Sistema de inteligencia artificial para la evaluación de la función motora en la trayectoria de extremidad superior

Abstract

The evaluation of motor function rehabilitation currently does not have a quantifiable way to measure its progress, since the medical specialist uses daily activities that the patient can perform or tables with ranges to measure the progress of rehabilitation. For this reason, for traditional rehabilitation measurement is a challenge in the accuracy part of progress. It is in this way that technology seeks to solve this problem from one of the most relevant branches that it has, which is artificial intelligence. The purpose of this research is to develop an artificial intelligence system for the evaluation of the mobility and extraction of the trajectory of an upper extremity, specifically the trajectory of the elbow and shoulder joint. Likewise, the use of the JAVA programming language is proposed to provide all the necessary tools in the detection of the key points of the body thanks to the use of artificial vision from the OpenCV artificial intelligence library and the combined use with NVIDIA cuDNN deep learning. with the Compute Unified Device Architecture (CUDA).