Publicación: EVIN, una aplicación adaptativa integral para el entrenamiento visual online de niños con baja visión
Cargando...
Fecha
2021
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
International Journal of Developmental and Educational Psychology
Resumen
La baja visión es una deficiencia visual que no puede ser mejorada con ayudas ópticas convencionales. No obstante, para incrementar sus habilidades estas personas pueden seguir un programa de entrenamiento visual planificado y supervisado por un experto en este campo. Este entrenamiento es especialmente efectivo en niños, debido a su plasticidad para aprender. Pero, debido a la falta de expertos especializados, las sesiones de entrenamiento son generalmente menos frecuentes de lo que sería conveniente. Los programas de entrenamiento visual online son una solución para mitigar este problema, porque pueden ser llevado a efecto por expertos y familias de forma conjunta. De este modo, desarrollamos la aplicación Estimulación Visual en Internet (EVIN), que proporciona un programa de entrenamiento visual en diferentes tareas a través de juegos. Además, presenta informes de los resultados de los niños durante el entrenamiento. Aunque en trabajos anteriores ya se ha probado la utilidad de EVIN, se ha visto necesaria abordar dos nuevas metas: (i) proporcionar algún tipo de soporte en EVIN que ayude a expertos y familias a trabajar juntos debido, entre otras causas, a la gran variedad de ejercicios y configuraciones que pueden ser prescritas a los niños y, (ii) diseñar un riguroso experimento para comparar el entrenamiento visual en niños con EVIN con el entrenamiento con métodos tradicionales. Para afrontar estos objetivos, presentamos una versión adaptativa de EVIN que proporciona una nueva herramienta que permite al experto planificar el entrenamiento visual usando plantillas de ejercicios prediseñadas. Además, hemos desarrollado nuevas métricas e informes que permiten valorar con mayor precisión los resultados de los niños. Todo ello nos ha permitido desarrollar un experimento para evaluar si se produce mejora significativa en los niños entrenados con EVIN.
Low vision is a visual impairment that cannot be improved by standard vision aids such as glasses. Therefore, to improve their visual skills, people affected by low vision usually follow a visual training program planned and supervised by an expert in this field. Visual training is especially suitable for children because of their plasticity for learning. However, due to a lack of experts specializing in this field, training sessions are usually less frequent than optimal. As a result, home-based visual training has emerged as a solution to mitigate this problem because it can be undertaken by experts and families together. Therefore, we implemented the Visual Stimulation on the Internet (EVIN) application, which provides comprehensive visual training tasks through games. In addition, it provides reports on children’s performance in these visual training tasks. However, although EVIN has already proven its usefulness in previous works, two main solutions are needed: (i) some kind of support setup in EVIN to help experts and families work together because, among other things, of the large variety of exercises and different configurations that can be prescribed to the child and (ii) a rigorous experimental design to compare children trained with EVIN with children trained with traditional materials. To face these challenges, we present an adaptive version of EVIN that provides a new design tool that allows expert to plan visual training tasks through templates in advance. In addition, we developed new metrics and reports to achieve a more accurate assessment of children’s improvement. Among other results, it allowed us to develop an authoritative experiment to evaluate significant improvements in those children trained with EVIN.
Low vision is a visual impairment that cannot be improved by standard vision aids such as glasses. Therefore, to improve their visual skills, people affected by low vision usually follow a visual training program planned and supervised by an expert in this field. Visual training is especially suitable for children because of their plasticity for learning. However, due to a lack of experts specializing in this field, training sessions are usually less frequent than optimal. As a result, home-based visual training has emerged as a solution to mitigate this problem because it can be undertaken by experts and families together. Therefore, we implemented the Visual Stimulation on the Internet (EVIN) application, which provides comprehensive visual training tasks through games. In addition, it provides reports on children’s performance in these visual training tasks. However, although EVIN has already proven its usefulness in previous works, two main solutions are needed: (i) some kind of support setup in EVIN to help experts and families work together because, among other things, of the large variety of exercises and different configurations that can be prescribed to the child and (ii) a rigorous experimental design to compare children trained with EVIN with children trained with traditional materials. To face these challenges, we present an adaptive version of EVIN that provides a new design tool that allows expert to plan visual training tasks through templates in advance. In addition, we developed new metrics and reports to achieve a more accurate assessment of children’s improvement. Among other results, it allowed us to develop an authoritative experiment to evaluate significant improvements in those children trained with EVIN.
Descripción
Categorías UNESCO
Palabras clave
baja visión, entrenamiento visual, plataformas online, sistemas adaptativos, low vision, visual training, on-line platforms, adaptive systems
Citación
Centro
E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial