Investigation of drivers' visual attributes in highway entrance zones utilizing Self-Organizing Mapping neural network.

With increasing highway traffic, safety issues from the ramp entrance to the merging area have become more prominent. This study uses drivers' eye-tracking data in real-world conditions to analyze visual behavior characteristics, including gaze duration, gaze angle, and gaze speed, in the entrance curve section, merging observation section, ramp merging section, and freeway section. Results show that the merging observation section exhibits the highest visual task load, with peak saccade time, angle, and speed at 100.78 ms, 35.09 deg, and 1.93 deg/ms, respectively, exceeding those in other sections. Through Self-Organizing Map (SOM) neural network clustering analysis, saccade time and angle were categorized into five groups. Driver visual behavior varies distinctly across different road sections. Notably, in the merging observation section, the average eye movement-speed matching index (EMSMI) peaks at 0.1249 deg/ms, with a marked increase in categories A2 and A5. This section involves complex driving tasks, requiring frequent visual adjustments to navigate dynamic traffic conditions. In contrast, the entrance curve and freeway section predominantly exhibit categories A1 and A3, with lower EMSMI values of 0.0410 deg/ms and 0.0408 deg/ms, respectively. These sections show fewer outliers and a more concentrated distribution, indicating reduced cognitive load. This study systematically analyzes drivers' visual behavior in complex traffic environments, providing a basis for traffic safety management and driving behavior modeling.