Por favor, use este identificador para citar o enlazar este ítem: http://dspace.udla.edu.ec/handle/33000/11554
Registro completo de metadatos
Campo DC Valor Lengua/Idioma
dc.contributor.advisorPozo Espín, David Fernando-
dc.creatorMantilla Brito, Juan Diego-
dc.date.accessioned2019-10-22T18:30:48Z-
dc.date.available2019-10-22T18:30:48Z-
dc.date.issued2019-
dc.identifier.citationMantilla Brito, J. D. (2019). Diseño de un sistema de control de una mano robótica mediante señales electromiográficas (Tesis de pregrado). Universidad de las Américas, Quito.es_ES
dc.identifier.otherUDLA-EC-TIERI-2019-20-
dc.identifier.urihttp://dspace.udla.edu.ec/handle/33000/11554-
dc.descriptionElectromyographic (EMG) signals are electrical pulses that are emitted by the muscles when we perform an action. Over the time they have been object of study in considerable areas of science, especially in medicine and robotics that have been able to create technological solutions to improve the lifestyle of the people. In this titling work, an integrated system is developed for the acquisition and processing of EMG signals that can be measured in the right forearm. The treatment of these signals allows the control of a robotic hand prototype to open or close it. This is possible through the use of the MYO Gesture Control Armband device, which has eight surface EMG sensors that capture and transmit the muscle signals via Bluetooth 4.0 to the control system composed mainly of an ATmega328P microcontroller and an STM32. Then, each signal is processed to extract its features (Absolute Mean Value, Variance, Standard Deviation and RMS) that are applied in the Naïve Bayes classifier algorithm previously trained by a group of seven users. Then the action is identified, and a control signal is sent to the robotic hand, to replicate the movement. Finally, with eleven people, system tests are performed configuring it to measure, encapsulate and process the EMG signals in packages of different sizes to evaluate the behavior of the system with the users that were part of the training and others outside it. The results are tabulated and by means of confusion matrices, we determine the system percentage of accuracy is between 74,67 percent and 89,31 percent with measurement times from 0,73 to 2,39 seconds and processing times of 0,03 to 0,05 seconds. Showing a total time range between 0,76 and 2,44 seconds, which allows us to conclude that the size of the EMG package configured to measure directly affects the response time and accuracy of the predictions.en
dc.description.abstractLas señales electromiográficas (EMG) son pulsos eléctricos que son emitidos por los músculos al realizar una acción...es_ES
dc.format.extent162 p.es_ES
dc.language.isospaes_ES
dc.publisherQuito: Universidad de las Américas, 2019es_ES
dc.rightsopenAccesses_ES
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 Ecuador*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/ec/*
dc.subjectROBÓTICAes_ES
dc.subjectSALUD HUMANAes_ES
dc.subjectINTELIGENCIA ARTIFICIALes_ES
dc.titleDiseño de un sistema de control de una mano robótica mediante señales electromiográficases_ES
dc.typebachelorThesises_ES
Aparece en las colecciones: Ingeniería en Electrónica y Redes de Información

Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
UDLA-EC-TIERI-2019-20.pdf4,09 MBAdobe PDFVisualizar/Abrir


Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons