Artificial Neural Networks to Quantify Motor Skills in Children with Cerebral Hemiparesis

Previous studies have sought to improve the way of classifying upper limb motor involvement in patients with alterations or pathologies in the central nervous system, so it has become of great importance to find an objective way of measuring and classifying the degree of movement capacity. This work uses the artificial neural network method to quantify the motor skils at five levels of the SSULF scale proposed to have a better assessment of the degree of upper limb motor functionality in patients diagnosed with cerebral hemiparesis.