A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device

Houtan Jebelli, Mohammad Mahdi Khalili, Sungjoo Hwang, Sang Hyun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Construction is known as one of the most stressful occupations due to its involvement with physiologically and psychologically demanding tasks performed in a hazardous work environment. Because workers' stress is a critical factor that adversely affects workers' productivity, safety, well-being, and work quality, understanding workers' stress should take precedence in the management of excessive stress. Various instruments for subjective measurement towards one's perceived stress have been used, but such methods rely on imprecise memory and reconstruction of feelings in the past. Recent advancements in wearable Electroencephalography (EEG) devices possess a potential for quantitative measurement of human stress by directly capturing central nervous system activities from stress. However, its capability of measuring field workers' stress under real occupational stressors remains questionable. This research thus proposes a framework to recognize construction workers' stress at the field based on their brain activity recorded from a wearable EEG. Specifically, this framework applies a supervised learning algorithm-support vector machine-in detecting workers' stress while working in different conditions. Workers salivary cortisol levels, which is a stress-related hormone, were used to label the tasks as low or high-stress level. Relevant time and frequency domain features in EEG signals were calculated. Results yielded a high of 71.1% accuracy using SVM in recognizing workers' stress, which is a very promising result given that stress recognition with an exquisite EEG device in the clinical domain has at most the similar level of accuracy. The results show the potential for recognizing construction workers' stress at the field by applying machine learning algorithms using workers' brain waves recorded from a wearable EEG device. This EEG based stress detection approach will help to enhance workplace environment and conditions as well as to improve workers' health by early detection and mitigation of the factors that cause stress.

Original languageEnglish (US)
Title of host publicationConstruction Research Congress 2018
Subtitle of host publicationSafety and Disaster Management - Selected Papers from the Construction Research Congress 2018
EditorsChristofer Harper, Yongcheol Lee, Rebecca Harris, Charles Berryman, Chao Wang
PublisherAmerican Society of Civil Engineers (ASCE)
Pages40-50
Number of pages11
ISBN (Electronic)9780784481288
DOIs
StatePublished - Jan 1 2018
EventConstruction Research Congress 2018: Safety and Disaster Management, CRC 2018 - New Orleans, United States
Duration: Apr 2 2018Apr 4 2018

Publication series

NameConstruction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018
Volume2018-April

Other

OtherConstruction Research Congress 2018: Safety and Disaster Management, CRC 2018
CountryUnited States
CityNew Orleans
Period4/2/184/4/18

Fingerprint

Supervised learning
Electroencephalography
Learning algorithms
Brain
Cortisol
Hormones
Bioelectric potentials
Neurology
Support vector machines
Learning systems
Labels

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Building and Construction

Cite this

Jebelli, H., Khalili, M. M., Hwang, S., & Lee, S. H. (2018). A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device. In C. Harper, Y. Lee, R. Harris, C. Berryman, & C. Wang (Eds.), Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018 (pp. 40-50). (Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018; Vol. 2018-April). American Society of Civil Engineers (ASCE). https://doi.org/10.1061/9780784481288.005
Jebelli, Houtan ; Khalili, Mohammad Mahdi ; Hwang, Sungjoo ; Lee, Sang Hyun. / A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device. Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018. editor / Christofer Harper ; Yongcheol Lee ; Rebecca Harris ; Charles Berryman ; Chao Wang. American Society of Civil Engineers (ASCE), 2018. pp. 40-50 (Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018).
@inproceedings{e31a3cda39e24b1b91cbf55e4f31ad94,
title = "A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device",
abstract = "Construction is known as one of the most stressful occupations due to its involvement with physiologically and psychologically demanding tasks performed in a hazardous work environment. Because workers' stress is a critical factor that adversely affects workers' productivity, safety, well-being, and work quality, understanding workers' stress should take precedence in the management of excessive stress. Various instruments for subjective measurement towards one's perceived stress have been used, but such methods rely on imprecise memory and reconstruction of feelings in the past. Recent advancements in wearable Electroencephalography (EEG) devices possess a potential for quantitative measurement of human stress by directly capturing central nervous system activities from stress. However, its capability of measuring field workers' stress under real occupational stressors remains questionable. This research thus proposes a framework to recognize construction workers' stress at the field based on their brain activity recorded from a wearable EEG. Specifically, this framework applies a supervised learning algorithm-support vector machine-in detecting workers' stress while working in different conditions. Workers salivary cortisol levels, which is a stress-related hormone, were used to label the tasks as low or high-stress level. Relevant time and frequency domain features in EEG signals were calculated. Results yielded a high of 71.1{\%} accuracy using SVM in recognizing workers' stress, which is a very promising result given that stress recognition with an exquisite EEG device in the clinical domain has at most the similar level of accuracy. The results show the potential for recognizing construction workers' stress at the field by applying machine learning algorithms using workers' brain waves recorded from a wearable EEG device. This EEG based stress detection approach will help to enhance workplace environment and conditions as well as to improve workers' health by early detection and mitigation of the factors that cause stress.",
author = "Houtan Jebelli and Khalili, {Mohammad Mahdi} and Sungjoo Hwang and Lee, {Sang Hyun}",
year = "2018",
month = "1",
day = "1",
doi = "10.1061/9780784481288.005",
language = "English (US)",
series = "Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018",
publisher = "American Society of Civil Engineers (ASCE)",
pages = "40--50",
editor = "Christofer Harper and Yongcheol Lee and Rebecca Harris and Charles Berryman and Chao Wang",
booktitle = "Construction Research Congress 2018",
address = "United States",

}

Jebelli, H, Khalili, MM, Hwang, S & Lee, SH 2018, A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device. in C Harper, Y Lee, R Harris, C Berryman & C Wang (eds), Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018. Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018, vol. 2018-April, American Society of Civil Engineers (ASCE), pp. 40-50, Construction Research Congress 2018: Safety and Disaster Management, CRC 2018, New Orleans, United States, 4/2/18. https://doi.org/10.1061/9780784481288.005

A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device. / Jebelli, Houtan; Khalili, Mohammad Mahdi; Hwang, Sungjoo; Lee, Sang Hyun.

Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018. ed. / Christofer Harper; Yongcheol Lee; Rebecca Harris; Charles Berryman; Chao Wang. American Society of Civil Engineers (ASCE), 2018. p. 40-50 (Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018; Vol. 2018-April).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device

AU - Jebelli, Houtan

AU - Khalili, Mohammad Mahdi

AU - Hwang, Sungjoo

AU - Lee, Sang Hyun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Construction is known as one of the most stressful occupations due to its involvement with physiologically and psychologically demanding tasks performed in a hazardous work environment. Because workers' stress is a critical factor that adversely affects workers' productivity, safety, well-being, and work quality, understanding workers' stress should take precedence in the management of excessive stress. Various instruments for subjective measurement towards one's perceived stress have been used, but such methods rely on imprecise memory and reconstruction of feelings in the past. Recent advancements in wearable Electroencephalography (EEG) devices possess a potential for quantitative measurement of human stress by directly capturing central nervous system activities from stress. However, its capability of measuring field workers' stress under real occupational stressors remains questionable. This research thus proposes a framework to recognize construction workers' stress at the field based on their brain activity recorded from a wearable EEG. Specifically, this framework applies a supervised learning algorithm-support vector machine-in detecting workers' stress while working in different conditions. Workers salivary cortisol levels, which is a stress-related hormone, were used to label the tasks as low or high-stress level. Relevant time and frequency domain features in EEG signals were calculated. Results yielded a high of 71.1% accuracy using SVM in recognizing workers' stress, which is a very promising result given that stress recognition with an exquisite EEG device in the clinical domain has at most the similar level of accuracy. The results show the potential for recognizing construction workers' stress at the field by applying machine learning algorithms using workers' brain waves recorded from a wearable EEG device. This EEG based stress detection approach will help to enhance workplace environment and conditions as well as to improve workers' health by early detection and mitigation of the factors that cause stress.

AB - Construction is known as one of the most stressful occupations due to its involvement with physiologically and psychologically demanding tasks performed in a hazardous work environment. Because workers' stress is a critical factor that adversely affects workers' productivity, safety, well-being, and work quality, understanding workers' stress should take precedence in the management of excessive stress. Various instruments for subjective measurement towards one's perceived stress have been used, but such methods rely on imprecise memory and reconstruction of feelings in the past. Recent advancements in wearable Electroencephalography (EEG) devices possess a potential for quantitative measurement of human stress by directly capturing central nervous system activities from stress. However, its capability of measuring field workers' stress under real occupational stressors remains questionable. This research thus proposes a framework to recognize construction workers' stress at the field based on their brain activity recorded from a wearable EEG. Specifically, this framework applies a supervised learning algorithm-support vector machine-in detecting workers' stress while working in different conditions. Workers salivary cortisol levels, which is a stress-related hormone, were used to label the tasks as low or high-stress level. Relevant time and frequency domain features in EEG signals were calculated. Results yielded a high of 71.1% accuracy using SVM in recognizing workers' stress, which is a very promising result given that stress recognition with an exquisite EEG device in the clinical domain has at most the similar level of accuracy. The results show the potential for recognizing construction workers' stress at the field by applying machine learning algorithms using workers' brain waves recorded from a wearable EEG device. This EEG based stress detection approach will help to enhance workplace environment and conditions as well as to improve workers' health by early detection and mitigation of the factors that cause stress.

UR - http://www.scopus.com/inward/record.url?scp=85047649358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047649358&partnerID=8YFLogxK

U2 - 10.1061/9780784481288.005

DO - 10.1061/9780784481288.005

M3 - Conference contribution

AN - SCOPUS:85047649358

T3 - Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018

SP - 40

EP - 50

BT - Construction Research Congress 2018

A2 - Harper, Christofer

A2 - Lee, Yongcheol

A2 - Harris, Rebecca

A2 - Berryman, Charles

A2 - Wang, Chao

PB - American Society of Civil Engineers (ASCE)

ER -

Jebelli H, Khalili MM, Hwang S, Lee SH. A supervised learning-based construction workers' stress recognition using a wearable electroencephalography (EEG) device. In Harper C, Lee Y, Harris R, Berryman C, Wang C, editors, Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018. American Society of Civil Engineers (ASCE). 2018. p. 40-50. (Construction Research Congress 2018: Safety and Disaster Management - Selected Papers from the Construction Research Congress 2018). https://doi.org/10.1061/9780784481288.005