Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Dec 30, 2025

Forced Salivation As a Method to Analyze Vector Competence of Mosquitoes
05:03

Forced Salivation As a Method to Analyze Vector Competence of Mosquitoes

Published on: August 7, 2018

10.1K

Classification and Morphological Analysis of Vector Mosquitoes using Deep Convolutional Neural Networks.

Junyoung Park1,2, Dong In Kim3,2, Byoungjo Choi1,2

  • 1Department of Embedded Systems Engineering, Incheon National University, Incheon, 22012, South Korea.

Scientific Reports
|January 25, 2020
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Longitudinal Healing and Amputation Trajectories in Diabetic Foot Ulcers: Predictive Power of Wound Area and Duration and Sample-Size Implications From the Diabetic Foot Consortium.

Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society·2026
Same author

Morphological characteristics of antennal and maxillary palp sensilla in three East Asian biting midges, Culicoides (Diptera: Ceratopogonidae).

Journal of medical entomology·2026
Same author

Prognostic effect of changes in high-density lipoprotein cholesterol after kidney transplantation.

Scientific reports·2026
Same author

Hematopoietic mosaic chromosomal alterations are pleiotropic drivers of inflammaging, multimorbidity, and mortality.

medRxiv : the preprint server for health sciences·2026
Same author

Beyond Fixed Thresholds: Optimizing Summaries of Wearable Device Data via Piecewise Linearization of Quantile Functions.

Statistics in medicine·2026
Same author

Magnesium at the Neurovascular Interface: A Narrative Review of Atherosclerosis, Peripheral Arterial Disease, and Neuropathic Pain.

Nutrients·2026

Deep learning models achieve over 97% accuracy in classifying vector mosquitoes from images. This approach utilizes deep convolutional neural networks (DCNNs) and transfer learning, mimicking human expert analysis for disease vector identification.

Area of Science:

  • Entomology
  • Computer Science
  • Public Health

Background:

  • Accurate classification of vector mosquitoes is crucial for early detection of mosquito-borne diseases.
  • Previous image-based classification methods lacked accuracy and required specific mosquito postures.
  • Deep convolutional neural networks (DCNNs) offer advanced visual feature extraction for object classification.

Purpose of the Study:

  • To evaluate state-of-the-art deep learning models for classifying mosquito species with high inter-species similarity and intra-species variations.
  • To address data scarcity by constructing a diverse dataset and exploring transfer learning.
  • To achieve classification accuracy comparable to human experts.

Main Methods:

  • Construction of a dataset with approximately 3,600 images of 8 mosquito species, including various postures and deformation conditions.

More Related Videos

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
10:35

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

3.4K
Alphavirus Transducing System: Tools for Visualizing Infection in Mosquito Vectors
07:12

Alphavirus Transducing System: Tools for Visualizing Infection in Mosquito Vectors

Published on: November 24, 2010

15.3K

Related Experiment Videos

Last Updated: Dec 30, 2025

Forced Salivation As a Method to Analyze Vector Competence of Mosquitoes
05:03

Forced Salivation As a Method to Analyze Vector Competence of Mosquitoes

Published on: August 7, 2018

10.1K
Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
10:35

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

3.4K
Alphavirus Transducing System: Tools for Visualizing Infection in Mosquito Vectors
07:12

Alphavirus Transducing System: Tools for Visualizing Infection in Mosquito Vectors

Published on: November 24, 2010

15.3K
  • Application of deep convolutional neural networks (DCNNs) for image classification.
  • Investigation of transfer learning by fine-tuning general features from a generic dataset.
  • Utilization of data augmentation techniques.
  • Visualization of discriminative regions to understand model decision-making.

    • Main Results:

    • Achieved over 97% classification accuracy by fine-tuning pre-trained deep learning models with appropriate data augmentation.
    • Demonstrated the effectiveness of transfer learning in overcoming data scarcity for mosquito image classification.
    • Identified that DCNNs utilize morphological features similar to those employed by human experts.

    Conclusions:

    • Deep learning models, particularly DCNNs, are highly effective for accurate automatic classification of vector mosquitoes.
    • Transfer learning combined with data augmentation is a viable strategy to address data limitations in specialized image classification tasks.
    • The developed approach shows potential for enhancing vector surveillance and early warning systems for mosquito-borne diseases.