our approach through comprehensive experiments on two distinct datasets, assessing the model’s performance using a range of evaluation metrics. The results suggest that the proposed model exhibits improved performance across both datasets.