MétaCan
Menu
Back to cohort
Record W7127917559 · doi:10.22260/crc-csce-2025/0201

Eye-Tracking-Based Risk Perception Prediction for Adaptive Hazard Recognition Training

2025· article· W7127917559 on OpenAlexfundno aff
Mohammad Rezaeiashtiani, Meesung Lee, Ali Golabchi, Vicente Gonzalez-Moret, Nizam Ahmed, Gaang Lee

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicGaze Tracking and Assistive Technology
Canadian institutionsnot available
FundersUniversity of AlbertaWorkSafeBC
KeywordsTraining (meteorology)PerceptionHazardFeature (linguistics)Risk assessment

Abstract

fetched live from OpenAlex

Hazard recognition is a critical cognitive skill that directly impacts construction site safety, yet conventional safety training methods often fail to account for individual differences in risk perception.This study explores the application of eye-tracking-based biosignal analysis for real-time risk perception assessment in adaptive virtual reality (VR) training.By capturing eye-tracking metrics such as fixation duration, gaze velocity, and pupil dilation, we developed a machine learning model to classify workers' risk perception levels.Among the evaluated classifiers, Gradient Boosting achieved the highest performance (accuracy = 76.81%,AUC = 0.81), demonstrating superior discrimination between high and low-risk perception groups.Compared to traditional physiological signals like EEG, EDA, and PPG, eye-tracking provides a non-invasive, real-time alternative for monitoring hazard recognition.These findings highlight the potential of integrating eye-tracking with adaptive VR training to improve risk perception assessment, which could inform personalized safety interventions in future research and applications.Further studies should validate these results in larger, more diverse cohorts and refine adaptive training algorithms for realworld implementation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.987
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.051
GPT teacher head0.299
Teacher spread0.248 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designOther design
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicGaze Tracking and Assistive TechnologyFrench-language works237,207