Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning

Adolfo Jara-Gavilanes; Romel Ávila-Faicán; Vladimir Robles-Bykbaev; Luis Serpa-Andrade

doi:10.1007/978-3-031-33258-6_46

Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning

Adolfo Jara-Gavilanes
, Romel Ávila-Faicán
, Vladimir Robles-Bykbaev
, Luis Serpa-Andrade

Research Group on Artificial Intelligence and Assistive Technologies (GI-IATA)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Pre-writing skills are a set of skills that have a great impact on children’s self-esteem and academic achievement. This is a big problem in the development of children. Educators and therapists don’t have much time to detect children lacking these skills in an early stage. To deal with this problem, we present a system that helps evaluate drawings of geometric shapes (circle, triangle, and square) drawn by children. To reach this goal, the system is divided into 4 phases: first the images are divided into 2 categories. Second, the dataset is loaded and a data augmentation is applied. Third, the following Convolutional Neural Networks are applied: CNN with hyperparameter tuning, VGG16, ResNet50 and InceptionV3. To feed these models, we used the “UPSWriting-Skills” dataset. Fourth, results are shown and the best models are selected to present their final hyperparameters. Finally, this system could be the base for new experiments with other Convolutional Neural Networks and other techniques to improve the accuracy of the system.

Original language	English
Title of host publication	Information Technology and Systems - ICITS 2023
Editors	Álvaro Rocha, Carlos Ferrás, Waldo Ibarra
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	505-515
Number of pages	11
ISBN (Print)	9783031332579
DOIs	https://doi.org/10.1007/978-3-031-33258-6_46
State	Published - 2023
Event	International Conference on Information Technology and Systems, ICITS 2023 - Cusco, Peru Duration: 24 Apr 2023 → 26 Apr 2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	691 LNNS

Conference

Conference	International Conference on Information Technology and Systems, ICITS 2023
Country/Territory	Peru
City	Cusco
Period	24/04/23 → 26/04/23

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

CNN
Education
InceptionV3
Pre-writing skills
ResNet50
VGG16

CACES Knowledge Areas

316A Software and Applications Development and Analysis
8116A Information Systems

Access to Document

10.1007/978-3-031-33258-6_46

Cite this

Jara-Gavilanes, A., Ávila-Faicán, R., Robles-Bykbaev, V., & Serpa-Andrade, L. (2023). Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning. In Á. Rocha, C. Ferrás, & W. Ibarra (Eds.), Information Technology and Systems - ICITS 2023 (pp. 505-515). (Lecture Notes in Networks and Systems; Vol. 691 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-33258-6_46

Jara-Gavilanes, Adolfo ; Ávila-Faicán, Romel ; Robles-Bykbaev, Vladimir et al. / Rating Pre-writing Skills in Ecuadorian Children : A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning. Information Technology and Systems - ICITS 2023. editor / Álvaro Rocha ; Carlos Ferrás ; Waldo Ibarra. Springer Science and Business Media Deutschland GmbH, 2023. pp. 505-515 (Lecture Notes in Networks and Systems).

@inproceedings{57d591316dc241dcba026680d77bbea7,

title = "Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning",

abstract = "Pre-writing skills are a set of skills that have a great impact on children{\textquoteright}s self-esteem and academic achievement. This is a big problem in the development of children. Educators and therapists don{\textquoteright}t have much time to detect children lacking these skills in an early stage. To deal with this problem, we present a system that helps evaluate drawings of geometric shapes (circle, triangle, and square) drawn by children. To reach this goal, the system is divided into 4 phases: first the images are divided into 2 categories. Second, the dataset is loaded and a data augmentation is applied. Third, the following Convolutional Neural Networks are applied: CNN with hyperparameter tuning, VGG16, ResNet50 and InceptionV3. To feed these models, we used the “UPSWriting-Skills” dataset. Fourth, results are shown and the best models are selected to present their final hyperparameters. Finally, this system could be the base for new experiments with other Convolutional Neural Networks and other techniques to improve the accuracy of the system.",

keywords = "CNN, Education, InceptionV3, Pre-writing skills, ResNet50, VGG16",

author = "Adolfo Jara-Gavilanes and Romel {\'A}vila-Faic{\'a}n and Vladimir Robles-Bykbaev and Luis Serpa-Andrade",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; International Conference on Information Technology and Systems, ICITS 2023 ; Conference date: 24-04-2023 Through 26-04-2023",

year = "2023",

doi = "10.1007/978-3-031-33258-6\_46",

language = "English",

isbn = "9783031332579",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "505--515",

editor = "{\'A}lvaro Rocha and Carlos Ferr{\'a}s and Waldo Ibarra",

booktitle = "Information Technology and Systems - ICITS 2023",

address = "Germany",

}

Jara-Gavilanes, A, Ávila-Faicán, R, Robles-Bykbaev, V & Serpa-Andrade, L 2023, Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning. in Á Rocha, C Ferrás & W Ibarra (eds), Information Technology and Systems - ICITS 2023. Lecture Notes in Networks and Systems, vol. 691 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 505-515, International Conference on Information Technology and Systems, ICITS 2023, Cusco, Peru, 24/04/23. https://doi.org/10.1007/978-3-031-33258-6_46

Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning. / Jara-Gavilanes, Adolfo; Ávila-Faicán, Romel; Robles-Bykbaev, Vladimir et al.
Information Technology and Systems - ICITS 2023. ed. / Álvaro Rocha; Carlos Ferrás; Waldo Ibarra. Springer Science and Business Media Deutschland GmbH, 2023. p. 505-515 (Lecture Notes in Networks and Systems; Vol. 691 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Rating Pre-writing Skills in Ecuadorian Children

T2 - International Conference on Information Technology and Systems, ICITS 2023

AU - Jara-Gavilanes, Adolfo

AU - Ávila-Faicán, Romel

AU - Robles-Bykbaev, Vladimir

AU - Serpa-Andrade, Luis

PY - 2023

Y1 - 2023

N2 - Pre-writing skills are a set of skills that have a great impact on children’s self-esteem and academic achievement. This is a big problem in the development of children. Educators and therapists don’t have much time to detect children lacking these skills in an early stage. To deal with this problem, we present a system that helps evaluate drawings of geometric shapes (circle, triangle, and square) drawn by children. To reach this goal, the system is divided into 4 phases: first the images are divided into 2 categories. Second, the dataset is loaded and a data augmentation is applied. Third, the following Convolutional Neural Networks are applied: CNN with hyperparameter tuning, VGG16, ResNet50 and InceptionV3. To feed these models, we used the “UPSWriting-Skills” dataset. Fourth, results are shown and the best models are selected to present their final hyperparameters. Finally, this system could be the base for new experiments with other Convolutional Neural Networks and other techniques to improve the accuracy of the system.

AB - Pre-writing skills are a set of skills that have a great impact on children’s self-esteem and academic achievement. This is a big problem in the development of children. Educators and therapists don’t have much time to detect children lacking these skills in an early stage. To deal with this problem, we present a system that helps evaluate drawings of geometric shapes (circle, triangle, and square) drawn by children. To reach this goal, the system is divided into 4 phases: first the images are divided into 2 categories. Second, the dataset is loaded and a data augmentation is applied. Third, the following Convolutional Neural Networks are applied: CNN with hyperparameter tuning, VGG16, ResNet50 and InceptionV3. To feed these models, we used the “UPSWriting-Skills” dataset. Fourth, results are shown and the best models are selected to present their final hyperparameters. Finally, this system could be the base for new experiments with other Convolutional Neural Networks and other techniques to improve the accuracy of the system.

KW - CNN

KW - Education

KW - InceptionV3

KW - Pre-writing skills

KW - ResNet50

KW - VGG16

UR - https://www.scopus.com/pages/publications/85169029375

U2 - 10.1007/978-3-031-33258-6_46

DO - 10.1007/978-3-031-33258-6_46

M3 - Conference contribution

AN - SCOPUS:85169029375

SN - 9783031332579

T3 - Lecture Notes in Networks and Systems

SP - 505

EP - 515

BT - Information Technology and Systems - ICITS 2023

A2 - Rocha, Álvaro

A2 - Ferrás, Carlos

A2 - Ibarra, Waldo

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 24 April 2023 through 26 April 2023

ER -

Jara-Gavilanes A, Ávila-Faicán R, Robles-Bykbaev V , Serpa-Andrade L. Rating Pre-writing Skills in Ecuadorian Children: A Preliminary Study Based on Transfer Learning, Hyperparameter Tuning, and Deep Learning. In Rocha Á, Ferrás C, Ibarra W, editors, Information Technology and Systems - ICITS 2023. Springer Science and Business Media Deutschland GmbH. 2023. p. 505-515. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-33258-6_46