Machine learning models using wearable physiological signals, particularly heart rate variability, successfully differentiated between mental states like stress, focus, and relaxation.
Can a machine learning model using multimodal physiological signals from wearable devices accurately classify mental states?
Wearable systems combining HR, HRV, and activity features with machine learning can effectively monitor and classify mental states in real time.
Absolute Event Rate: 0% vs 0%
This study shows how to use machine learning to sort people's mental states using a variety of physiological signals collected from wearable devices. The suggested method combines heart rate (HR), heart rate variability (HRV), and features based on activity to capture both physiological and behavioral patterns. A supervised classification model was made and tested on data that had been broken up into time segments. It showed that it could tell the difference between states like stress, focus, and relaxation. Experimental results show that physiological variability metrics, especially HRV, are very good at finding temporary changes in cognitive and emotional states. The results show that wearable systems could be used to monitor mental states in real time for adaptive human-computer interaction, health tracking, and improving cognitive performance.
Negm et al. (Sun,) reported a other. Machine learning models using wearable physiological signals, particularly heart rate variability, successfully differentiated between mental states like stress, focus, and relaxation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: