Sign Language Recognition System Using Myo Armband and Neural Network

Santiago Felipe Luna Romero; Luis Javier Serpa Andrade

Sign Language Recognition System Using Myo Armband and Neural Network

Título traducido de la contribución: Sistema de reconocimiento de lenguaje de señas usando Myo Armband y Neural Network

Santiago Felipe Luna Romero, Luis Javier Serpa Andrade

Grupo de Investigación de Inteligencia Artificial y Tecnologías de Asistencia (GI-IATa)

Producción científica: Contribución a una conferencia › Documento

Resumen

la interacción entre una persona sorda y una persona natural se ha convertido en un temamuy recurrente en la actualidad debido a la necesidad de lograr que estos dos grupos de personas puedan establecer una comunicación. Este artículo propone un sistema inteligente que permite interpretar los signos de la lengua sorda y convertirlos en lenguaje de escritura para que una persona natural pueda entender lo que una persona sorda quiere expresar. Este trabajo hace una revisión de la literatura en la que expresa las diferentes metodologías ytécnicas que se han desarrollado a lo largo del tiempo para la clasificación de los signos del lenguaje sordo, también propone un método que funciona en tiempo real utilizando la electromiografía del brazalete llamado “Brazalete MYO” que reconoce 10 Signos del lenguaje sordo a través de un algoritmo de recolección, procesamiento y clasificación designos. Las características obtenidas del MYO son estadísticas de tiempo y frecuencia. Para la etapa de clasificación de palabras y frases, este trabajo propone utilizar una red neuronal artificial de perceptron multicapa. Para verificar la eficacia de este trabajo, se propuso un experimento con un grupo de 25 personas para entrenamiento y otras 25 personaspara evaluación. La eficiencia del sistema se midió por la cantidad de éxitos del total de personas en la evaluación, obteniendo una eficiencia del 77% en la clasificación de signos.

Título traducido de la contribución	Sistema de reconocimiento de lenguaje de señas usando Myo Armband y Neural Network
Idioma original	Inglés estadounidense
Estado	Publicada - 30 ago. 2019
Evento	V Congreso Internacional de Ciencia, Tecnología e Innovación para la Sociedad (CITIS 2018-2019) - EC Duración: 6 feb. 2019 → 8 feb. 2019 https://citis.blog.ups.edu.ec/8000-2

Conferencia

Conferencia	V Congreso Internacional de Ciencia, Tecnología e Innovación para la Sociedad (CITIS 2018-2019)
Período	6/02/19 → 8/02/19
Dirección de internet	https://citis.blog.ups.edu.ec/8000-2

Palabras clave

Electromiografía (emg)
Neuronales.
Redes
Señales bioeléctricas producidas fisiológicamente

Areas de Conocimiento del CACES

417A Electrónica, automatización y sonido

Otros archivos y enlaces

Other Link

Citar esto

@conference{1a46aa9a04624f89be7e979a751ceab2,

title = "Sign Language Recognition System Using Myo Armband and Neural Network",

abstract = "The interaction between a deaf person and a natural person has become a very recurring topic nowadays due to the need to ensure that these two groups of people can establish communication. This article proposes an intelligent system that allows interpreting the signs of the deaf language and converting them into written language so that a natural person can understand what a deaf person wants to express. This work makes a review of the literature in which it expresses the different methodologies and techniques that have been developed over time for the classification of deaf language signs, it also proposes a method that works in real time using the electromyography of the bracelet called {"}MYO bracelet{"} that recognizes 10 signs of deaf language through a sign collection, processing and classification algorithm. The characteristics obtained from the MYO are time and frequency statistics. For the word and phrase classification stage, this work proposes to use a multilayer perceptron artificial neural network. To verify the effectiveness of this work, an experiment was proposed with a group of 25 people for training and another 25 people for evaluation. The efficiency of the system was measured by the number of successes of the total number of people in the evaluation, obtaining an efficiency of 77% in the classification of signs.",

keywords = "Electromiograf{\'i}a (emg), Neuronales., Redes, Se{\~n}ales bioel{\'e}ctricas producidas fisiol{\'o}gicamente, Electromiograf{\'i}a (emg), Neuronales., Redes, Se{\~n}ales bioel{\'e}ctricas producidas fisiol{\'o}gicamente",

author = "{Luna Romero}, {Santiago Felipe} and {Serpa Andrade}, {Luis Javier}",

year = "2019",

month = aug,

day = "30",

language = "English (US)",

note = "V Congreso Internacional de Ciencia, Tecnolog{\'i}a e Innovaci{\'o}n para la Sociedad (CITIS 2018-2019) ; Conference date: 06-02-2019 Through 08-02-2019",

url = "https://citis.blog.ups.edu.ec/8000-2",

}

TY - CONF

T1 - Sign Language Recognition System Using Myo Armband and Neural Network

AU - Luna Romero, Santiago Felipe

AU - Serpa Andrade, Luis Javier

PY - 2019/8/30

Y1 - 2019/8/30

N2 - The interaction between a deaf person and a natural person has become a very recurring topic nowadays due to the need to ensure that these two groups of people can establish communication. This article proposes an intelligent system that allows interpreting the signs of the deaf language and converting them into written language so that a natural person can understand what a deaf person wants to express. This work makes a review of the literature in which it expresses the different methodologies and techniques that have been developed over time for the classification of deaf language signs, it also proposes a method that works in real time using the electromyography of the bracelet called "MYO bracelet" that recognizes 10 signs of deaf language through a sign collection, processing and classification algorithm. The characteristics obtained from the MYO are time and frequency statistics. For the word and phrase classification stage, this work proposes to use a multilayer perceptron artificial neural network. To verify the effectiveness of this work, an experiment was proposed with a group of 25 people for training and another 25 people for evaluation. The efficiency of the system was measured by the number of successes of the total number of people in the evaluation, obtaining an efficiency of 77% in the classification of signs.

AB - The interaction between a deaf person and a natural person has become a very recurring topic nowadays due to the need to ensure that these two groups of people can establish communication. This article proposes an intelligent system that allows interpreting the signs of the deaf language and converting them into written language so that a natural person can understand what a deaf person wants to express. This work makes a review of the literature in which it expresses the different methodologies and techniques that have been developed over time for the classification of deaf language signs, it also proposes a method that works in real time using the electromyography of the bracelet called "MYO bracelet" that recognizes 10 signs of deaf language through a sign collection, processing and classification algorithm. The characteristics obtained from the MYO are time and frequency statistics. For the word and phrase classification stage, this work proposes to use a multilayer perceptron artificial neural network. To verify the effectiveness of this work, an experiment was proposed with a group of 25 people for training and another 25 people for evaluation. The efficiency of the system was measured by the number of successes of the total number of people in the evaluation, obtaining an efficiency of 77% in the classification of signs.

KW - Electromiografía (emg)

KW - Neuronales.

KW - Redes

KW - Señales bioeléctricas producidas fisiológicamente

KW - Electromiografía (emg)

KW - Neuronales.

KW - Redes

KW - Señales bioeléctricas producidas fisiológicamente

UR - https://dspace.ups.edu.ec/handle/123456789/17843

M3 - Paper

T2 - V Congreso Internacional de Ciencia, Tecnología e Innovación para la Sociedad (CITIS 2018-2019)

Y2 - 6 February 2019 through 8 February 2019

ER -

Sign Language Recognition System Using Myo Armband and Neural Network

Resumen

Conferencia

Palabras clave

Areas de Conocimiento del CACES

Otros archivos y enlaces

Huella

Citar esto