Key result
A novel 1DCNN-LSTM deep learning architecture for contactless PPG signal extraction achieved recognition rates of 82.8% for valence and 70.7% for arousal classification.
Why the study?
Traditional automatic recognition of human emotions relies on body-placed sensors, but contactless photoplethysmography signal extraction from facial video footage can eliminate the need for physical contact.
Population
Video footage from a widely used emotional database
Comparison
Various methods for extracting contactless PPG signals
Authors
Loading...
Video-based facial PPG for emotion classification requires prospective validation; leaves open remote cardiovascular monitoring applications.
A novel deep learning framework using 1DCNN-LSTM for contactless PPG extraction from facial videos demonstrates promising accuracy for automatic emotion recognition.
Traeger et al. (2023) studied Emotion recognition. 1DCNN-LSTM deep learning architecture for contactless PPG vs. State-of-the-art methods was evaluated on Accuracy in valence and arousal classification. A novel 1DCNN-LSTM deep learning architecture for contactless PPG signal extraction achieved recognition rates of 82.8% for valence and 70.7% for arousal classification.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: