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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Shear Behavior of GMTC/BPC-GCL Interface Under Dry and Hydrated Conditions with Varying Polymer Content.

Polymers·2026
Same author

From CAT-like to POD-like enzymatic activity of Cu-BHT tuning by substrate engineering.

Physical chemistry chemical physics : PCCP·2026
Same author

Synergistic Modulation of Crystallization Kinetics and Interface Energy-Level Alignment for Efficient Perovskite/Silicon Tandem Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Cough Audio Recognition for Early Detection of Respiratory Diseases: Algorithm Development and Validation Study.

JMIR medical informatics·2026
Same author

Phenol-soluble modulin alpha (PSMα) mediates autophagy induction and intracellular survival of <i>Staphylococcus Aureus</i> in bovine mammary epithelial cells.

The veterinary quarterly·2026
Same author

First-Principles Investigation of Ag Doping Effects on Phase Stability and Mechanical Properties in Rare-Earth Magnesium Alloy Mg<sub>24</sub>(Gd,Y)<sub>5</sub>.

Materials (Basel, Switzerland)·2026

Related Experiment Video

Updated: Aug 6, 2025

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.2K

Mosquito swarm counting via attention-based multi-scale convolutional neural network.

Huahua Chen1, Junhao Ren1, Wensheng Sun2

  • 1School of Communication Engineering, Hangzhou Dianzi University, 1158 2nd Street, Hangzhou, China.

Scientific Reports
|March 15, 2023
PubMed
Summary
This summary is machine-generated.

Accurately estimating mosquito swarm counts from images is crucial for predicting disease transmission. This study introduces an attention-based model that effectively counts mosquitoes, aiding in public health prevention efforts.

More Related Videos

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K
Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.
10:14

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

10.7K

Related Experiment Videos

Last Updated: Aug 6, 2025

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.2K
Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.2K
Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.
10:14

Tactile Conditioning And Movement Analysis Of Antennal Sampling Strategies In Honey Bees Apis mellifera L.

Published on: December 12, 2012

10.7K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Public Health

Background:

  • Mosquito-borne disease prevention relies on accurate mosquito density monitoring.
  • Predicting disease transmission risk requires precise mosquito swarm counting from imagery.

Purpose of the Study:

  • To develop and evaluate an accurate mosquito swarm counting model using deep learning.
  • To improve the estimation of mosquito density for public health surveillance.

Main Methods:

  • Proposed an attention-based multi-scale mosquito swarm counting model (AMRN).
  • Utilized VGG-16 for feature extraction and a multi-scale convolutional neural network with attention for density mapping.
  • Collected and annotated a dataset of 391 mosquito swarm images containing 15,466 mosquitoes.

Main Results:

  • The proposed model achieved a Mean Absolute Error (MAE) of 1.810.
  • The Root Mean Square Error (RMSE) was recorded as 3.467.
  • Demonstrated strong performance on the custom mosquito swarm image dataset.

Conclusions:

  • The attention-based multi-scale model provides accurate mosquito swarm counts.
  • This method can significantly enhance mosquito density monitoring for disease prevention.