A Machine Learning Strategy for Locomotion Classification and Parameter Estimation Using Fusion of Wearable Sensors.

The accurate classification of ambulation modes and estimation of walking parameters is a challenging problem that is key to many applications. Knowledge of the user's state can enable rehabilitative devices to adapt to changing conditions, while in a clinical setting it can provide physicians with more detailed patient activity information. This study describes the development and optimization process of a combined locomotion mode classifier and environmental parameter estimator using machine learning and wearable sensors.

Automated gap-filling for marker-based biomechanical motion capture data.

Marker-based motion capture presents the problem of gaps, which are traditionally processed using motion capture software, requiring intensive manual input. We propose and study an automated method of gap-filling that uses inverse kinematics (IK) to close the loop of an iterative process to minimize error, while nearly eliminating user input. Comparing our method to manual gap-filling, we observe a 21% reduction in the worst-case gap-filling error ( < 0.