NeuroSafeDrive: An Intelligent System Using fNIRS for Driver Distraction Recognition

Driver distraction remains a critical factor in road accidents, necessitating intelligent systems for real-time detection. This study introduces a novel fNIRS-based method to to classify varying levels of driver distraction across diverse simulated scenarios, including cognitive, visual-manual, and auditory sources of inattention. Unlike previous work, we evaluated multiple neurophysiological metrics-including oxygenated, deoxygenated, and combined haemoglobin-to identify the most reliable biomarker for distraction detection. Neurophysiological data were collected, and three multi-class classifiers (SVM, KNN, decision tree) were applied across different fNIRS metrics. Our results show that oxygenated haemoglobin outperforms other signals in distinguishing distracted from non-distracted states, while the combined signal performs best in differentiating distraction from baseline. The proposed SVM model achieved ≈ 77.9% accuracy in detecting distracted and relaxed driving states based on brain oxygen levels. Our findings also show that increased distraction correlates with elevated activity in the dorsolateral prefrontal cortex and premotor cortex, whereas driving without distraction exhibits lower neurovascular engagement. This study contributes to affective computing and intelligent transportation systems and could support the development of future driver distraction monitoring systems for safer and more adaptive vehicle control.