Bibliographic record
Abstract
This research presents a machine learning-based interactive design method for the creation of customized inserts that improve the fit of the PPE 3M 1863 and 3M 8833 respiratory face masks. These two models are the most commonly used by doctors and professionals during the recent covid19 pandemic. The proper fit of the mask is crucial for their performance. Characteristics and fit of current leading market brands were analyzed to develop a parametric design software workflow that results in a 3D printed insert customized to specific facial features and the mask that will be used. The insert provides a perfect fit for the respirator mask. Statistical face meshes were generated from an anthropometric database, and 3D facial scans and photos were taken from 200 doctors and nurses on an NHS trust hospital. The software workflow can start from either a 2D image of the face (picture) or a 3D mesh taken from a scanning device. The platform uses machine learning and a parametric design workflow based on key performance facial parameters to output the insert between the face and the 3M masks. It also generates the 3d printing file, which can be processed onsite at the hospital. The 2D image approach and the 3D scan approach initializing the system were digitally compared, and the resultant inserts were physically tested by 20 frontline personnel in an NHS trust hospital. Finally, we demonstrate the criticality of proper fit on masks for doctors and nurses and the versatility of our approach augmenting an already tested product through customized digital design and fabrication.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.005 | 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".