SHAP-selected features from multimodal physiological signals fed to a hybrid XGBoost-LightGBM ensemble yield 80.91% test accuracy and 0.79 macro-F1 for driving behavior classification.
Visual dominance and emerging multi- modal approaches in distracted driving detection: A review of machine learning techniques
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physiologically Grounded Driver Behavior Classification: SHAP-Driven Elite Feature Selection and Hybrid Gradient Boosting for Multimodal Physiological Signals
SHAP-selected features from multimodal physiological signals fed to a hybrid XGBoost-LightGBM ensemble yield 80.91% test accuracy and 0.79 macro-F1 for driving behavior classification.