A benchmarking framework for eye-tracking-based vigilance prediction of vessel traffic controllers

Zhimin Li, Ruilin Li, Liqiang Yuan, Jian Cui, Fan Li

Abstract: Highlights•We present a comprehensive analysis of eye-tracking features under the framework.•A hierarchical feature importance analysis based on SHAP is introduced.•We propose an efficient vigilance ensemble model, which shows superior performance.•A comparative analysis of professional and novice VTCs is performed.