Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11861/7137
Title: Studying construction hazard awareness via artificial intelligence eye tracking: a tale of three groups of engineers
Authors: Zhu, Xiaoe 
Prof. LI Yi Man, Rita 
Issue Date: 2021
Source: 2021 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2021)
Conference: 2021 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2021) 
Abstract: Construction is a high-risk industry. The ability of construction workers to recognize hazards and the speed of response affects the likelihood of accidents happening on sites or the level of severity of construction events. Eye-tracking is a measure of people’s situational awareness in response to environments. Although prior research attempted to do experiments by using eye-tracking technology to analyze the hazard recognition ability and visual attention of tower crane operators, design and cost engineers construction industry practitioners, few studies are using artificial intelligence eye tracking. There is even fewer eye-tracking experiment for workers on construction site. This research attempts to analyze the online eye-tracking data of three groups of construction-related practitioners, including data such as heat map images, visual distribution, mouse clicks, opacity images, and facial expression changes. The analysis results show that different construction workers’ visual distribution and emotional changes are significantly different. Tower crane operators have a broader focus, and their emotional distribution is significantly different from that of indoor and cost engineers and is also significantly different from green leaf engineers or site supervisors.
Type: Conference Paper
URI: http://hdl.handle.net/20.500.11861/7137
Appears in Collections:Economics and Finance - Publication

Show full item record

Page view(s)

96
Last Week
1
Last month
checked on Dec 20, 2024

Google ScholarTM

Impact Indices

PlumX

Metrics


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.