Deep learning approaches for challenging species and gender identification of mosquito vectors

Abstract Microscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-onl...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Veerayuth Kittichai, Theerakamol Pengsakul, Kemmapon Chumchuen, Yudthana Samung, Patchara Sriwichai, Natthaphop Phatthamolrat, Teerawat Tongloy, Komgrit Jaksukam, Santhad Chuwongin, Siridech Boonsang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9f1704ac7cf0410296b933f43d63cd5e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9f1704ac7cf0410296b933f43d63cd5e
record_format	dspace
spelling	oai:doaj.org-article:9f1704ac7cf0410296b933f43d63cd5e2021-12-02T13:20:22ZDeep learning approaches for challenging species and gender identification of mosquito vectors10.1038/s41598-021-84219-42045-2322https://doaj.org/article/9f1704ac7cf0410296b933f43d63cd5e2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84219-4https://doaj.org/toc/2045-2322Abstract Microscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-only-look-once (YOLO) algorithm. This model can be used to simultaneously classify and localize the images to identify the species of the gender of field-caught mosquitoes. The results indicated that the concatenated two YOLO v3 model exhibited the optimal performance in identifying the mosquitoes, as the mosquitoes were relatively small objects compared with the large proportional environment image. The robustness testing of the proposed model yielded a mean average precision and sensitivity of 99% and 92.4%, respectively. The model exhibited high performance in terms of the specificity and accuracy, with an extremely low rate of misclassification. The area under the receiver operating characteristic curve (AUC) was 0.958 ± 0.011, which further demonstrated the model accuracy. Thirteen classes were detected with an accuracy of 100% based on a confusion matrix. Nevertheless, the relatively low detection rates for the two species were likely a result of the limited number of wild-caught biological samples available. The proposed model can help establish the population densities of mosquito vectors in remote areas to predict disease outbreaks in advance.Veerayuth KittichaiTheerakamol PengsakulKemmapon ChumchuenYudthana SamungPatchara SriwichaiNatthaphop PhatthamolratTeerawat TongloyKomgrit JaksukamSanthad ChuwonginSiridech BoonsangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Veerayuth Kittichai Theerakamol Pengsakul Kemmapon Chumchuen Yudthana Samung Patchara Sriwichai Natthaphop Phatthamolrat Teerawat Tongloy Komgrit Jaksukam Santhad Chuwongin Siridech Boonsang Deep learning approaches for challenging species and gender identification of mosquito vectors
description	Abstract Microscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-only-look-once (YOLO) algorithm. This model can be used to simultaneously classify and localize the images to identify the species of the gender of field-caught mosquitoes. The results indicated that the concatenated two YOLO v3 model exhibited the optimal performance in identifying the mosquitoes, as the mosquitoes were relatively small objects compared with the large proportional environment image. The robustness testing of the proposed model yielded a mean average precision and sensitivity of 99% and 92.4%, respectively. The model exhibited high performance in terms of the specificity and accuracy, with an extremely low rate of misclassification. The area under the receiver operating characteristic curve (AUC) was 0.958 ± 0.011, which further demonstrated the model accuracy. Thirteen classes were detected with an accuracy of 100% based on a confusion matrix. Nevertheless, the relatively low detection rates for the two species were likely a result of the limited number of wild-caught biological samples available. The proposed model can help establish the population densities of mosquito vectors in remote areas to predict disease outbreaks in advance.
format	article
author	Veerayuth Kittichai Theerakamol Pengsakul Kemmapon Chumchuen Yudthana Samung Patchara Sriwichai Natthaphop Phatthamolrat Teerawat Tongloy Komgrit Jaksukam Santhad Chuwongin Siridech Boonsang
author_facet	Veerayuth Kittichai Theerakamol Pengsakul Kemmapon Chumchuen Yudthana Samung Patchara Sriwichai Natthaphop Phatthamolrat Teerawat Tongloy Komgrit Jaksukam Santhad Chuwongin Siridech Boonsang
author_sort	Veerayuth Kittichai
title	Deep learning approaches for challenging species and gender identification of mosquito vectors
title_short	Deep learning approaches for challenging species and gender identification of mosquito vectors
title_full	Deep learning approaches for challenging species and gender identification of mosquito vectors
title_fullStr	Deep learning approaches for challenging species and gender identification of mosquito vectors
title_full_unstemmed	Deep learning approaches for challenging species and gender identification of mosquito vectors
title_sort	deep learning approaches for challenging species and gender identification of mosquito vectors
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/9f1704ac7cf0410296b933f43d63cd5e
work_keys_str_mv	AT veerayuthkittichai deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT theerakamolpengsakul deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT kemmaponchumchuen deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT yudthanasamung deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT patcharasriwichai deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT natthaphopphatthamolrat deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT teerawattongloy deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT komgritjaksukam deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT santhadchuwongin deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors AT siridechboonsang deeplearningapproachesforchallengingspeciesandgenderidentificationofmosquitovectors
_version_	1718393229319077888

Deep learning approaches for challenging species and gender identification of mosquito vectors

Ejemplares similares