Abstract: A method for training an algorithm for predicting a knee adduction moment (KAM) includes, while each subject walks over forceplates, capturing kinematic data, generating first ground reaction force (GRF) data, generating second GRF data, and generating reference KAM data based on the kinematic data and the first GRF data. While repeatedly training the algorithm by incrementing i by one, the method performs generating a model, which predicts reference KAM data, validating the predicted reference KAM data based on reference KAM data of the subjects other than the i-th subject, adjusting internal parameters by minimizing an error between the predicted KAM data and reference KAM data of the subjects other than the i-th subject, and producing an accuracy score for the model based on an error between the predicted reference KAM data and the reference KAM data of the i-th subject.

Abstract: A method for training an algorithm for predicting a knee adduction moment (KAM) includes, while each subject walks over forceplates, capturing kinematic data, generating first ground reaction force (GRF) data, generating second GRF data, and generating reference KAM data based on the kinematic data and the first GRF data. While repeatedly training the algorithm by incrementing i by one, the method performs generating a model, which predicts reference KAM data, validating the predicted reference KAM data based on reference KAM data of the subjects other than the i-th subject, adjusting internal parameters by minimizing an error between the predicted KAM data and reference KAM data of the subjects other than the i-th subject, and producing an accuracy score for the model based on an error between the predicted reference KAM data and the reference KAM data of the i-th subject.

Abstract: A gait analysis apparatus includes a bottom insole pad, a top insole pad layered over the bottom insole pad and configured to be worn by a limb of a subject, a plurality of force sensors configured to sense force exerted by the limb at least in two directions and affixed between the top insole pad and the bottom insole pad, and a processor configured to collect measurement data from the plurality of force sensors and determine a pose of or abnormality in the limb based on the measurement data and a predetermined profile.