Paperdoi:10.3390/s26227250

Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics

Venue listedDated Nov 17, 2026Added Nov 17, 2026

  • XL
  • KW
  • ZH
  • SU

Authors: Xiaoyu Yan (Xi'an Physical Education Univ.); Mengjia Lu, Kexin Wang, Zebin Huang, Shiyi He (Hunan Normal Univ.); Yewei Ouyang (Shenzhen Univ.)

Sensors 26(22):7250 (2026), MDPI

TL;DR

Thirty-one male construction workers wore wrist accelerometers through hot-weather morning and afternoon shifts (62 records). Mean METs from the accelerometer, plus BMI, age, experience, fitness and shift period, predicted whether accuracy on a short visual hazard-cue task dropped after work. Under nested leave-one-worker-out validation, elastic-net logistic regression reached AUC 0.819 (Brier 0.170, 77.4% accuracy); mean METs was the most consistent predictor.

Abstract

Workers’ ability to detect hazard cues is essential for construction safety, yet continuous assessment during hot-weather work remains challenging. This study investigated whether wearable-sensor-derived physical workload and individual characteristics could predict declines in hazard-cue information acquisition after work. Thirty-one male construction workers contributed 62 morning and afternoon work-period records. Wrist-worn triaxial accelerometers provided mean metabolic equivalents (METs), which were combined with body mass index, age, work experience, physical fitness, and work period. Decline was defined as a reduction in accuracy on a brief visual hazard-cue information-acquisition task administered before and after work. Four classifiers, including L2-regularized logistic regression, elastic net logistic regression, a shallow random forest, and a constrained gradient-boosting tree, were evaluated using nested leave-one-worker-out cross-validation, with hyperparameters selected by the Brier score. Thirty-four records showed declining hit rate. Elastic net logistic regression achieved the highest area under the receiver operating characteristic curve (0.819) and the lowest Brier score (0.170), with an accuracy of 77.4%. The constrained gradient-boosting tree achieved the highest accuracy (79.0%). Permutation analysis identified mean METs as the most consistent contributor across algorithms. These findings suggest that wearable activity measurements combined with individual characteristics provide a promising basis for predicting hazard-cue information acquisition decline during hot-weather construction work.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Stress

Signals

Keywords

FatigueMental FatigueOccupationalConstructionHeat ExposureWrist AccelMetsHazard Perception

How it works

How Method works: Setup → Method → TargetSetup: Signals (accel). Method: Method. Target: Stress.SetupSignals: accelxyzSignalsaccelMethodMethodTargetStressStress

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Yan, X., Lu, M., Wang, K., Huang, Z., He, S., & Ouyang, Y. (2026). Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics. Sensors , MDPI, 26(22), 7250. https://doi.org/10.3390/s26227250
Yan, Xiaoyu, Mengjia Lu, Kexin Wang, Zebin Huang, Shiyi He, and Yewei Ouyang. 2026. "Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics." Sensors , MDPI 26 (22): 7250. https://doi.org/10.3390/s26227250.
Yan, X., Lu, M., Wang, K., Huang, Z., He, S. and Ouyang, Y. (2026) 'Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics', Sensors , MDPI, 26(22), p. 7250. doi: 10.3390/s26227250.
Yan, Xiaoyu, et al. "Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics." Sensors , MDPI, vol. 26, no. 22, 2026, p. 7250. https://doi.org/10.3390/s26227250.
X. Yan, M. Lu, K. Wang, Z. Huang, S. He, and Y. Ouyang, "Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics," Sensors , MDPI, vol. 26, no. 22, p. 7250, 2026, doi: 10.3390/s26227250.
@article{yan2026predicting,
  title         = {{Predicting Declines in Hazard-Cue Information Acquisition in Construction Workers Under Heat Exposure Using Workload and Individual Characteristics}},
  author        = {Yan, Xiaoyu and Lu, Mengjia and Wang, Kexin and Huang, Zebin and He, Shiyi and Ouyang, Yewei},
  year          = {2026},
  journal       = {Sensors , MDPI},
  volume        = {26},
  number        = {22},
  pages         = {7250},
  doi           = {10.3390/s26227250}
}

Added to the ChatPPG research hub