Near-miss accident detection for ironworkers using inertial measurement unit sensors

Sepideh S. Aria, Kanghyeok Yang, Changbum Ahn, Mehmet C. Vuran

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

Abstract

In the construction industry, fall accidents are the leading cause of construction-related fatalities; in particular, ironworkers have the highest risk of fatal accidents. Detecting near-miss accidents for ironworkers provides crucial information for interrupting and preventing the precursors of fall accidents while simultaneously addressing the problem of sparse accident data for ironworkers' fall-risk assessments. However, current methods for detecting near-miss accidents are based upon workers' self-reporting, which introduces variability to the collected data. This paper aims to present a method that uses Inertial Measurement Unit (IMU) sensor data to automatically detect near-miss accidents during ironworkers' walking motion. Then, using a Primal Laplacian Support Vector Machine, a developed semi-supervised algorithm trains a system to predict near-miss incidents using this data. The accuracy of this semi-supervised algorithm was measured with different metrics to assess the impact of the automated near-miss incident detection in construction worksites. The experimental validation of the algorithm indicates that near-miss incidents may be estimated and classified with considerable accuracy-above 98 percent. Then the computational burden of the proposed algorithm was compared with a One-Class Support Vector Machine (OC-SVM). Based upon the proposed detection approach, high-risk actions in the construction site can be detected efficiently, and steps towards reducing or eliminating them may be taken.

Original languageEnglish (US)
Title of host publication31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings
EditorsQuang Ha, Ali Akbarnezhad, Xuesong Shen
PublisherUniversity of Technology Sydney
Pages854-859
Number of pages6
ISBN (Electronic)9780646597119
StatePublished - Jan 1 2014
Event31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Sydney, Australia
Duration: Jul 9 2014Jul 11 2014

Publication series

Name31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings

Other

Other31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014
CountryAustralia
CitySydney
Period7/9/147/11/14

Fingerprint

Units of measurement
Accidents
Sensors
Support vector machines
Construction industry
Risk assessment

Keywords

  • Inertial Measurement Unit sensor
  • Near-misss
  • Sensing and Communication
  • Worker safety

ASJC Scopus subject areas

  • Artificial Intelligence
  • Hardware and Architecture
  • Civil and Structural Engineering
  • Building and Construction

Cite this

Aria, S. S., Yang, K., Ahn, C., & Vuran, M. C. (2014). Near-miss accident detection for ironworkers using inertial measurement unit sensors. In Q. Ha, A. Akbarnezhad, & X. Shen (Eds.), 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings (pp. 854-859). (31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings). University of Technology Sydney.

Near-miss accident detection for ironworkers using inertial measurement unit sensors. / Aria, Sepideh S.; Yang, Kanghyeok; Ahn, Changbum; Vuran, Mehmet C.

31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings. ed. / Quang Ha; Ali Akbarnezhad; Xuesong Shen. University of Technology Sydney, 2014. p. 854-859 (31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings).

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

Aria, SS, Yang, K, Ahn, C & Vuran, MC 2014, Near-miss accident detection for ironworkers using inertial measurement unit sensors. in Q Ha, A Akbarnezhad & X Shen (eds), 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings. 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings, University of Technology Sydney, pp. 854-859, 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014, Sydney, Australia, 7/9/14.
Aria SS, Yang K, Ahn C, Vuran MC. Near-miss accident detection for ironworkers using inertial measurement unit sensors. In Ha Q, Akbarnezhad A, Shen X, editors, 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings. University of Technology Sydney. 2014. p. 854-859. (31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings).
Aria, Sepideh S. ; Yang, Kanghyeok ; Ahn, Changbum ; Vuran, Mehmet C. / Near-miss accident detection for ironworkers using inertial measurement unit sensors. 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings. editor / Quang Ha ; Ali Akbarnezhad ; Xuesong Shen. University of Technology Sydney, 2014. pp. 854-859 (31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings).
@inproceedings{662f9e0329c04817a3d17a2a21af159b,
title = "Near-miss accident detection for ironworkers using inertial measurement unit sensors",
abstract = "In the construction industry, fall accidents are the leading cause of construction-related fatalities; in particular, ironworkers have the highest risk of fatal accidents. Detecting near-miss accidents for ironworkers provides crucial information for interrupting and preventing the precursors of fall accidents while simultaneously addressing the problem of sparse accident data for ironworkers' fall-risk assessments. However, current methods for detecting near-miss accidents are based upon workers' self-reporting, which introduces variability to the collected data. This paper aims to present a method that uses Inertial Measurement Unit (IMU) sensor data to automatically detect near-miss accidents during ironworkers' walking motion. Then, using a Primal Laplacian Support Vector Machine, a developed semi-supervised algorithm trains a system to predict near-miss incidents using this data. The accuracy of this semi-supervised algorithm was measured with different metrics to assess the impact of the automated near-miss incident detection in construction worksites. The experimental validation of the algorithm indicates that near-miss incidents may be estimated and classified with considerable accuracy-above 98 percent. Then the computational burden of the proposed algorithm was compared with a One-Class Support Vector Machine (OC-SVM). Based upon the proposed detection approach, high-risk actions in the construction site can be detected efficiently, and steps towards reducing or eliminating them may be taken.",
keywords = "Inertial Measurement Unit sensor, Near-misss, Sensing and Communication, Worker safety",
author = "Aria, {Sepideh S.} and Kanghyeok Yang and Changbum Ahn and Vuran, {Mehmet C.}",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
series = "31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings",
publisher = "University of Technology Sydney",
pages = "854--859",
editor = "Quang Ha and Ali Akbarnezhad and Xuesong Shen",
booktitle = "31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings",

}

TY - GEN

T1 - Near-miss accident detection for ironworkers using inertial measurement unit sensors

AU - Aria, Sepideh S.

AU - Yang, Kanghyeok

AU - Ahn, Changbum

AU - Vuran, Mehmet C.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In the construction industry, fall accidents are the leading cause of construction-related fatalities; in particular, ironworkers have the highest risk of fatal accidents. Detecting near-miss accidents for ironworkers provides crucial information for interrupting and preventing the precursors of fall accidents while simultaneously addressing the problem of sparse accident data for ironworkers' fall-risk assessments. However, current methods for detecting near-miss accidents are based upon workers' self-reporting, which introduces variability to the collected data. This paper aims to present a method that uses Inertial Measurement Unit (IMU) sensor data to automatically detect near-miss accidents during ironworkers' walking motion. Then, using a Primal Laplacian Support Vector Machine, a developed semi-supervised algorithm trains a system to predict near-miss incidents using this data. The accuracy of this semi-supervised algorithm was measured with different metrics to assess the impact of the automated near-miss incident detection in construction worksites. The experimental validation of the algorithm indicates that near-miss incidents may be estimated and classified with considerable accuracy-above 98 percent. Then the computational burden of the proposed algorithm was compared with a One-Class Support Vector Machine (OC-SVM). Based upon the proposed detection approach, high-risk actions in the construction site can be detected efficiently, and steps towards reducing or eliminating them may be taken.

AB - In the construction industry, fall accidents are the leading cause of construction-related fatalities; in particular, ironworkers have the highest risk of fatal accidents. Detecting near-miss accidents for ironworkers provides crucial information for interrupting and preventing the precursors of fall accidents while simultaneously addressing the problem of sparse accident data for ironworkers' fall-risk assessments. However, current methods for detecting near-miss accidents are based upon workers' self-reporting, which introduces variability to the collected data. This paper aims to present a method that uses Inertial Measurement Unit (IMU) sensor data to automatically detect near-miss accidents during ironworkers' walking motion. Then, using a Primal Laplacian Support Vector Machine, a developed semi-supervised algorithm trains a system to predict near-miss incidents using this data. The accuracy of this semi-supervised algorithm was measured with different metrics to assess the impact of the automated near-miss incident detection in construction worksites. The experimental validation of the algorithm indicates that near-miss incidents may be estimated and classified with considerable accuracy-above 98 percent. Then the computational burden of the proposed algorithm was compared with a One-Class Support Vector Machine (OC-SVM). Based upon the proposed detection approach, high-risk actions in the construction site can be detected efficiently, and steps towards reducing or eliminating them may be taken.

KW - Inertial Measurement Unit sensor

KW - Near-misss

KW - Sensing and Communication

KW - Worker safety

UR - http://www.scopus.com/inward/record.url?scp=84912535831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912535831&partnerID=8YFLogxK

M3 - Conference contribution

T3 - 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings

SP - 854

EP - 859

BT - 31st International Symposium on Automation and Robotics in Construction and Mining, ISARC 2014 - Proceedings

A2 - Ha, Quang

A2 - Akbarnezhad, Ali

A2 - Shen, Xuesong

PB - University of Technology Sydney

ER -