State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models
arXiv:2606.26723v1 Announce Type: cross Abstract: Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. This work reframes RESP-based recognition as a joint predictive and explanatory problem. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutiona
Advances in machine learning and accessible physiological sensing technologies are enabling more granular and interpretable analysis of biometric data for affective computing.
This research contributes to the development of more robust and user-friendly wearable technologies capable of real-time stress and emotional state recognition, which has broad applications in health monitoring, human-computer interaction, and well-being.
The focus shifts from mere classification accuracy to understanding the underlying interpretable physiological markers, potentially leading to more transparent and trustworthy AI systems in health monitoring.
- · Wearable tech companies
- · Healthcare providers
- · AI developers in affective computing
- · Individuals seeking personalized wellness solutions
- · Generic, non-interpretable biometric analysis methods
Improved accuracy and explainability of AI models for stress and affective recognition via wearable devices.
Wider adoption of real-time psychological state monitoring in everyday applications and professional settings.
Ethical and privacy debates intensify regarding continuous monitoring of emotional states and their potential misuse.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG