Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales

Detalhes bibliográficos
Autor(a) principal: Muñoz Villalobos, Ignacio Andrés
Data de Publicação: 2022
Outros Autores: Bolt, Alfredo
Tipo de documento: Artigo
Idioma: spa
Título da fonte: AtoZ (Curitiba)
Texto Completo: https://revistas.ufpr.br/atoz/article/view/81419
Resumo: Introduction: Mobile apps, through artificial vision, are capable of recognizing vegetable species in real time. However, the existing species recognition apps do not take in consideration the wide variety of endemic and native (Chilean) species, which leads to wrong species predictions. This study introduces the development of a chilean species dataset and an optimized classification model implemented to a mobile app. Method: the data set was built by putting together pictures of several species captured on the field and by selecting some pictures available from other datasets available online. Convolutional neural networks were used in order to develop the images prediction models. The networks were trained by performing a sensitivity analysis, validating with k-fold cross validation and performing tests with different hyper-parameters, optimizers, convolutional layers, and learning rates in order to identify and choose the best models and then put them together in one classification model. Results: The final data set was compounded by 46 species, including native species, endemic and exotic from Chile, with 6120 training pictures and 655 testing pictures. The best models were implemented on a mobile app, obtaining a 95% correct prediction rate with respect to the set of tests. Conclusion: The app developed in this study is capable of classifying species with a high level of accuracy, depending on the state of the art of the artificial vision and it can also show relevant information related to the classified species.
id UFPR-6_55edbd6ca3a41ddfcaaff4d8293d5316
oai_identifier_str oai:revistas.ufpr.br:article/81419
network_acronym_str UFPR-6
network_name_str AtoZ (Curitiba)
repository_id_str
spelling Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionalesDesign and development of a mobile application for the classification of Chilean native flora using convolutional neural networksCiencias de la Computación: Inteligencia Artificial ; Aprendizaje ProfundoVisión artificial; Redes neuronales convolucionales; Flora Chilena; Aplicaciones móviles.Computer vision; Convolutional Neural Network; Chilean flora; Mobile apps.Introduction: Mobile apps, through artificial vision, are capable of recognizing vegetable species in real time. However, the existing species recognition apps do not take in consideration the wide variety of endemic and native (Chilean) species, which leads to wrong species predictions. This study introduces the development of a chilean species dataset and an optimized classification model implemented to a mobile app. Method: the data set was built by putting together pictures of several species captured on the field and by selecting some pictures available from other datasets available online. Convolutional neural networks were used in order to develop the images prediction models. The networks were trained by performing a sensitivity analysis, validating with k-fold cross validation and performing tests with different hyper-parameters, optimizers, convolutional layers, and learning rates in order to identify and choose the best models and then put them together in one classification model. Results: The final data set was compounded by 46 species, including native species, endemic and exotic from Chile, with 6120 training pictures and 655 testing pictures. The best models were implemented on a mobile app, obtaining a 95% correct prediction rate with respect to the set of tests. Conclusion: The app developed in this study is capable of classifying species with a high level of accuracy, depending on the state of the art of the artificial vision and it can also show relevant information related to the classified species.Introducción: Las aplicaciones móviles, a través de la visión artificial, son capaces de reconocer especies vegetales en tiempo real. Sin embargo, las actuales aplicaciones de reconocimiento de especies no consideran la gran variedad de especies endémicas y nativas de Chile, tendiendo a predecir erróneamente. Esta investigación presenta la construcción de un dataset de especies chilenas y el desarrollo de un modelo de clasificación optimizado e implementado en una aplicación móvil.  Método: La construcción del dataset se realizó a través de la captura de fotografías de especies en terreno y selección de imágenes de datasets en línea. Se utilizaron redes neuronales convolucionales para desarrollar los modelos de predicción de imágenes. Se realizó un análisis de sensibilidad al entrenar las redes, validando con k-fold cross validation y efectuando pruebas con distintos hiperparámetros, optimizadores, capas convolucionales y tasas de aprendizaje, para seleccionar los mejores modelos y luego ensamblarlos en un solo modelo de clasificación. Resultados: El dataset construido se conformó por 46 especies, incluyendo especies nativas, endémicas y exóticas de Chile, con 6120 imágenes de entrenamiento y 655 de prueba. Los mejores modelos se implementaron en una aplicación móvil, donde se obtuvo un porcentaje de acierto de aproximadamente 95% con respecto al conjunto de pruebas. Conclusiones: La aplicación desarrollada es capaz de clasificar especies correctamente con una probabilidad de acierto acorde con el estado del arte de la visión artificial y de mostrar información de la especie clasificada.Programa de Pós-graduação em Gestão da Informação - UFPRMuñoz Villalobos, Ignacio AndrésBolt, Alfredo2022-01-22info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArtículo evaluado por paresExperimental; prototipos; Investigación cuantitativaAvaliado pelos paresapplication/pdfhttps://revistas.ufpr.br/atoz/article/view/8141910.5380/atoz.v11i0.81419AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 13AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 13AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 132237-826X10.5380/atoz.v11i0reponame:AtoZ (Curitiba)instname:Universidade Federal do Paraná (UFPR)instacron:UFPRspahttps://revistas.ufpr.br/atoz/article/view/81419/45682https://revistas.ufpr.br/atoz/article/downloadSuppFile/81419/51456Zona central de ChileEl dataset está disponible públicamenteDireitos autorais 2022 AtoZ: novas práticas em informação e conhecimentohttp://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccess2023-05-29T22:23:13Zoai:revistas.ufpr.br:article/81419Revistahttp://revistas.ufpr.br/atozPUBhttp://ojs.c3sl.ufpr.br/ojs2/index.php/atoz/oai||revistaatoz@ufpr.br|| contatoatoz@gmail.com2237-826X2237-826Xopendoar:2023-05-29T22:23:13AtoZ (Curitiba) - Universidade Federal do Paraná (UFPR)false
dc.title.none.fl_str_mv Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
Design and development of a mobile application for the classification of Chilean native flora using convolutional neural networks
title Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
spellingShingle Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
Muñoz Villalobos, Ignacio Andrés
Ciencias de la Computación: Inteligencia Artificial ; Aprendizaje Profundo
Visión artificial; Redes neuronales convolucionales; Flora Chilena; Aplicaciones móviles.
Computer vision; Convolutional Neural Network; Chilean flora; Mobile apps.
title_short Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
title_full Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
title_fullStr Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
title_full_unstemmed Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
title_sort Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales
author Muñoz Villalobos, Ignacio Andrés
author_facet Muñoz Villalobos, Ignacio Andrés
Bolt, Alfredo
author_role author
author2 Bolt, Alfredo
author2_role author
dc.contributor.none.fl_str_mv

dc.contributor.author.fl_str_mv Muñoz Villalobos, Ignacio Andrés
Bolt, Alfredo
dc.subject.none.fl_str_mv
dc.subject.por.fl_str_mv Ciencias de la Computación: Inteligencia Artificial ; Aprendizaje Profundo
Visión artificial; Redes neuronales convolucionales; Flora Chilena; Aplicaciones móviles.
Computer vision; Convolutional Neural Network; Chilean flora; Mobile apps.
topic Ciencias de la Computación: Inteligencia Artificial ; Aprendizaje Profundo
Visión artificial; Redes neuronales convolucionales; Flora Chilena; Aplicaciones móviles.
Computer vision; Convolutional Neural Network; Chilean flora; Mobile apps.
description Introduction: Mobile apps, through artificial vision, are capable of recognizing vegetable species in real time. However, the existing species recognition apps do not take in consideration the wide variety of endemic and native (Chilean) species, which leads to wrong species predictions. This study introduces the development of a chilean species dataset and an optimized classification model implemented to a mobile app. Method: the data set was built by putting together pictures of several species captured on the field and by selecting some pictures available from other datasets available online. Convolutional neural networks were used in order to develop the images prediction models. The networks were trained by performing a sensitivity analysis, validating with k-fold cross validation and performing tests with different hyper-parameters, optimizers, convolutional layers, and learning rates in order to identify and choose the best models and then put them together in one classification model. Results: The final data set was compounded by 46 species, including native species, endemic and exotic from Chile, with 6120 training pictures and 655 testing pictures. The best models were implemented on a mobile app, obtaining a 95% correct prediction rate with respect to the set of tests. Conclusion: The app developed in this study is capable of classifying species with a high level of accuracy, depending on the state of the art of the artificial vision and it can also show relevant information related to the classified species.
publishDate 2022
dc.date.none.fl_str_mv 2022-01-22
dc.type.none.fl_str_mv

dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Artículo evaluado por pares
Experimental; prototipos; Investigación cuantitativa
Avaliado pelos pares
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://revistas.ufpr.br/atoz/article/view/81419
10.5380/atoz.v11i0.81419
url https://revistas.ufpr.br/atoz/article/view/81419
identifier_str_mv 10.5380/atoz.v11i0.81419
dc.language.iso.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv https://revistas.ufpr.br/atoz/article/view/81419/45682
https://revistas.ufpr.br/atoz/article/downloadSuppFile/81419/51456
dc.rights.driver.fl_str_mv Direitos autorais 2022 AtoZ: novas práticas em informação e conhecimento
http://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Direitos autorais 2022 AtoZ: novas práticas em informação e conhecimento
http://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv Zona central de Chile

El dataset está disponible públicamente



dc.publisher.none.fl_str_mv Programa de Pós-graduação em Gestão da Informação - UFPR
publisher.none.fl_str_mv Programa de Pós-graduação em Gestão da Informação - UFPR
dc.source.none.fl_str_mv AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 13
AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 13
AtoZ: novas práticas em informação e conhecimento; v. 11 (2022); 1 - 13
2237-826X
10.5380/atoz.v11i0
reponame:AtoZ (Curitiba)
instname:Universidade Federal do Paraná (UFPR)
instacron:UFPR
instname_str Universidade Federal do Paraná (UFPR)
instacron_str UFPR
institution UFPR
reponame_str AtoZ (Curitiba)
collection AtoZ (Curitiba)
repository.name.fl_str_mv AtoZ (Curitiba) - Universidade Federal do Paraná (UFPR)
repository.mail.fl_str_mv ||revistaatoz@ufpr.br|| contatoatoz@gmail.com
_version_ 1809276796261105664