Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 2, 2026

HRV-based Random Forest model outperforms other models in predicting driver fatigue and comfort.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

To develop a real-time machine learning model based on heart rate variability to mitigate the risks associated with fatigue and discomfort during prolonged driving.

Can a machine learning model based on Heart Rate Variability (HRV) accurately predict driver fatigue and comfort levels?

Comparison

Machine learning model based on Heart Rate… vs Other machine learning models

Design

Other

Key result

A Random Forest machine learning model based on heart rate variability outperformed other models in predicting driver fatigue (RMSE = 14.55) and comfort (RMSE = 1.56).

Authors

WJWeisheng JiangQZQianxiang ZhouZLZhongqi Liu

Discussion

Loading...

Member takes

Overview

HRV-based ML may aid real-time driver fatigue detection; leaves open prospective validation before clinical or safety adoption.

Key Points

  • The aim is to create a model for real-time monitoring of driver fatigue and comfort using heart rate variability.
  • Developed a machine learning model based on heart rate variability features.
  • Utilized Random Forest for prediction of fatigue and comfort levels.
  • Identified six key HRV features linked to autonomic nervous system activity.
  • Random Forest model achieved RMSE of 14.55 for fatigue prediction and 1.56 for comfort.
  • Six HRV features identified as crucial: HRV Triangular Index, Shannon Entropy, Minimum NN interval, Geometric Index, Lorenz Plot Index, and Power of Asymmetry Segment.
  • The model shows high reliability for continuous driver status monitoring.

Structured PICO

Can a machine learning model based on Heart Rate Variability (HRV) accurately predict driver fatigue and comfort levels?

I
Intervention
Machine learning model based on Heart Rate Variability (HRV)
C
Comparator
Other machine learning models
O
Outcome
Prediction of fatigue and comfort levelssurrogate

A Random Forest machine learning model using six HRV features can continuously and objectively assess driver fatigue and comfort.

Limitations

  • Requires validation in real-world driving conditions
  • Needs validation in real-world driving conditions

Cite This Study

Jiang et al. (2026) studied Driver fatigue and discomfort. Random Forest model based on Heart Rate Variability (HRV) vs. Other models was evaluated on Prediction of fatigue and comfort. A Random Forest machine learning model based on heart rate variability outperformed other models in predicting driver fatigue (RMSE = 14.55) and comfort (RMSE = 1.56).

synapsesocial.com/papers/69f5949771405d493afff697https://doi.org/10.1080/15389588.2026.2649870
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Predicting driver fatigue using HRV measures and machine learning2026 · 1 citations
  2. 2Assessment of flight fatigue using heart rate variability and machine learning approaches2025 · 13 citations
  3. 3Driver Fatigue Detection Using Measures of Heart Rate Variability and Electrodermal Activity2023 · 56 citations
  4. 4Heart rate variability as an indicator of fatigue: A structural equation model approach2024 · 35 citations
  5. 5Heart Rate Variability for Classification of Alert Versus Sleep Deprived Drivers in Real Road Driving Conditions2020 · 107 citations