Level-of-Expertise Classification for Identifying Safe and Productive Masons
Bibliographic record
Abstract
A large portion of the injuries incurred on construction sites is due to the lack of posture awareness among labors and crew while performing highly physical tasks. Most of these injuries are caused by bad and inexpert poses. Posture and gesture awareness is therefore a critical issue that can substantially decrease the number of injuries on construction sites. This paper presents a framework for identifying the level of expertise based using a machine learning-based classification algorithm. Expert and inexpert performance are identified, in order to detect unsafe and/or unproductive postures taken workers, and avoid injuries to improve productivity. The proposed framework has two major components: (1) codebook generation based on a sensor-based body joints model representing the poses taken by the labors, and (2) training a support vector machine (SVM)-based classifier for identifying expert vs inexpert performance. A set of experiments, with twenty-one masons with varying levels-of-expertise, is designed for verification and validation of the proposed methodology. An inertial measurement unit (IMU) suit, with 17 sensors, is used for data collection. While the method is applicable to any types of construction trades, this study focuses on masonry brick laying tasks. Results show that the classifier is capable of identifying the two forms with a reasonable accuracy. Moreover, SVM linear kernel classifier generates the most accurate results with lowest computational cost in classification. The low computational cost of this classifier makes it feasible for on-the-field deployment.
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 | 0.000 |
| 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 | 0.000 |
| 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".