Related Experiment Video
Updated: Aug 27, 2025
10:35
Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
Published on: May 31, 2020
3.1K
Dataset of vector mosquito images
Reshma Pise1, Kailas Patil2, Meena Laad3
1Research scholar, Vishwakarma University, Pune, India.
Data in Brief
|September 27, 2022
Summary
This study introduces a new image dataset of dangerous mosquito species, Aedes Aegypti, Anopheles stephensi, and Culex quinquefasciatus. This resource aids in developing automated systems for mosquito species identification and disease control.
Area of Science:
- Medical Entomology
- Computer Vision
- Public Health
Background:
- Mosquitoes are significant global health threats, transmitting diseases like Dengue, Yellow Fever, Chikungunya, and Zika.
- Accurate identification of mosquito vectors, including Aedes, Anopheles, and Culex genera, is crucial for effective vector control strategies.
- Existing methods for mosquito identification may lack the scalability and precision required for widespread public health initiatives.
Purpose of the Study:
- To create a novel, comprehensive dataset of high-quality images for dangerous mosquito species.
- To facilitate the development and training of machine learning and deep learning models for automated mosquito species classification.
- To support advancements in vector control by enabling precise and rapid identification of disease-carrying mosquitoes.
Main Methods:
- Compilation of an image dataset featuring adult mosquitoes from three key species: Aedes Aegypti, Anopheles stephensi, and Culex quinquefasciatus.
- Inclusion of both original and augmented images to enhance dataset diversity and robustness, totaling 2640 augmented images.
- Dataset organized into distinct folders for original and augmented images, ensuring accessibility for various research needs.
Main Results:
- A novel dataset comprising original and augmented images of Aedes Aegypti, Anopheles stephensi, and Culex quinquefasciatus has been successfully constructed.
- The dataset contains 2640 augmented images, providing a rich resource for training sophisticated identification models.
- The organized structure of the dataset facilitates its use in machine learning and deep learning applications.
Conclusions:
- The developed mosquito image dataset is a valuable resource for advancing automated species identification.
- This dataset will empower researchers to build more accurate and efficient AI models for mosquito surveillance and control.
- Facilitating automated identification can significantly enhance public health efforts against mosquito-borne diseases.
