Evaluation of Self-Rehabilitation Movements by Hidden Markov Model

Abstract:

This study aims to propose a statistical model to automatically assess the correctness of rehabilitation movements performed by patients. Ten Hidden Markov Models are developed and trained, in order to discriminate in real time the main faults in the execution of therapeutic exercises for reeducation after hip replacement surgery. An experiment on real patients shows that the algorithm is as accurate as the physiotherapists to discriminate and identify the error in the movement. The results are discussed in terms of the required setup for a successful implementation of this method in a tele-rehabilitation platform.

Año de publicación:

2018

Keywords:

• movement recognition
• Decision Support Systems
• Machine learning
• Probabilistic model
• Health computing

Fuente:

scopus