Smart work package learning for decentralized fatigue monitoring through facial images

Xiao Li; Jianhuan Zeng; Chen Chen; Hung lin Chi; Geoffrey Qiping Shen

doi:10.1111/mice.12891

Smart work package learning for decentralized fatigue monitoring through facial images

Xiao Li, Jianhuan Zeng, Chen Chen, Hung lin Chi, Geoffrey Qiping Shen

Research output: Journal article publication › Journal article › Academic research › peer-review

9 Citations (Scopus)

Abstract

Monitoring the fatigue of construction equipment operators (CEOs) is critical for preventing accidents and ensuring precision construction occupational health and safety (COHS). However, there exists a theoretical dilemma between centralized technical efficiency and decentralized data privacy. Thus, this study introduces smart work package learning (SWPL), a decentralized deep learning approach to monitor CEOs’ fatigue without privacy exposure risks. To illustrate the feasibility of SWPL as the fatigue classifier, this study implements fatigue monitoring through noninvasive facial images, and SWPL merges the updated parameters of the model from each smart work package (SWP). These updates are then validated by SWPs in the blockchain network and stored on the blockchain. More than 356 videos were derived from 124 operators. The results present that SWPL on decentralized SWP networks outperforms the deep learning model on individual SWP. The computational novelty is SWPL's dynamic parameter aggregation mechanism to avoid parameter exposure in centralized or fixed aggregators. The proposed SWPL will open up advanced developments in precision COHS.

Original language	English
Journal	Computer-Aided Civil and Infrastructure Engineering
DOIs	https://doi.org/10.1111/mice.12891
Publication status	Accepted/In press - Jul 2022

ASJC Scopus subject areas

Civil and Structural Engineering
Building and Construction
Computer Science Applications
Computer Graphics and Computer-Aided Design
Computational Theory and Mathematics

More information

10.1111/mice.12891

http://hdl.handle.net/10397/107781

Cite this

@article{c72e9218563e4f5ca31b581d8ae0c94c,

title = "Smart work package learning for decentralized fatigue monitoring through facial images",

abstract = "Monitoring the fatigue of construction equipment operators (CEOs) is critical for preventing accidents and ensuring precision construction occupational health and safety (COHS). However, there exists a theoretical dilemma between centralized technical efficiency and decentralized data privacy. Thus, this study introduces smart work package learning (SWPL), a decentralized deep learning approach to monitor CEOs{\textquoteright} fatigue without privacy exposure risks. To illustrate the feasibility of SWPL as the fatigue classifier, this study implements fatigue monitoring through noninvasive facial images, and SWPL merges the updated parameters of the model from each smart work package (SWP). These updates are then validated by SWPs in the blockchain network and stored on the blockchain. More than 356 videos were derived from 124 operators. The results present that SWPL on decentralized SWP networks outperforms the deep learning model on individual SWP. The computational novelty is SWPL's dynamic parameter aggregation mechanism to avoid parameter exposure in centralized or fixed aggregators. The proposed SWPL will open up advanced developments in precision COHS.",

author = "Xiao Li and Jianhuan Zeng and Chen Chen and Chi, {Hung lin} and Shen, {Geoffrey Qiping}",

note = "Funding Information: The authors would like to acknowledge the financial support from The Hong Kong Polytechnic University Start‐up Fund (No. P0039232), HK RGC General Research Fund (No. 15219422), and the Fellowship of China Postdoctoral Science Foundation (No. 2021M692169). Publisher Copyright: {\textcopyright} 2022 Computer-Aided Civil and Infrastructure Engineering.",

year = "2022",

month = jul,

doi = "10.1111/mice.12891",

language = "English",

journal = "Computer-Aided Civil and Infrastructure Engineering",

issn = "1093-9687",

publisher = "Wiley-Blackwell Publishing Ltd",

}

TY - JOUR

T1 - Smart work package learning for decentralized fatigue monitoring through facial images

AU - Li, Xiao

AU - Zeng, Jianhuan

AU - Chen, Chen

AU - Chi, Hung lin

AU - Shen, Geoffrey Qiping

N1 - Funding Information: The authors would like to acknowledge the financial support from The Hong Kong Polytechnic University Start‐up Fund (No. P0039232), HK RGC General Research Fund (No. 15219422), and the Fellowship of China Postdoctoral Science Foundation (No. 2021M692169). Publisher Copyright: © 2022 Computer-Aided Civil and Infrastructure Engineering.

PY - 2022/7

Y1 - 2022/7

N2 - Monitoring the fatigue of construction equipment operators (CEOs) is critical for preventing accidents and ensuring precision construction occupational health and safety (COHS). However, there exists a theoretical dilemma between centralized technical efficiency and decentralized data privacy. Thus, this study introduces smart work package learning (SWPL), a decentralized deep learning approach to monitor CEOs’ fatigue without privacy exposure risks. To illustrate the feasibility of SWPL as the fatigue classifier, this study implements fatigue monitoring through noninvasive facial images, and SWPL merges the updated parameters of the model from each smart work package (SWP). These updates are then validated by SWPs in the blockchain network and stored on the blockchain. More than 356 videos were derived from 124 operators. The results present that SWPL on decentralized SWP networks outperforms the deep learning model on individual SWP. The computational novelty is SWPL's dynamic parameter aggregation mechanism to avoid parameter exposure in centralized or fixed aggregators. The proposed SWPL will open up advanced developments in precision COHS.

AB - Monitoring the fatigue of construction equipment operators (CEOs) is critical for preventing accidents and ensuring precision construction occupational health and safety (COHS). However, there exists a theoretical dilemma between centralized technical efficiency and decentralized data privacy. Thus, this study introduces smart work package learning (SWPL), a decentralized deep learning approach to monitor CEOs’ fatigue without privacy exposure risks. To illustrate the feasibility of SWPL as the fatigue classifier, this study implements fatigue monitoring through noninvasive facial images, and SWPL merges the updated parameters of the model from each smart work package (SWP). These updates are then validated by SWPs in the blockchain network and stored on the blockchain. More than 356 videos were derived from 124 operators. The results present that SWPL on decentralized SWP networks outperforms the deep learning model on individual SWP. The computational novelty is SWPL's dynamic parameter aggregation mechanism to avoid parameter exposure in centralized or fixed aggregators. The proposed SWPL will open up advanced developments in precision COHS.

UR - http://www.scopus.com/inward/record.url?scp=85135179798&partnerID=8YFLogxK

U2 - 10.1111/mice.12891

DO - 10.1111/mice.12891

M3 - Journal article

AN - SCOPUS:85135179798

SN - 1093-9687

JO - Computer-Aided Civil and Infrastructure Engineering

JF - Computer-Aided Civil and Infrastructure Engineering

ER -

Smart work package learning for decentralized fatigue monitoring through facial images

Abstract

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this