Why the study?
Driver fatigue and unpleasant emotions increase driving risks, but existing models rarely combine detection of both states and recognition accuracy can be improved.
Population
Captured video image sequences and the Fer2013 dataset
Design
Algorithm development and validation study
Key result
The proposed driver fatigue and emotional state detection method achieved an accuracy rate of 73.32% on the Fer2013 dataset.
Authors
Loading...
May support AI-driven driver monitoring development; leaves open real-world validation before any clinical use.
A novel time series fusion method combining driver fatigue and emotion detection achieved 73.32% accuracy for emotion recognition, offering a potential tool for assisted safe driving.
Shang et al. (2022) studied Driver fatigue and emotional state. Time series fusion-based driver fatigue and emotional state detection method was evaluated on Accuracy of the emotion recognition network on the Fer2013 dataset. The proposed driver fatigue and emotional state detection method achieved an accuracy rate of 73.32% on the Fer2013 dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: