Sprint Assessment Using Machine Learning and a Wearable Accelerometer.

This study aims to automate sprint assessment by estimating υ0 and τ using machine learning and accelerometer data. To this end, photocells recorded 10 m split times of 28 subjects for three 40 m sprints while wearing an accelerometer around the waist. Features extracted from the accelerometer data were used to train a classifier to identify the sprint start and regression models to estimate the sprint model parameters. Estimates of υ0, τ, and 30 m sprint time (t30) were compared between the proposed method and a photocell method using root mean square error (RMSE) and Bland-Altman analysis. The RMSE of the sprint start estimate was 0.22 s and ranged from 0.52-0.93 m/s for υ0, 0.14-0.17 s for τ, and 0.23-0.34 s for t30. Model-derived sprint performance metrics from most regression models were significantly (p < 0.01) correlated with 30. Comparison of the proposed method and a physics-based method suggest pursuit of a combined approach since their strengths appear to complement each other. PMID: 30676153 [PubMed - as supplied by publisher]
Source: Journal of Applied Biomechanics - Category: Sports Medicine Tags: J Appl Biomech Source Type: research