Abstract
In the construction industry, it is difficult to predict occupational accidents because various accident characteristics arise simultaneously and organically in different types of work. Furthermore, even when analyzing occupational accident data, it is difficult to deduce meaningful results because the data recorded by the incident investigator are qualitative and include a wide variety of data types and categories. Recently, numerous studies have used machine learning to analyze the correlations in such complex construction accident data; however, heretofore the focus has been on predicting severity with various variables, and several limitations remain when deriving the correlations between features from various variables. Thus, this paper proposes a data processing procedure that can efficiently manipulate accident data using optimal machine learning techniques and derive and systematize meaningful variables to rationally approach such complex problems. In particular, among the various variables, the most influential variables are derived through methods such as clustering, chi-square, Cramer’s V, and predictor importance; then, the analysis is simplified by optimally grouping the variables. For accident data with optimal variables and elements, a predictive model is constructed between variables, using a support vector machine and decision-tree-based ensemble; then, the correlation between the dependent and independent variables is analyzed through an alluvial flow diagram for several cases. Therefore, a new processing procedure has been introduced in data preprocessing and accident prediction modelling to overcome difficulties from complex and diverse construction occupational accident data, and effective accident prevention is possible by deriving correlations of construction accidents using this process.
Highlights
In recent decades, various industrial safety management systems have been introduced and improved upon; occupational safety remains unstable and low
The first data preprocessing was carried out to derive the main variables that have a major influence on the construction accident
latent class cluster analysis (LCCA) was first applied as a data preprocessing method, because it can group without specifying a separate target
Summary
Various industrial safety management systems have been introduced and improved upon; occupational safety remains unstable and low. Sci. 2020, 10, 7949 occupational accidents through simple correlations—and thereby establish safety measures to prevent them—are limited. Extensive research has been conducted over the past decades to increase the safety performance of construction sites. In 2002, Hinze conducted a study to improve the safety performance of and incentives for minimizing injuries on construction sites [2]; in 2005, Chi et al analyzed the correlations of factors contributing to different types of falls [3]. In 2008, Choudhry et al analyzed fundamental safety factors through a questionnaire, based on the practical abilities of construction safety experts to ensure site safety, and they proposed measures to improve safety in the industry [4]. The concept of occupational safety at construction sites was not well defined at an early stage; the data collected were not sufficient to identify accidents. The dynamic characteristics of construction projects have not been adequately reflected in most studies, and because most of the developed models did not rely on empirical data, they could only be applied to limited cases
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
