Physiological Signals as Predictors of Cognitive Load Induced by the Type of Automotive Head-Up Display

Abstract

Visual information complexity of automotive head-up displays (HUDs) may increase cognitive load and reduce driver performance in critical situations. This study examined whether physiological indicators of cognitive load could predict the type of HUD while driving. Physiological signals of heart rate variability (HRV), electrodermal activity (EDA), skin temperature, and pupil dilation were recorded from 28 participants using a motion-based driving simulator. Two types of HUD with different information complexities were compared: baseline HUD and augmented reality HUD. Heart rate and EDA were processed to generate standardized biomedical features. Two separate sets of features were created for pupil dilation and skin temperature using time-series analysis and basic statistics. The fusion of physiological signals was used to test the impact of different signal combinations on classification performance. Three gradient boosting classifiers LightGBM (LGBM), HistGradientBoostingClassifier (HGBC), and XGBoost (XGB) were trained on physiological signals to predict the type of HUD. Classifiers based on the fusion of HRV, EDA and time-series features for skin temperature and pupil dilation achieved moderate performance, with average AUC ROC scores of XGB=0.67, LGBM=0.69, and HGBC=0.70. Classifiers based on the fusion of HRV, EDA, and the basic statistical features for skin temperature and pupil dilation achieved notable overall improvement in performance, with an average AUC ROC score = 0.76 for all three classifiers and the best score of LGBM=0.96, XGB=0.96, and HGBC=0.98. These results demonstrate the potential of physiological signals for modeling HUD-induced cognitive load and dynamically regulating its effects in real-time.