MOCAP and AI-Based Automated Physical Demand Analysis for Workplace Safety
Bibliographic record
Abstract
Worker safety and productivity and the factors that affect them, such as ergonomics, are essential aspects of construction projects. The application of ergonomics and the identification of the connections between workers and assigned tasks have led to a decrease in worker injuries and discomfort, beneficial effects on productivity, and a reduction in project costs. Nevertheless, workers in the construction area are often subjected to awkward body postures and repetitive motions that cause musculoskeletal disorders, in turn leading to delays in production. As a systematic and widely used procedure that generates a final document or form, physical demand analysis (PDA) assesses the health and safety of workers engaged in construction or manufacturing activities and proactively evaluates ergonomic risks. However, to gather the necessary information, traditional PDA methods require ergonomists to spend significant time observing and interviewing workers. To increase the speed and accuracy of PDA, this study focuses on developing a systematic PDA framework to automatically fill a posture-based PDA form and address the physiological aspects of task demands. In contrast to the traditional observation-based approach, the proposed framework uses a motion capture (MOCAP) system and a rule-based expert system to obtain joint angles and body segment positions in different work situations, convert the measurements to objective identification of activities and their frequencies, and then automatically populate the PDA forms. The framework is tested and validated in both laboratory and on-site environments by comparing the generated forms with PDA forms filled out by ergonomists. The results indicate that the MOCAP-/AI-based automated PDA framework successfully improves the performance of PDA in terms of accuracy, consistency, and time consumption. Ultimately, this framework can aid in the design of job tasks and work environments with the goal of promoting health, safety, and productivity in the workplace.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".