Regresar

Rehabilitation of Patients with Hemiplegia Using Deep Learning Techniques to Control a Video Game

Abstract:

This document presents the design and implementation of a videogame with the use of Deep Learning, which helps the rehabilitation of the upper limb in minor patients with hemiplegia. The video game was developed in the Unity silver-form and aims to incite the movement of the affected member, for this, the user’s avatar performs different controlled actions through the gesticulation of the said limb. System tests were performed on a patient with left hemiparesis, which is a condition of the attenuated symptomatology of hemiplegia. The Neuronal Network was trained with 800 images of open hands and 800 images of closed hands of a child with left-hemiparesis. The results showed 99% reliability in the recognition of the hand, both open and closed. In this way, the patient with hemiparesis was motivated to open and close his hand continuously to carry out the control actions required by the videogame, promoting his rehabilitation and improvement of his fine motor skills.