Hyperparameter Optimization for Image Recognition over an AR-Sandbox Based on Convolutional Neural Networks Applying a Previous Phase of Segmentation by Color-Space
Autor:
Restrepo Rodríguez, Andrés Ovidio
; Casas Mateus, Daniel Esteban
; Gaona-García, Paulo Alonso
; Montenegro-Marín, Carlos
; González-Crespo, Rubén
Fecha:
12/2018Palabra clave:
Revista / editorial:
Sysmmetry. BaselTipo de Ítem:
Articulo Revista IndexadaDirección web:
https://www.mdpi.com/2073-8994/10/12/743Resumen:
Immersive techniques such as augmented reality through devices such as the AR-Sandbox and deep learning through convolutional neural networks (CNN) provide an environment that is potentially applicable for motor rehabilitation and early education. However, given the orientation towards the creation of topographic models and the form of representation of the AR-Sandbox, the classification of images is complicated by the amount of noise that is generated in each capture. For this reason, this research has the purpose of establishing a model of a CNN for the classification of geometric figures by optimizing hyperparameters using Random Search, evaluating the impact of the implementation of a previous phase of color-space segmentation to a set of tests captured from the AR-Sandbox, and evaluating this type of segmentation using similarity indexes such as Jaccard and Sorensen-Dice. The aim of the proposed scheme is to improve the identification and extraction of characteristics of the geometric figures. Using the proposed method, an average decrease of 39.45% to a function of loss and an increase of 14.83% on average in the percentage of correct answers is presented, concluding that the selected CNN model increased its performance by applying color-space segmentation in a phase that was prior to the prediction, given the nature of multiple pigmentation of the AR-Sandbox.
Este ítem aparece en la(s) siguiente(s) colección(es)
Estadísticas de uso
Año |
2012 |
2013 |
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
2022 |
2023 |
2024 |
Vistas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
160 |
83 |
39 |
63 |
51 |
74 |
Descargas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Emotional characterization of children through a learning environment using learning analytics and AR-Sandbox
Restrepo Rodríguez, Andrés Ovidio; Ariza Riaño, Maddyzeth; Gaona-García, Paulo Alonso; Montenegro-Marin, Carlos Enrique; González-Crespo, Rubén; Wu, Xing (Journal of Ambient Intelligence and Humanized Computing, 03/2020)Identifying emotions experienced by students in a learning environment contributes to measuring the impact when technologies such as augmented reality (AR) are implemented in the educational field. The most frequent methods ... -
Initial Approach for Construction of a Public Dataset for Emotional Analysis Through Brain-Computer Interfaces and Second Language Platforms
Restrepo Rodríguez, Andrés Ovidio; Ariza Riaño, Maddyzeth; Gaona-García, Paulo Alonso; Montenegro Marin, Carlos Enrique; González-Crespo, Rubén (IEEE Global Engineering Education Conference, EDUCON, 2023)In recent years, the deepening of the role of emotions in education has increased, since it has been shown that emotions influence what we learn and retain, in different areas such as learning a second language. Likewise, ... -
Time Series for Evaluation of Performance Metrics as of Interaction with an AR-Sandbox Using Brain Computer Interfaces
Restrepo Rodríguez, Andrés Ovidio ; Ariza Riaño, Maddyzeth; Gaona-García, Paulo Alonso; Montenegro-Marín, Carlos (Lecture Notes in Networks and Systems, 2022)Technologies such as Augmented Reality (AR) can generate an impact within the educational process of students, which can be measured from the perspective of users. Generally, this perspective is evaluated from questionnaires ...