Cite this model
Hyodo 2024 interpretable PRV DNN for mental fatigue (wrist PPG). (2024).
@misc{hyodoprvmentalfa2024hyodo,
title = {{Hyodo 2024 interpretable PRV DNN for mental fatigue (wrist PPG)}},
year = {2024}
}Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
Hyodo et al. present a physiologically interpretable deep neural network for mental-fatigue recognition from wrist-PPG pulse-rate variability, with a feature method meant to capture temporal accumulation of arousal. In their experiments the approach reached accuracy 0.90 and F1 0.91 and increased the contribution of HRV indices linked to cognitive function. Source: IEEE ACIIW 2024 (10.1109/ACIIW63320.2024.00043).
Physiologically interpretable DNN on PRV/HRV indices + temporal arousal-accumulation feature

Hyodo 2024 interpretable PRV DNN for mental fatigue (wrist PPG). (2024).
@misc{hyodoprvmentalfa2024hyodo,
title = {{Hyodo 2024 interpretable PRV DNN for mental fatigue (wrist PPG)}},
year = {2024}
}Added to the ChatPPG research hub