Enhancing Safety and Well Being of Aging Workforce within the Transportation Sector: An Association Rule Data Mining Approach for Understanding Causes and Impacts of Worker Compensation Claims

Details

• Creators:
  El-awaday, Islam
• Corporate Creators:
  University of Nebraska. Mid-America Transportation Center ; Missouri University of Science and Technology
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Data Mining Injury Causes Insurance Claims Labor Force Occupational Safety Workers Compensation
• Publication/ Report Number:
  25-1121-3002-103
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report June 2023 – May 2025
• Corporate Publisher:
  University of Nebraska-Lincoln. Mid-America Transportation Center
• Abstract:
  Safety within the transportation sector has long been a concern for researchers and industry stakeholders. High injury rates in the transportation sector and an increase in expenditure toward transportation projects, state departments of transportation put in place key performance indicators aiming for a safer workforce. To do so, root causes of safety incidents must be studied to help prevent/mitigate future incidents. Previous studies addressed this using various analytical approaches; however, they have either failed to account for both internal and external factors, only accounted for one factor at a time affecting safety, or conducted a methodology requiring extensive, confidential data that is difficult to retrieve. The goal is to decipher combinations of internal and external reasons behind occupational injuries in the transportation sector by utilizing top-level data without the need to access detailed confidential records. This was accomplished through a systematic methodological approach, employing a funneled multiple linear regression (MLR), that offered a novel way of evaluating the influence of different variable combinations on safety outcomes. The methodology was composed of (1) identifying independent and dependent variables from publicly available data by the Bureau of Labor Statistics, (2) studying multicollinearity, (3) conducting feature selection, and (4) applying a funneled MLR approach to examine all possible variable combinations. The findings included 5 high-performing MLR models composed of critical combinations of variables impacting safety incidents in the transportation sector. The contribution of this research is providing actionable insights for developing targeted interventions aimed at mitigating safety risks and enhancing workplace safety within the transportation sector.
• Format:
  PDF
• Funding:
  69A3552348307
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:cd4e675b40e61c074f5177310190e17c3e719f405d56379dd59fd6c3065805f4536ed558aa0120f57be4c19e903f4504cc083dba460a791d7343a4fc18a49594
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/85152/dot_85152_DS1.pdf
• File Type:
  [PDF - 2.03 MB ]