Reconstrução de parâmetros biomecânicos da marcha por meio de ciclogramas e redes neurais artificiais

• Autor(a) principal: Caparelli, Thiago Bruno
• Data de Publicação: 2017
• Tipo de documento: Tese
• Idioma: por
• Título da fonte: Repositório Institucional da UFU
• Texto Completo: https://repositorio.ufu.br/handle/123456789/20879; http://dx.doi.org/10.14393/ufu.te.2018.42
• topic: Marcha; Gait; Ciclogramas; Cyclograms; Redes Neurais Artificiais; Artificial Neural Networks; CNPQ::ENGENHARIAS::ENGENHARIA BIOMEDICA::BIOENGENHARIA::PROCESSAMENTO DE SINAIS BIOLOGICOS

Gait is one of the most influential elements in determining the quality of life of an individual, answering for more than 10% of the time spent in daily life activities. Gait alterations have a direct impact on a person´s functional capacity, affecting the maintenance of an independent and autonomous life. Early identification of dysfunctions allows the use of simpler and more effective therapies, reducing an overload of the public health system, and improving a patient's quality of life. In this study, a new predictive method for human gait was developed. The gait of 40 volunteers walking on a treadmill was recorded in the sagittal plane, using a 2D motion capture system. The extracted joint angles data were used to create cyclograms. Sections of the cyclograms were used as inputs to artificial neural networks (ANNs), since they can represent the kinematic behavior of the lower body. This allowed for prediction of future states of the moving body. The results indicate that ANNs can predict the future states of the gait with high accuracy. Both single point and cyclogram section predictions were successfully performed. Pearson’s correlation coefficient and matched-pairs ttest ensured the significance of the obtained results. The combined use of ANNs and simple, accessible hardware is of great value in clinical practice. The use of cyclograms facilitates the analysis, as several gait characteristics can be easily recognized by their characteristic geometric shape. The predictive model presented facilitates generation of data that can be used in robotic locomotion therapy both as control signals or feedback elements, aiding in the rehabilitation process of patients with gait dysfunction. The proposed system constitutes an interesting tool that can be explored to increase rehabilitation possibilities, providing better quality of life to patients.