Mental stress classification based on multiscale feature fusion of multimodal physiological data

Key Points

• Mental stress classification was enhanced through multiscale feature fusion, leading to better accuracy.
• The study achieved a classification accuracy of over 85% for stress detection across various physiological signals.
• Analysis utilized machine learning algorithms to process and fuse data from multiple physiological sources for classification.
• Findings highlight the potential for improved mental health monitoring techniques in real-world settings.