Chapter
Mar 29, 2018
Evaluating the Performance of Machine Learning Algorithms on Construction Accidents: An Application of ROC Curves
Authors: Pouya Gholizadeh [email protected], Behzad Esmaeili [email protected], and Babak Memarian [email protected]Author Affiliations
Publication: Construction Research Congress 2018
Abstract
The significant amount of safety data being collected on construction sites provides a valuable source of information for researchers seeking to better understand the root causes of accidents using advanced-analysis methods such as data mining and machine learning techniques. However, evaluating the predictive performance of these methods can be challenging. While simple measures such as total accuracy have been widely used to assess the classification performance of these algorithms, studies show that relying solely on these individual measures can be misleading. One of the techniques that can be used to organize classifiers and visualize their performance is receiver operating characteristics (ROC) curves. ROC curves are commonly used in machine learning and data mining studies to improve medical decision making; however, their application in construction safety is minimal. This study evaluates the application of ROC curves to more accurately interpret the output of machine learning methods, because understanding the mechanism of ROC curves will improve the classification performance of machine learning methods (i.e., AdaBoost) when predicting the degree of construction injuries. To achieve this goal, more than 700 accident reports were collected from national databases and analyzed via multiple machine learning techniques. The findings of this study indicate that applying ROC curves can yield the selection of better classification criteria and can reduce the cost of classification errors. The method is particularly beneficial when the costs of errors are unequal or when the data is highly imbalanced.
Get full access to this article
View all available purchase options and get full access to this chapter.
Information & Authors
Information
Published In
Copyright
© 2018 American Society of Civil Engineers.
History
Published online: Mar 29, 2018
Permissions
Request permissions for this article.
Authors
Affiliations
Ph.D. Student, Sid and Reva Dewberry Dept. of Civil, Environmental and Infrastructure Engineering, Volgenau School of Engineering, George Mason Univ., 4400 University Dr., Fairfax, VA 22030. E-mail: [email protected]
Assistant Professor, Sid and Reva Dewberry Dept. of Civil, Environmental and Infrastructure Engineering, Volgenau School of Engineering, George Mason Univ., 4400 University Dr., MS 6C1, Fairfax, VA 22030. E-mail: [email protected]
Director, Exposure Control Technologies Research, CPWR – The Center for Construction Research and Training, 8484 Georgia Ave., Suite 1000, Silver Spring, MD 20910. E-mail: [email protected]
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
View Options
Get Access
Access content
Please select your options to get access
Log in/Register
Log in via your institution (Shibboleth)
ASCE Members:
Please log in to see member pricing
Purchase
Save for later Item saved, go to cart Information on ASCE Library Cards
ASCE Library Cards let you download journal articles, proceedings papers, and available book chapters across the entire ASCE Library platform. ASCE Library Cards remain active for 24 months or until all downloads are used. Note: This content will be debited as one download at time of checkout.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Get Access
Access content
Please select your options to get access
Log in/Register
Log in via your institution (Shibboleth)
ASCE Members:
Please log in to see member pricing
Purchase
Save for later Item saved, go to cart Information on ASCE Library Cards
ASCE Library Cards let you download journal articles, proceedings papers, and available book chapters across the entire ASCE Library platform. ASCE Library Cards remain active for 24 months or until all downloads are used. Note: This content will be debited as one download at time of checkout.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.
Terms of Use: ASCE Library Cards are for individual, personal use only. Reselling, republishing, or forwarding the materials to libraries or reading rooms is prohibited.