Abstract
The purpose of the present study is to grasp the situation of construction sites easily by distinguishing the movements of construction workers at construction sites from the accelerometer data attached to their waists. For the construction manager to accurately perceive the active or inactive state of his workers, their movements were classified into three distinct categories: walking, standing, and sitting. We tracked and observed two rebar workers for 5 days at a large building construction site. Their movements were classified by two-axis plots of (1) the difference between the maximum and minimum absolute values and (2) the value of acceleration at each second, and visualized by a heatmap among others for this trial. The results showed that despite the difficulty in distinguishing rebar work without a total body movement while sitting, the accuracy of discrimination was 60–80% in walking and sitting. From this analysis, we were able to identify repetitive tasks and the differences between morning and afternoon tasks. Furthermore, by applying simple visualization, we could concisely represent changes in work intensity over a relatively long period.
Highlights
Construction workers and their productivity are routinely monitored to improve results and safety at construction sites
A single-function accelerometer was affixed to the worker in this study
We developed a method to classify the work in construction sites using an accelerometer from the study by Gondo and Miura (2020)
Summary
Construction workers and their productivity are routinely monitored to improve results and safety at construction sites. The lack of orderly progress, a significant condition at construction sites, leads to projects going off schedule and financial loss It is the big difference from analyzing worker movements in a controlled laboratory setting. Since 2000, new technologies, such as biometric sensors (Hwang et al, 2016), image recognition (Kim et al, 2009), motion capture (Yu et al, 2019), and Artificial Intelligence (AI) (Peddi, 2008), have been developed to monitor human movement These technologies focus primarily on how detailed and precise the discrimination of work can be, cost and other factors are additional evaluation indicators in preparing for widespread use (Sanhudo et al, 2021).
Sign-in/Register to view highlights & summary 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.
