Colombian Sign Language Interpretation Model using Artificial Intelligence

In this work, two interpretation models of Colombian Sign Language (CSL) are presented, using static and dynamic methods that employ artificial intelligence. The CRISP-DM methodology was used as a reference, creating a database with videos from seventy non-expert participants, being preprocessed and...

Full description

Autores:
Tipo de recurso:
http://purl.org/coar/resource_type/c_6739
Fecha de publicación:
2023
Institución:
Universidad Pedagógica y Tecnológica de Colombia
Repositorio:
RiUPTC: Repositorio Institucional UPTC
Idioma:
spa
OAI Identifier:
oai:repositorio.uptc.edu.co:001/10432
Acceso en línea:
https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840
https://repositorio.uptc.edu.co/handle/001/10432
Palabra clave:
colombian sign language;
CNN;
LSTM;
CRISP-DM
lengua de señas colombiano;
CNN;
LSTM;
CRISP-DM
Rights
License
Derechos de autor 2023 Revista de Investigación, Desarrollo e Innovación
id REPOUPTC2_caaac2383614c07518749d40a4eb3233
oai_identifier_str oai:repositorio.uptc.edu.co:001/10432
network_acronym_str REPOUPTC2
network_name_str RiUPTC: Repositorio Institucional UPTC
repository_id_str
spelling 2023-08-152024-07-05T18:04:17Z2024-07-05T18:04:17Zhttps://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/1684010.19053/20278306.v13.n2.2023.16840https://repositorio.uptc.edu.co/handle/001/10432In this work, two interpretation models of Colombian Sign Language (CSL) are presented, using static and dynamic methods that employ artificial intelligence. The CRISP-DM methodology was used as a reference, creating a database with videos from seventy non-expert participants, being preprocessed and subsequently divided into proportions of 70% - 30% for training and testing, respectively. The repository was named LSC-W70 and was used on a pre-trained model of convolutional neural networks and another in combination with LSTM networks. The results reached 67% and 76% accuracy for the static and dynamic models, respectively, where the dynamic model presents improvements in similar signs by identifying the direction of movement to define the type of sign. In this sense, a dynamic Colombian sign language interpretation tool was developed that helps close communication gaps, generating equality between people.En este trabajo se presentan dos modelos de interpretación de Lengua de Señas Colombiana (LSC), usando métodos estáticos y dinámicos que emplean inteligencia artificial. Se utilizó como referente la metodología CRISP-DM, creando una base de datos con videos de setenta participantes no expertos, siendo preprocesados y posteriormente divididos en proporciones de 70% - 30% para entrenamiento y prueba, respectivamente. El repositorio se nombró como LSC-W70 y se empleó sobre un modelo preentrenado de redes neuronales convolucionales y otro en combinación con redes LSTM. Los resultados alcanzaron un 67% y 76% accuracy para los modelos estático y dinámico, respectivamente, donde el modelo dinámico presenta mejoras en señas similares identificando la dirección del movimiento para definir el tipo de seña. En este sentido, se desarrolló una herramienta de interpretación dinámica de lengua de señas colombiano que ayuda a cerrar brechas de comunicación generando igualdad entre las personas.application/pdftext/xmlspaspaUniversidad Pedagógica y Tecnológica de Colombiahttps://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840/13652https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840/13935Derechos de autor 2023 Revista de Investigación, Desarrollo e Innovaciónhttp://purl.org/coar/access_right/c_abf240http://purl.org/coar/access_right/c_abf2Revista de Investigación, Desarrollo e Innovación; Vol. 13 No. 2 (2023): Julio-Diciembre; 357-366Revista de Investigación, Desarrollo e Innovación; Vol. 13 Núm. 2 (2023): Julio-Diciembre; 357-3662389-94172027-8306colombian sign language;CNN;LSTM;CRISP-DMlengua de señas colombiano;CNN;LSTM;CRISP-DMColombian Sign Language Interpretation Model using Artificial IntelligenceModelo de interpretación de lengua de señas colombiano usando inteligencia artificialinfo:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6739http://purl.org/coar/resource_type/c_2df8fbb1info:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a323http://purl.org/coar/version/c_970fb48d4fbd8a85Muñoz-Galindez, Jader AlejandroVargas-Cañas, Rubiel001/10432oai:repositorio.uptc.edu.co:001/104322025-07-18 11:51:36.615metadata.onlyhttps://repositorio.uptc.edu.coRepositorio Institucional UPTCrepositorio.uptc@uptc.edu.co
dc.title.en-US.fl_str_mv Colombian Sign Language Interpretation Model using Artificial Intelligence
dc.title.es-ES.fl_str_mv Modelo de interpretación de lengua de señas colombiano usando inteligencia artificial
title Colombian Sign Language Interpretation Model using Artificial Intelligence
spellingShingle Colombian Sign Language Interpretation Model using Artificial Intelligence
colombian sign language;
CNN;
LSTM;
CRISP-DM
lengua de señas colombiano;
CNN;
LSTM;
CRISP-DM
title_short Colombian Sign Language Interpretation Model using Artificial Intelligence
title_full Colombian Sign Language Interpretation Model using Artificial Intelligence
title_fullStr Colombian Sign Language Interpretation Model using Artificial Intelligence
title_full_unstemmed Colombian Sign Language Interpretation Model using Artificial Intelligence
title_sort Colombian Sign Language Interpretation Model using Artificial Intelligence
dc.subject.en-US.fl_str_mv colombian sign language;
CNN;
LSTM;
CRISP-DM
topic colombian sign language;
CNN;
LSTM;
CRISP-DM
lengua de señas colombiano;
CNN;
LSTM;
CRISP-DM
dc.subject.es-ES.fl_str_mv lengua de señas colombiano;
CNN;
LSTM;
CRISP-DM
description In this work, two interpretation models of Colombian Sign Language (CSL) are presented, using static and dynamic methods that employ artificial intelligence. The CRISP-DM methodology was used as a reference, creating a database with videos from seventy non-expert participants, being preprocessed and subsequently divided into proportions of 70% - 30% for training and testing, respectively. The repository was named LSC-W70 and was used on a pre-trained model of convolutional neural networks and another in combination with LSTM networks. The results reached 67% and 76% accuracy for the static and dynamic models, respectively, where the dynamic model presents improvements in similar signs by identifying the direction of movement to define the type of sign. In this sense, a dynamic Colombian sign language interpretation tool was developed that helps close communication gaps, generating equality between people.
publishDate 2023
dc.date.accessioned.none.fl_str_mv 2024-07-05T18:04:17Z
dc.date.available.none.fl_str_mv 2024-07-05T18:04:17Z
dc.date.none.fl_str_mv 2023-08-15
dc.type.none.fl_str_mv info:eu-repo/semantics/article
dc.type.coar.fl_str_mv http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_6739
dc.type.version.spa.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.coarversion.spa.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a323
format http://purl.org/coar/resource_type/c_6739
status_str publishedVersion
dc.identifier.none.fl_str_mv https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840
10.19053/20278306.v13.n2.2023.16840
dc.identifier.uri.none.fl_str_mv https://repositorio.uptc.edu.co/handle/001/10432
url https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840
https://repositorio.uptc.edu.co/handle/001/10432
identifier_str_mv 10.19053/20278306.v13.n2.2023.16840
dc.language.none.fl_str_mv spa
dc.language.iso.spa.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840/13652
https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/16840/13935
dc.rights.es-ES.fl_str_mv Derechos de autor 2023 Revista de Investigación, Desarrollo e Innovación
dc.rights.coar.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf240
rights_invalid_str_mv Derechos de autor 2023 Revista de Investigación, Desarrollo e Innovación
http://purl.org/coar/access_right/c_abf240
http://purl.org/coar/access_right/c_abf2
dc.format.none.fl_str_mv application/pdf
text/xml
dc.publisher.es-ES.fl_str_mv Universidad Pedagógica y Tecnológica de Colombia
dc.source.en-US.fl_str_mv Revista de Investigación, Desarrollo e Innovación; Vol. 13 No. 2 (2023): Julio-Diciembre; 357-366
dc.source.es-ES.fl_str_mv Revista de Investigación, Desarrollo e Innovación; Vol. 13 Núm. 2 (2023): Julio-Diciembre; 357-366
dc.source.none.fl_str_mv 2389-9417
2027-8306
institution Universidad Pedagógica y Tecnológica de Colombia
repository.name.fl_str_mv Repositorio Institucional UPTC
repository.mail.fl_str_mv repositorio.uptc@uptc.edu.co
_version_ 1839633870503280640