Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/43391
Title: Development of an early-warning system for site work in hot and humid environments : a case study
Authors: Yi, W
Chan, APC 
Wang, X
Wang, J
Keywords: Artificial neural networks (ANNs)
Construction industry
Early-warning system
Heat stress
Hong Kong
Occupational health and safety (OHS)
Issue Date: 2016
Publisher: Elsevier
Source: Automation in construction, 2016, v. 62, p. 101-113 How to cite?
Journal: Automation in construction 
Abstract: This study presents an early-warning system for working in hot and humid environment. The developed system can monitor workers' heat strain level when they have to work under such hostile conditions continuously. Health alert messages with corresponding intervention measures will be prompted to workers to safeguard their wellbeing. Heat strain is evaluated by a subjective index perception rating of perceived exertion (RPE) and an objective heat strain indicator heart rate. A database containing 550 sets of synchronized work-related, environmental, and personal data were used to construct the prediction model. Artificial neural networks were applied to forecast the RPE of construction workers. Statistical measures including MAPE, RMSE and R2 confirm that the established model is good fitting with high accuracy. The proposed system could be automated by integrating smart sensor technology, location tracking technology, and information communication technology, which could be in the form of GSM based environmental sensor, smart bracelet, and smart phone application, to protect the wellbeing for those who have to work in hot and humid conditions.
URI: http://hdl.handle.net/10397/43391
ISSN: 0926-5805
EISSN: 1872-7891
DOI: 10.1016/j.autcon.2015.11.003
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

13
Last Week
0
Last month
Citations as of Sep 11, 2017

WEB OF SCIENCETM
Citations

10
Last Week
0
Last month
Citations as of Sep 22, 2017

Page view(s)

55
Last Week
5
Last month
Checked on Sep 17, 2017

Google ScholarTM

Check

Altmetric



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