Immediate effects of EVA midsole resilience and upper shoe structure on running biomechanics: a machine learning approach

Abstract

BackgroundResilience of midsole material and the upper structure of the shoe are conceptual characteristics that can interfere in running biomechanics patterns. Artificial intelligence techniques can capture features from the entire waveform, adding new perspective for biomechanical analysis. This study tested the influence of shoe midsole resilience and upper structure on running kinematics and kinetics of non-professional runners by using feature selection, information gain, and artificial neural network analysis.MethodsTwenty-seven experienced male runners (63 ± 44 km/week run) ran in four-shoe design that combined two resilience-cushioning materials (low and high) and two uppers (minimalist and structured). Kinematic data was acquired by six infrared cameras at 300 Hz, and ground reaction forces were acquired by two force plates at 1,200 Hz. We conducted a Machine Learning analysis to identify features from the complete kinematic and kinetic time series and from 42 discrete variables that had better discriminate the four shoes studied. For that analysis, we built an input data matrix of dimensions 1,080 (10 trials × 4 shoes × 27 subjects) × 1,254 (3 joints × 3 planes of movement × 101 data points + 3 vectors forces × 101 data points + 42 discrete calculated kinetic and kinematic features).ResultsThe applied feature selection by information gain and artificial neural networks successfully differentiated the two resilience materials using 200(16%) biomechanical variables with an accuracy of 84.8% by detecting alterations of running biomechanics, and the two upper structures with an accuracy of 93.9%.DiscussionThe discrimination of midsole resilience resulted in lower accuracy levels than did the discrimination of the shoe uppers. In both cases, the ground reaction forces were among the 25 most relevant features. The resilience of the cushioning material caused significant effects on initial heel impact, while the effects of different uppers were distributed along the stance phase of running. Biomechanical changes due to shoe midsole resilience seemed to be subject-dependent, while those due to upper structure seemed to be subject-independent.

Alternative shoe closure designs alter biomechanical performance during agility-based movements

“…It is possible that mechanical factors such as tighter fixation leading to less energy loss affected performance, yet changes in proprioceptive feedback may have also influenced these outcomes. The shoe upper has the largest contact area with the foot of any other part of the shoe (Onodera et al 2017), and likely influences proprioception in addition to comfort, fit, and mechanical properties. While it is difficult to directly determine if a shoe is aiding an athlete in using their preferred movement path (Nigg et al 2018), increased proprioceptive feedback should allow for increased awareness of the athlete's segment motion, and enable more accurate and quickly executed adjustments in their movement.…”

“…While the majority of shoe designs focus on the midsole, the shoe upper further facilitates the foot-to-shoe connection and provides the environment for the foot to operate. The shoe upper has the largest contact area with the foot of any other part of the shoe (Onodera et al 2017), and likely influences proprioception in addition to comfort, fit, and mechanical properties. Designers recognise the importance of fit to an athlete, but this has traditionally been defined by how the shoe last imitates an individual athlete (McPoil, 2000).…”

Three-dimensional motion capture data during repetitive overarm throwing practice

“…Studies that use more advanced analysis methods are mostly focused on cyclic movements such as gait and running. It has been shown that these methods may detect age- 2 and fatigue-related 5 changes, overall variability 3 , 4 , 7 , and the effects of different equipment 6 . However, limitations such as the sheer amount of rigorous work time and the financial support it takes to collect and process the data for the further calculations make it difficult for researchers to use more advanced analysis techniques.…”

Synthesis of the structure of functional systems of conversion class with a portional supply of initial products

“…Researchers try to solve optimization problems by creating new data processing technologies [22], for example, by integration of neural nets into the system structure [23]. However, the neural net must undergo a training procedure in order to distinguish one effective solution from another, more or less effective solution.…”