Diferencias entre la imaginación y ejecución motora durante los movimientos ponerse de pie y sentarse a través de modelos autorregresivos

The analysis of motor imagination and execution (MI-ME) is one of the main research challenges in the field of brain-computer interfaces (BCI) based on electroencephalography (EEG). EEG signals play an important role in the learning, rehabilitation, and assistance of complex motor skills. However, t...

Full description

Autores:
Moreno Arévalo, Brayan Sneider
Tipo de recurso:
Trabajo de grado de pregrado
Fecha de publicación:
2021
Institución:
Universidad Antonio Nariño
Repositorio:
Repositorio UAN
Idioma:
spa
OAI Identifier:
oai:repositorio.uan.edu.co:123456789/6579
Acceso en línea:
http://repositorio.uan.edu.co/handle/123456789/6579
Palabra clave:
Imaginación motora
Ejecución motora
Interfaces cerebro-computadora
Electroencefalografía
Rehabilitación
Habilidades motoras-complejas
Ponerse de pie y sentarse
620
Motor Imagination
Motor Execution
Brain-Computer Interfaces
Electroencephalography
Rehabilitation
Complex Motor Skills
Sit to Stand
Rights
openAccess
License
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Description
Summary:The analysis of motor imagination and execution (MI-ME) is one of the main research challenges in the field of brain-computer interfaces (BCI) based on electroencephalography (EEG). EEG signals play an important role in the learning, rehabilitation, and assistance of complex motor skills. However, this type of signal presents a highly non-stationary nature and noise. Electroencephalography signals proper of sensory-motor activity, corresponding to execution defects and motor imagination, were analyzed. The present research aims to determine the differences that exist between motor imagination and motor execution from a proof of concept, in the movements of sitting and standing. A comparative study was carried out between a method based on desynchronization / synchronization (ERDs) and a new method based on autoregressive moving average models with exogenous input (ARMAX). In this research, the normalized root mean square error (NRMSE), the mean square error (RMSE) and the mean absolute error (MAE) are used as evaluation metrics, in addition to the classification percentages. The results found show that it is possible to estimate and classify the movements of standing and sitting for the tasks of execution and motor imagination from channels C3, Cz and C4 with a high % of precision. It is expected, in the long term, to contribute to improve the quality of life of people with motor functional diversity.