Performance of artificial neural network compared to multi-linear regression in prediction of countermovement jump height

Abstract

Previous research has used primarily linear regression models to predict jump height and establish contributors of performance. The purpose of this study was to compare the performance of artificial neural network (ANN) and multi-linear regression (MLR) in prediction of countermovement jump (CMJ) height and investigating the contribution of kinematic variables to CMJ performance. Thirty-four healthy young male athletes performed a total of 204 CMJ while eight kinematic variables (the hip, knee, and ankle angles at the begging of the concentric phase of CMJ, the hip and knee take-off angles, and the shoulder, hip, and knee maximum angular velocities) were used as inputs to ANN and MLR to predict CMJ height. The correlation coefficients between the jump height and the predicted value by the developed models indicated that ANN predict CMJ height better than MLR (R² = 0.68 compared to R² = 0.44). Moreover, the root mean squared error of prediction showed better performance of the ANN rather than the MLR (4.8 cm compared to 5.3 cm). The shoulder and hip maximum angular velocities were the most important contributors, and then the hip and knee take-off angles contributed to CMJ height. In conclusion, implementing ANN to identify key variables of performance may also be relevant for other sport skills.