A Data-Driven Approach for Deploying Safety Policies for Schedule Planning in Industrial Construction Projects: A Case Study
Bibliographic record
Abstract
Construction, by the nature of the work, is more accident-prone than other industries despite advancements in improving safety performance. Proactive mitigation and assessment of the safety performance of construction projects remain challenging due to the difficulty of acquiring, storing, and using data to produce accurate predictive models. This research focused on devising methods that allow decision makers to leverage existing data in the planning phase to streamline the development of predictive models. A data-driven approach to predict the probability of a safety incident occurring in a given construction project and within a novel discipline-level schedule is presented. By implementing the proposed model, decision makers can evaluate and mitigate the risk of a given project incident occurring by deploying discipline-level safety policies in the planning phase and modifying the schedule accordingly. A predictive model was developed based on selected safety-related metrics extracted from a data set comprising daily payroll data and incident reports, which represent 28 million working hours within eight different industrial construction projects in Canada. The model was implemented in a case study based on an industrial project to demonstrate the framework’s functionality and practical utility during the project planning phase. The results show that the revised safe plan can be achieved by incorporating safety considerations in the planning phase.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| 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".