Time-Cuboid Model with Reduced False Alarms for Construction Safety
Bibliographic record
Abstract
Struck-by-equipment hazard is a leading cause of construction fatalities. Although several proximity detection systems have been developed to alleviate the risks of this type of hazard, the frequently generated false alarms which do not represent actual hazardous situations have limited their real-world application. Therefore, the time-cuboid model is developed to enhance construction safety by preventing struck-by-equipment accidents with reduced false alarms. The time-cuboid model effectively reduces false alarms by (1) fully considering an entities’ 3D position, orientation and velocity; (2) using a dynamic and adjusted warning distance; and (3) utilizing the developed safety rules which use relative position, moving direction, speed and a pairwise 3D safety query to identify actual as well as impending spatial interferences. Simulation and a controlled field experiment were conducted to evaluate the effectiveness of the time-cuboid model. The time-cuboid model is effective in reducing false alarms as no false negatives are generated and all obtained false positive rates (FPRs) are zero which are much lower than the FPRs of the prevalent proximity detection method (62.1% averagely). The reduced alarm percentages (RAPs) indicate that at least 50.2% alarms generated by the prevalent method can be avoided by the time-cuboid model. Reduction of false alarms contributes to enhancing construction safety, mobility and productivity.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".