Towards automatic classification of mosquito species based on wing geometrical features

Dennis Carrillo; Diego S. Benitez; Giovanni Ramon; Noel Perez

doi:10.1109/ANDESCON50619.2020.9271981

Towards automatic classification of mosquito species based on wing geometrical features

Dennis Carrillo
, Diego S. Benitez
, Giovanni Ramon
, Noel Perez

Universidad San Francisco de Quito

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

3 Scopus citations

Abstract

This paper presents an initial version of a system for the automated classification of mosquitoes species, based on relevant features extracted from their wing's morphology. The algorithm developed allows identifying the mosquito's species by using key reference points of the wing, such as the radio of the circular geometries of spots presents within the wing. The aim was to develop an initial version of a system for improving the standard manual method in which mosquitoes are classified, as a proof of concept. For testing the system, two particular species: Limatus durhamii and Wyeomyia sp. were used for classification using a simple perceptron. The model reached an accuracy value of 95.46% in predicting new wing samples. Initial results indicate that with future refinements, an automated classification system is feasible.

Original language	English
Title of host publication	2020 IEEE ANDESCON, ANDESCON 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728193656
DOIs	https://doi.org/10.1109/ANDESCON50619.2020.9271981
State	Published - 13 Oct 2020
Event	2020 IEEE ANDESCON, ANDESCON 2020 - Quito, Ecuador Duration: 13 Oct 2020 → 16 Oct 2020

Publication series

Name	2020 IEEE ANDESCON, ANDESCON 2020

Conference

Conference	2020 IEEE ANDESCON, ANDESCON 2020
Country/Territory	Ecuador
City	Quito
Period	13/10/20 → 16/10/20

Keywords

Automated classification
Geometrical features
Mosquito species
Supervised learning

Access to Document

10.1109/ANDESCON50619.2020.9271981

Cite this

@inproceedings{217af919e5834df4b0f71831c21623a7,

title = "Towards automatic classification of mosquito species based on wing geometrical features",

abstract = "This paper presents an initial version of a system for the automated classification of mosquitoes species, based on relevant features extracted from their wing's morphology. The algorithm developed allows identifying the mosquito's species by using key reference points of the wing, such as the radio of the circular geometries of spots presents within the wing. The aim was to develop an initial version of a system for improving the standard manual method in which mosquitoes are classified, as a proof of concept. For testing the system, two particular species: Limatus durhamii and Wyeomyia sp. were used for classification using a simple perceptron. The model reached an accuracy value of 95.46\% in predicting new wing samples. Initial results indicate that with future refinements, an automated classification system is feasible.",

keywords = "Automated classification, Geometrical features, Mosquito species, Supervised learning",

author = "Dennis Carrillo and Benitez, \{Diego S.\} and Giovanni Ramon and Noel Perez",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE ANDESCON, ANDESCON 2020 ; Conference date: 13-10-2020 Through 16-10-2020",

year = "2020",

month = oct,

day = "13",

doi = "10.1109/ANDESCON50619.2020.9271981",

language = "Ingl{\'e}s",

series = "2020 IEEE ANDESCON, ANDESCON 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 IEEE ANDESCON, ANDESCON 2020",

}

Carrillo, D, Benitez, DS, Ramon, G & Perez, N 2020, Towards automatic classification of mosquito species based on wing geometrical features. in 2020 IEEE ANDESCON, ANDESCON 2020., 9271981, 2020 IEEE ANDESCON, ANDESCON 2020, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE ANDESCON, ANDESCON 2020, Quito, Ecuador, 13/10/20. https://doi.org/10.1109/ANDESCON50619.2020.9271981

Towards automatic classification of mosquito species based on wing geometrical features. / Carrillo, Dennis; Benitez, Diego S.; Ramon, Giovanni et al.
2020 IEEE ANDESCON, ANDESCON 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9271981 (2020 IEEE ANDESCON, ANDESCON 2020).

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

TY - GEN

T1 - Towards automatic classification of mosquito species based on wing geometrical features

AU - Carrillo, Dennis

AU - Benitez, Diego S.

AU - Ramon, Giovanni

AU - Perez, Noel

PY - 2020/10/13

Y1 - 2020/10/13

N2 - This paper presents an initial version of a system for the automated classification of mosquitoes species, based on relevant features extracted from their wing's morphology. The algorithm developed allows identifying the mosquito's species by using key reference points of the wing, such as the radio of the circular geometries of spots presents within the wing. The aim was to develop an initial version of a system for improving the standard manual method in which mosquitoes are classified, as a proof of concept. For testing the system, two particular species: Limatus durhamii and Wyeomyia sp. were used for classification using a simple perceptron. The model reached an accuracy value of 95.46% in predicting new wing samples. Initial results indicate that with future refinements, an automated classification system is feasible.

AB - This paper presents an initial version of a system for the automated classification of mosquitoes species, based on relevant features extracted from their wing's morphology. The algorithm developed allows identifying the mosquito's species by using key reference points of the wing, such as the radio of the circular geometries of spots presents within the wing. The aim was to develop an initial version of a system for improving the standard manual method in which mosquitoes are classified, as a proof of concept. For testing the system, two particular species: Limatus durhamii and Wyeomyia sp. were used for classification using a simple perceptron. The model reached an accuracy value of 95.46% in predicting new wing samples. Initial results indicate that with future refinements, an automated classification system is feasible.

KW - Automated classification

KW - Geometrical features

KW - Mosquito species

KW - Supervised learning

UR - https://www.scopus.com/pages/publications/85098589815

U2 - 10.1109/ANDESCON50619.2020.9271981

DO - 10.1109/ANDESCON50619.2020.9271981

M3 - Contribución a la conferencia

AN - SCOPUS:85098589815

T3 - 2020 IEEE ANDESCON, ANDESCON 2020

BT - 2020 IEEE ANDESCON, ANDESCON 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE ANDESCON, ANDESCON 2020

Y2 - 13 October 2020 through 16 October 2020

ER -

Towards automatic classification of mosquito species based on wing geometrical features

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this