Multi-dimensional Research Framework Construction and Optimization Strategy Design for the Impact of Tunnel Light Environment on Driving Safety

In the era of rapid development of artificial intelligence, data analysis, and cloud computing, intelligent research in the field of traffic safety continues to deepen. To address the need for further exploration of the relationship between tunnel light environments and driving safety, this paper proposes an innovative research scheme combining psychophysiological indicator detection technology with driving simulation experiments. Based on light environment theory and drivers’ physiological-psychological mechanisms, the study plans to collect physiological data such as heart rate variability (HRV), eye movement characteristics, and electroencephalogram (EEG) signals using a multi-channel physiological recorder and dynamic visual tester. This data will be combined with subjective questionnaires and driving behavior trajectory analysis, and analyzed through multivariate statistics and machine learning algorithms to systematically investigate the dynamic impact mechanisms of different light environment parameters on drivers’ physiological indicators, psychological perceptions, and driving behaviors. The research aims to construct an integrated“environment-physiology-behavior” multidimensional framework, quantitatively clarifying the relationship between tunnel light environment variations and driving safety risks. Based on this framework, potential optimization strategies are proposed, including lighting layout, light color regulation, and transition zone optimization, laying a theoretical foundation and practical pathway for enhancing tunnel traffic safety.