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

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