Machine learning prediction of footwear slip resistance on glycerol-contaminated surfaces: A pilot study

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.

Prediction of coefficient of friction based on footwear outsole features

Traction testing of footwear is expensive, which may create barriers for certain users to assess footwear. This study aimed to develop a statistical model that predicts available coefficient of friction (ACOF) under boundary lubrication conditions based on inexpensive measurements of footwear outsole features. Geometric and material hardness parameters were measured from fifty-eight footwear designs labeled as slip-resistant. A robotic friction measurement device was used to quantify ACOF with canola oil as the contaminant. Stepwise regression methods were used to develop models based on the outsole parameters and floor type to predict ACOF. The predictive ability of the regression models was tested using the k-fold cross-validation method. Results indicated that 87% of ACOF variation was explained by three shoe outsole parameters (tread surface area, heel shape, hardness) and floor type. This approach may provide an assessment tool for safety practitioners to assess footwear traction and improve workers' safety.