Table 2.

Feature sets and performance metrics of machine learning models trained on helmet impact testing data

	Training			Validation
Model features	RMSE	MAE	R2	RMSE	MAE	R2
MBM MPS	0.036	0.026	0.906	0.054	0.043	0.746
Peak angular velocity	0.033	0.024	0.928	0.059	0.046	0.707
Peak angular acceleration	0.038	0.029	0.897	0.066	0.052	0.617
MBM MPS, peak angular velocity	0.031	0.022	0.933	0.051	0.040	0.785
MBM MPS, peak angular acceleration	0.029	0.020	0.949	0.052	0.038	0.759
Peak angular velocity, peak angular acceleration	0.029	0.020	0.950	0.058	0.046	0.715
All	0.028	0.019	0.953	0.047	0.035	0.823

Features were drawn from each plane, e.g., the MBM MPS model included one feature from each plane. Metrics used to evaluate the training and validation of the ML models include RMSE, MAE, and correlation coefficient (R²). The model utilizing both MBM-based and all kinematics-based features (bolded) performed best.