Abstract
Considering the vigorous development of the tunnel transportation industry, research on improving the health and comfort of tunnel workers has become important. Requirements for tunnel construction illumination vary worldwide, and the use of inappropriate illumination can lead to increased worker fatigue. This study used virtual-reality simulation of tunnel construction environments, with illumination intensity as the sole variable, combined with eye-tracking technology to record and analyze the performance of eight indicators across four categories under nine illumination conditions. The optimal illumination range was found to be 100–150 lx. The potential significance of each indicator was explored based on the varying interpretative capacities. A random forest algorithm was employed to construct a classification prediction model for illumination fatigue, achieving an accuracy rate of 75.5%. Noticeable fatigue was predicted with an accuracy of 85%, and that of mild fatigue was 80%. The significance of this study lies in the successful application of eye-tracking technology to detect and classify illumination fatigue in tunnel construction environments. However, illumination fatigue is not confined to underground environments. The experimental methods and results presented in this paper can aid in conducting research in various construction environments with limited natural light.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
