A scalable offline AI-based solution to assist the diseases and plague detection in agriculture

Early detection of diseases and pests is a key factor in eradicating or minimising the damage that these may cause. In this work, a comprehensive solution is presented that is based on the composition of existing cloud solutions and mobile tools to detect in-situ issues. The platform presented was u...

Descripción completa

Detalles Bibliográficos
Autores principales: Urbieta, Mario Matías, Urbieta, Martín, Pereyra, Mauro Ezequiel, Laborde, Tomás, Villarreal, Guillermo, Pino, Mariana del
Formato: Articulo
Lenguaje:Inglés
Publicado: 2023
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/160240
Aporte de:
id I19-R120-10915-160240
record_format dspace
spelling I19-R120-10915-1602402023-11-16T20:08:05Z http://sedici.unlp.edu.ar/handle/10915/160240 A scalable offline AI-based solution to assist the diseases and plague detection in agriculture Urbieta, Mario Matías Urbieta, Martín Pereyra, Mauro Ezequiel Laborde, Tomás Villarreal, Guillermo Pino, Mariana del 2023-06-22 2023-11-16T12:33:22Z en Informática Agriculture Cloud Machine-learning Mobile tomato powder mould cladosporium Early detection of diseases and pests is a key factor in eradicating or minimising the damage that these may cause. In this work, a comprehensive solution is presented that is based on the composition of existing cloud solutions and mobile tools to detect in-situ issues. The platform presented was used for the detection of powdery mildew and Cladosporium diseases in tomatoes. The results of using the approach to carry out this task were more than satisfactory since it managed to correctly detect the symptoms, having mAP of 0.41 in at least some of these symptoms. We analysed the performance of our dataset, on the one hand, and the combination of PlantDoc dataset, on the other hand. This shows that the platform can be used in the agriculture sector, as an additional tool for detecting diseases and pests in order to combat the problem and reduce its consequences. Laboratorio de Investigación y Formación en Informática Avanzada Articulo Articulo http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Informática
Agriculture
Cloud
Machine-learning
Mobile
tomato
powder mould
cladosporium
spellingShingle Informática
Agriculture
Cloud
Machine-learning
Mobile
tomato
powder mould
cladosporium
Urbieta, Mario Matías
Urbieta, Martín
Pereyra, Mauro Ezequiel
Laborde, Tomás
Villarreal, Guillermo
Pino, Mariana del
A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
topic_facet Informática
Agriculture
Cloud
Machine-learning
Mobile
tomato
powder mould
cladosporium
description Early detection of diseases and pests is a key factor in eradicating or minimising the damage that these may cause. In this work, a comprehensive solution is presented that is based on the composition of existing cloud solutions and mobile tools to detect in-situ issues. The platform presented was used for the detection of powdery mildew and Cladosporium diseases in tomatoes. The results of using the approach to carry out this task were more than satisfactory since it managed to correctly detect the symptoms, having mAP of 0.41 in at least some of these symptoms. We analysed the performance of our dataset, on the one hand, and the combination of PlantDoc dataset, on the other hand. This shows that the platform can be used in the agriculture sector, as an additional tool for detecting diseases and pests in order to combat the problem and reduce its consequences.
format Articulo
Articulo
author Urbieta, Mario Matías
Urbieta, Martín
Pereyra, Mauro Ezequiel
Laborde, Tomás
Villarreal, Guillermo
Pino, Mariana del
author_facet Urbieta, Mario Matías
Urbieta, Martín
Pereyra, Mauro Ezequiel
Laborde, Tomás
Villarreal, Guillermo
Pino, Mariana del
author_sort Urbieta, Mario Matías
title A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
title_short A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
title_full A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
title_fullStr A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
title_full_unstemmed A scalable offline AI-based solution to assist the diseases and plague detection in agriculture
title_sort scalable offline ai-based solution to assist the diseases and plague detection in agriculture
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/160240
work_keys_str_mv AT urbietamariomatias ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT urbietamartin ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT pereyramauroezequiel ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT labordetomas ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT villarrealguillermo ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT pinomarianadel ascalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT urbietamariomatias scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT urbietamartin scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT pereyramauroezequiel scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT labordetomas scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT villarrealguillermo scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
AT pinomarianadel scalableofflineaibasedsolutiontoassistthediseasesandplaguedetectioninagriculture
_version_ 1807221856953958400