TY - DATA
T1 - Machine learning-based classification model corresponding to the paper 'Machine learning to improve orientation estimation in sports situations challenging for inertial sensor use'
PY - 2021/07/13
AU - Marit van Dijk
UR - https://data.4tu.nl/articles/software/Machine_learning-based_classification_model_corresponding_to_the_paper_Machine_learning_to_improve_orientation_estimation_in_sports_situations_challenging_for_inertial_sensor_use_/14883927/1
DO - 10.4121/14883927.v1
KW - Madgwick filter
KW - Inertial Measurement Unit
KW - orientation estimation
KW - kinematics
KW - machine learning
KW - sports
N2 - Machine learning model as used in 'Machine learning to improve orientation estimation in sports situations challenging for inertial sensor use'. The model to run the Extended Madgwick filter is based on a random forest algorithm and can be used as explained in Figure 3 in the paper.<div><br></div><div>Explanation for use:</div><div>The model can be loaded and executed in Python using the following code</div><div>- RFmodel = pickle.load(open([filename_RFmodel], 'rb'))</div><div>- y = RFmodel.predict_proba(X)[:,1]<div>- if y > 0.5</div><div>     EFcorrect = 1</div><div> else</div><div>     EFcorrect = 0</div><div> </div><div>X are (normalized) input variables</div><div>y are probabilities for EFcorrect (see paper)<br></div></div>
ER -