Fatigue-Related Reaction Time Forecasting via EEG Functional Connectivity in Sustained Attention Task

TL;DR

This study develops a model using EEG functional connectivity to forecast reaction times up to 20 seconds ahead, aiding proactive fatigue management in safety-critical tasks.

Contribution

It introduces a novel EEG-based reaction time forecasting model with high accuracy and interpretability for sustained attention tasks.

Findings

The model predicts reaction times with an RMSE of around 24 ms.

Forecasting accuracy remains high across different time horizons up to 20 seconds.

Interpretability analysis identifies distinct temporal EEG biomarkers.

Abstract

Mental fatigue related behavioral performance decline precipitates catastrophic accidents in sustained attention tasks. While existing neurophysiological systems effectively detect current behavioral performance, they often lack the capability to forecast behavioral lapses with sufficient temporal lead time for intervention. This study proposes a novel model for the reaction time (RT) forecasting using EEG functional connectivity features. Thirty participants engaged in a sustained Psychomotor Vigilance Test (PVT) with concurrent 30-channel EEG recording. Mutual information (MI) between electrodes was calculated as functional connectivity features. Random Forest regression model (RF) was trained to predict single-trial RTs across forecasting horizons ranging from 0 to 20 seconds. The model demonstrated robust predictive validity, achieving a Root Mean Square Error (RMSE) of 23.75 ms for immediate detection and maintaining high accuracy (RMSE = 24.07 ms) across different forecasting horizons. Interpretability analysis via SHAP and Linear Mixed Effects model further support the validity of the proposed model and revealed distinct temporal biomarkers. This study validates the feasibility of forecasting behavioral performance 20 seconds in advance, offering a promising methodology for proactive fatigue management in safety-critical systems.