Category
Wearable Technology
Document Type
Paper
Abstract
The purpose of this study was to provide athletes/coaches with an easy-to-implement estimate of the power of standing long jump (SLJ), recognized as an indicator of the ability of lower limbs of exert power. To this aim, inertial sensors embedded in smartphones were used. A sample group of 150 trained young participants was recruited and asked to perform the SLJ task while holding the smartphone. A set of features was identified, based on biomechanical knowledge and literature, and then selected through Lasso regression to be feed as input of three different optimized machine learning architectures to estimate the SLJ power. A Multi-Layer Perceptron Regressor was selected as best performing model and showed, in the test phase, a RMSE of 0.37 W/kg. This smartphone-based estimate, if compared to an average power of 1.8 W/kg, represents a reasonable approximation.
Recommended Citation
DE LAZZARI, BEATRICE; VANNOZZI, GIUSEPPE; and CAMOMILLA, VALENTINA
(2024)
"STANDING LONG JUMP POWER ESTIMATION FROM SMARTPHONE IMUS,"
ISBS Proceedings Archive: Vol. 42:
Iss.
1, Article 203.
Available at:
https://commons.nmu.edu/isbs/vol42/iss1/203