×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

Machine learning in rehabilitation medicine and an example of the finger movement classifier for wrist simulator

Abstract

Machine learning in rehabilitation medicine and an example of the finger movement classifier for wrist simulator

Stebakov I.N., Shutin D.V., Marakhin N.A.

Incoming article date: 17.06.2020

This article provides an overview of scientific papers that describe the use of machine learning methods for various tasks in rehabilitatin medicine. Examples of studies and their main results are given. At the moment, a simulator for wrist joint restoration is being developed. The use of simulators to restore the hand can be associated with the finger movements determination on a healthy hand. This problem requires a classification of movements and can be solved by using machine learning. This article presents the results of the development of classifiers for determining finger movements. The following methods were used: logistic regression, the support vector machine, and the neural network. The database obtained by using electromyographic sensors was used to train and test the models. Classification results are also compared with the results of original studies. The most effective method for classifying finger movements was selected and justified.

Keywords: rehabilitation, machine learning, neural networks, classification of movements, wrist simulator