Application of Machine Learning to Predict Trajectory of the Center of Pressure (COP) Path of Postural Sway Using a Triaxial Inertial Sensor

Table 2

The parameters of ML algorithms.

ML algorithms	Parameter setting
LSBoost	No. of weak learners: 100 weak learners: decision trees
Bagging	No. of weak learners: 100 Weak learners: decision trees
SVM	Kernel function: rbf Epsilon: tenth of the standard deviation using the interquartile range of the desired outputs
ANN	Network type: feedforward No. of layers and nodes: 2 layers, [3 4] nodes
GP	Kernel function: squared exponentially Sigma: standard deviation of the desired outputs divided by Basic function: constant = 1