Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

Abstract Classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Song-Quan Ong, Hamdan Ahmad, Gomesh Nair, Pradeep Isawasan, Abdul Hafiz Ab Majid
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/4be1f46a17c843fea7c14d3e3a135713
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4be1f46a17c843fea7c14d3e3a135713
record_format	dspace
spelling	oai:doaj.org-article:4be1f46a17c843fea7c14d3e3a1357132021-12-02T17:02:05ZImplementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time10.1038/s41598-021-89365-32045-2322https://doaj.org/article/4be1f46a17c843fea7c14d3e3a1357132021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-89365-3https://doaj.org/toc/2045-2322Abstract Classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.Song-Quan OngHamdan AhmadGomesh NairPradeep IsawasanAbdul Hafiz Ab MajidNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Song-Quan Ong Hamdan Ahmad Gomesh Nair Pradeep Isawasan Abdul Hafiz Ab Majid Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
description	Abstract Classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.
format	article
author	Song-Quan Ong Hamdan Ahmad Gomesh Nair Pradeep Isawasan Abdul Hafiz Ab Majid
author_facet	Song-Quan Ong Hamdan Ahmad Gomesh Nair Pradeep Isawasan Abdul Hafiz Ab Majid
author_sort	Song-Quan Ong
title	Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
title_short	Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
title_full	Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
title_fullStr	Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
title_full_unstemmed	Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time
title_sort	implementation of a deep learning model for automated classification of aedes aegypti (linnaeus) and aedes albopictus (skuse) in real time
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/4be1f46a17c843fea7c14d3e3a135713
work_keys_str_mv	AT songquanong implementationofadeeplearningmodelforautomatedclassificationofaedesaegyptilinnaeusandaedesalbopictusskuseinrealtime AT hamdanahmad implementationofadeeplearningmodelforautomatedclassificationofaedesaegyptilinnaeusandaedesalbopictusskuseinrealtime AT gomeshnair implementationofadeeplearningmodelforautomatedclassificationofaedesaegyptilinnaeusandaedesalbopictusskuseinrealtime AT pradeepisawasan implementationofadeeplearningmodelforautomatedclassificationofaedesaegyptilinnaeusandaedesalbopictusskuseinrealtime AT abdulhafizabmajid implementationofadeeplearningmodelforautomatedclassificationofaedesaegyptilinnaeusandaedesalbopictusskuseinrealtime
_version_	1718381966530707456

Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

Ejemplares similares