The study extracted 55 time-domain, frequency-domain, non-linear, and morphological features from electrocardiogram signals for machine learning-based mental stress detection.
Can machine learning models using single-sensor ECG accurately detect mental stress amid everyday activities?
While machine learning models can detect mental stress via ECG with high sensitivity, single-sensor approaches struggle to differentiate mental stress from physical exertion in everyday settings.
ML models can detect MS with high sensitivity and remain robust to lower sampling rates and fewer features. Generalization to novel stressors was stressor-dependent. Importantly, our results highlight challenges in distinguishing stress-related cardiac responses from those caused by physical exertion, revealing critical limitations of single-sensor ECG approaches for MS detection.
Uendes et al. (Tue,) conducted a other in Mental stress. Machine learning model using ECG features was evaluated. The study extracted 55 time-domain, frequency-domain, non-linear, and morphological features from electrocardiogram signals for machine learning-based mental stress detection.