Machine learning prediction of footwear slip resistance on glycerol-contaminated surfaces: A pilot study
Bibliographic record
Abstract
Slippery surfaces due to oil spills pose a significant risk in various environments, including industrial workplaces, kitchens, garages, and outdoor areas. These situations can lead to accidents and falls, resulting in injuries that range from minor bruises to severe fractures or head trauma. To mitigate such risks, the use of slip resistant footwear plays a crucial role. In this study, we aimed to develop an Artificial Intelligence model capable of classifying footwear as having either high or low slip resistance based on the geometric characteristics and material parameters of their outsoles. Our model was trained on a unique dataset comprising images of 37 indoor work footwear outsoles made of rubber. To evaluate the slip resistant property of the footwear, all samples were tested using a cart-type friction measurement device, and the static and dynamic Coefficient of Frictions (COFs) of each outsole was determined on a glycerol-contaminated surface. Machine learning techniques were implemented, and a classification model was developed to determine high and low slip resistant footwear. Among the various models evaluated, the Support Vector Classifier (SVC) obtained the best results. This model achieved an accuracy of 0.68 ± 0.15 and an F1-score of 0.68 ± 0.20. Our results indicate that the proposed model effectively yet modestly identified outsoles with high and low slip resistance. This model is the first step in developing a model that footwear manufacturers can utilize to enhance product quality and reduce slip and fall incidents.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".