Modelo computacional baseado em conhecimento para avaliação postural tridimensional

• Ano de defesa: 2017
• Autor(a) principal: Sant'Ana, Hugo Gustavo Franco
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Alagoas; Brasil; Programa de Pós-Graduação em Modelagem Computacional de Conhecimento; UFAL
• Palavras-chave em Português: Fotogrametria; Postura humana; Biofotogrametria computadorizada; Modelo computacional; Software; Photogrammetry; Human posture; Computerized biophotogrammetry; Computational model; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: http://www.repositorio.ufal.br/handle/riufal/1845

It is well established in the literature the importance of the posture characterization for a good kinetic-functional diagnosis, identifying and measuring postural changes and muscle imbalances allowing the adequate elaboration of rehabilitation programs. To facilitate the action of the specialist, computer programs were developed for three-dimensional analyzes of the curvatures of the spine from two-dimensional images. Such methods have limitations, even with technological evolution, including the most recent methods with the use of three-dimensional capture for the evaluation of muscular imbalances. Thus, there is an urgent need to improve the methods used to evaluate postural changes, correcting the limitations and improving existing techniques for identifying asymmetries, spinal deviations and alterations in peripheral joints. This study is a methodological research of development With the general aim of proposing a knowledge-based computer model for three-dimensional postural evaluation. And, specific objectives: to develop new algorithms or to perfect those that already exist for a postural analysis based on Cartesian coordinates in three dimensions; Propose a knowledge-based computer model that minimizes the limitations of existing methods; Test the implementation of the model through a pilot study. Finally, the study showed that, the proposed model intends to solve part of the limitations that the current computer tools for the biophotogrammetric evaluation bear.