Establishment of Risk Management Groups in Construction Based on Workers’ Age and Accident Probability Using Unsupervised Learning
Bibliographic record
Abstract
The construction industry is currently experiencing increased risks due to the aging workforce. As workers age, their physical capabilities often decline, leading to an increased likelihood of accidents. Despite this known correlation, no established standards exist to assess and manage the risks associated with workers’ age. This study aims to establish quantitative risk management groups based on workers’ age and accident probability, providing a structured framework for age-specific safety strategies in construction. To address this gap, this study systematically assessed accident rates based on workers’ age and identified risk management groups using a quantitative approach. The study began with data collection from 441 construction sites in Korea, encompassing 1.7 million workers and 2,460 accidents. Next, accident rates were calculated by worker age and categorized by construction project types, including residential, commercial, infrastructure, and plant projects. Using k-means clustering, a widely used machine learning technique for grouping data based on similarities, workers were grouped into risk management categories based on their age. Statistical validation confirmed the reliability of these clusters, demonstrating significant differences in accident rates across groups and project types. Notably, four risk management groups were identified for each project type, except for plant projects, which formed three distinct groups. These findings underscore the elevated risks faced by older workers and offer a structured, data-driven approach for safety decision-making. By providing project-specific insights, this study enables the implementation of targeted safety interventions, such as enhanced monitoring, tailored training programs, and resource allocation for high-risk groups. This framework offers decision-makers practical tools to enhance safety management and reduce accident risks effectively.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".