Working Group leader: Alex Vakanski
Group members: David Paul, Russell Baker
This group focuses on the development of mathematical models for representing human motions, to potentially benefit patients undertaking a physical rehabilitation therapy (e.g., following a stroke, or due to other medical conditions). The research employs deep neural networks for modeling human motions at multiple hierarchical levels of abstraction. The aim is to encode the movements of a patient in performing physical exercises into a set of trajectory features and further use the features in developing an algorithm for evaluation of the patient’s performance.
The group developed a preliminary model of human movements by using a recurrent neural networks architecture, as well as the team proposed a set of metrics for assessment of patient’s performance during physical therapy exercises. The group has created a dataset of human motions related to physical rehabilitations exercises. The current focus of the group is on expanding the work on modeling therapy exercises into hierarchical models of patient movements, and subsequently, comparison and assessment of performance metrics for movement evaluation.
The objective of the group is to apply for external funding in 2018 and to continue the work with external funds.
Mathematical Modeling and Evaluation of Human Motions in Physical Therapy Using Mixture Density Neural Networks
Vakanski A, Ferguson JM, Lee S, (2016) Mathematical modeling and evaluation of human motions in physical therapy using mixture density neural networks. Journal of Physiotherapy & Physical Rehabilitation, 1(118). PMC5242735
Vakanski, A., Ferguson, J. M., & Lee, S. (2017). Metrics for Performance Evaluation of Patient Exercises during Physical Therapy. International Journal of Physical Medicine & Rehabilitation, 5(3), 403.
Vakanski, A., Jun, H., Paul, D., & Baker, R. (2018). A Data Set of Human Body Movements for Physical Rehabilitation Exercises. Data, 3(1), 2. http://doi.org/10.3390/data3010002