Publication: Análisis de los parámetros característicos de la marcha normal y patológica
Loading...
Identifiers
Publication date
2019-06-17
Defense date
2019-07-03
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Impact
Export
Abstract
La memoria presente recoge un análisis realizado sobre los parámetros característicos que compone la marcha humana y la marcha humana patológica, por lo que se centrará en parámetros recogidos del tren inferior de los usuarios.
El objetivo principal de este trabajo es el análisis de los parámetros característicos de la marcha permitiéndonos diferenciarlo de la marcha patológica y facilitar de esta manera la detección de patologías, de manera más rápida y fácil, para el paciente y para el especialista.
Para ello se ha desarrollado una base de datos en la que almacenaremos todos los paseos de los usuarios (con patologías o sin ellas). La captura de paseos se realizará mediante unos sensores de captura de movimiento, y se tomarán dos tipos de muestras, la primera será un paseo normal y en la segunda se incluirá un dispositivo inmovilizador tipo alza en uno de los pies simulando el pie zambo o pie equino varo.
Por tanto, podemos definir como objetivos secundarios:
La parametrización de los paseos en los que se simula la patología del pie equino.
La parametrización de los paseos en los que los usuarios sufren otra patología distinta al pie equino.
Comprobar si los parámetros capturados durante la marcha normal y la marcha patológica son detectables
Clasificar los parámetros capturados mediante algoritmos de Machine Learning.
This report contains an analysis of the characteristic parameters of human and pathological gait, and will therefore focus on parameters collected from the undercarriage of users. The main objective of this work is the analysis of the characteristic parameters of gait allowing us to differentiate it from pathological gait and thus facilitate the detection of pathologies, in a faster and easier way, for the patient and for the specialist. To this end, a database has been developed in which we will store all user walks (with or without pathologies). The capture of walks will be carried out by means of movement capture sensors, and two types of samples will be taken, the first will be a normal walk and the second will include an immobilising device such as a lift in one of the feet simulating the clubfoot or clubfoot. Therefore, we can define as secondary objectives: The parameterization of the walks in which the pathology of the clubfoot is simulated. The parametrization of the walks in which the users suffer another pathology different from the equine foot. Check whether the parameters captured during normal gait and pathological gait are detectable. Classify the captured parameters using Machine Learning algorithms.
This report contains an analysis of the characteristic parameters of human and pathological gait, and will therefore focus on parameters collected from the undercarriage of users. The main objective of this work is the analysis of the characteristic parameters of gait allowing us to differentiate it from pathological gait and thus facilitate the detection of pathologies, in a faster and easier way, for the patient and for the specialist. To this end, a database has been developed in which we will store all user walks (with or without pathologies). The capture of walks will be carried out by means of movement capture sensors, and two types of samples will be taken, the first will be a normal walk and the second will include an immobilising device such as a lift in one of the feet simulating the clubfoot or clubfoot. Therefore, we can define as secondary objectives: The parameterization of the walks in which the pathology of the clubfoot is simulated. The parametrization of the walks in which the users suffer another pathology different from the equine foot. Check whether the parameters captured during normal gait and pathological gait are detectable. Classify the captured parameters using Machine Learning algorithms.
Description
Keywords
Marcha humana, Marcha humana patológica, Parametrización, Algoritmos, Aprendizaje máquina, Machine Learning