Detecting the Impacts of Socioeconomic Factors on Regional Severity of Work-Related Casualties in China

Abstract

ABSTRACTWork-related casualties always cause serious damages to regional social and economic development. China's rapid development is raising a series of concerns about work-related casualties. The self-organizing maps (SOM) approach is applied in this study to detect the impacts of socioeconomic factors on the severity of work-related casualties in 31 regions of mainland China. The results show that: (1) the regional severity of work-related casualties and socioeconomic development seem to follow an inverted U-shaped pattern (i.e., the number of work-related fatalities increases to a peak at a certain stage and then decline along with socioeconomic development); (2) the industrial and employment structure have negative correlation with the regional severity of work-related casualties, specifically, the higher percentage of tertiary industry in gross regional product (GRP) and percentage of employed persons in tertiary industry may lead to fewer numbers of work-related fatalities in one region; (3) some socioeconomic factors like education level, medical condition, and insurance coverage have negative impacts on the regional severity of work-related casualties. Furthermore, the study also shows that the SOM approach is capable of improving clustering quality and visualization effects when facing multidimensional datasets compared with traditional cluster approaches such as K-Means and hierarchical-based clustering methods.