Model

Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle)

Cite
UnconfirmedCatalog paper date: 2023Added to atlas: Nov 9, 2026

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.

Schwarz et al. trained nine binary random-forest drowsiness detectors combining an Aisin camera driver-monitoring system, National Advanced Driving Simulator vehicle data, and Empatica E4 wrist HRV. Forty participants drove a simulator for up to three hours after at least 16 hours awake. Classification accuracy ranged from 0.77 to 0.92; the most timely model flagged drowsiness 6.7 minutes before a drowsy lane departure. Adding physiology improved accuracy only slightly (Traffic Injury Prevention 2023).

Signals
PPG, EDA, HRV, camera, vehicle
Form factor
Wrist
License
Paper CC BY (T&F OA)
Year
2023
Architecture

Random forest (binary), 9 variants over data-source and label combinations

At a glance
Type
Task model
Form factor
Wrist
Parameters
Not reported
Architecture
Random forest (binary), 9 variants over data-source and label combinations
Venue
Not reported
Year
2023
arXiv
Not reported
DOI
Not reported
Code
Not released
Weights
Not released
Licence
Paper CC BY (T&F OA)
Caveats
Not reported
Datasets
Not reported
Added
Nov 9, 2026
Updated
Nov 9, 2026
Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle): ChatPPG research summary card

How it works

How Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle) works: Input signals → Model → Downstream tasksInput signals: PPG (Photoplethysmogram); EDA (Electrodermal activity); HRV; camera. Model: Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle) (Gradient-boosted trees). Downstream tasks: Stress.Input signalsPPG: PhotoplethysmogramPPGPhotoplethysmogramEDA: Electrodermal activityEDAElectrodermal activityHRVHRVcameracameraModelSchwarz 2023 multi-sensor…Gradient-boosted treesDownstream tasksStressStress
Architecture
Random forest (binary), 9 variants over data-source and label combinations
Inputs
PPG, EDA, HRV, camera, vehicle
Approach
fatigue · physiology · classical

Datasets used

No public datasets linked yet.

Papers· 1

Cite this model

Cite the publication recorded for this model. Check it against the publisher before submitting.

Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle). (2023).
@misc{schwarze4hrvdrow2023schwarz,
  title         = {{Schwarz 2023 multi-sensor drowsiness random forests (E4 wrist HRV + camera DMS + vehicle)}},
  year          = {2023}
}

Source metadata: 2023

Record updated Nov 9, 2026

History

  1. Added to the ChatPPG research hub