GBU College Logo
Sign in with GBU Microsoft

Identification of Mosquito Species from Larvae Using Machine Learning and Augmented Reality

TEM Journal | 2026

Paper Details

Authors: Kajornkasirat S.; Puangsuwan K.; Limrattanabunjong C.; Nopnorb P.

DOI: 10.18421/TEM151-01

Journal: TEM Journal

Year: 2026

Publisher: UIKTEN - Association for Information Communication Technology Education and Science

Document Type: Article

Open Access: All Open Access; Gold Open Access

Cited by: 0

Abstract

– This study is focused on enhancing the development of skills and promoting a comprehensive understanding of health science education by providing an accessible educational tool aligned with current technology trends. Users access the mobile application to classify mosquito larvae species by uploading pictures of the larvae to the system. The system provides a 3D model of mosquito larvae that users can view via AR (Augmented Reality) using their mobile camera. TensorFlow was used to train a mosquito larvae identification model for 50 rounds, achieving a 92% accuracy. AR can be used to give users a close-up look at the different features of mosquito larvae, such as their segmented body, siphon, and bristles. This can help users to better understand the biology and behavior of mosquito larvae, and to learn to identify their species. These systems can be trained on a labeled dataset of mosquito larvae images to learn to identify different species of mosquitoes, including Aedes and Culex spp. Once trained, these systems can be used to identify mosquito larvae quickly and accurately. Automated mosquito larval identification systems have the potential to play a significant role in the prevention and control of mosquito-borne diseases. © (2026), (UIKTEN - Association for Information Communication Technology Education and Science). All rights reserved.

Keywords

3D model; augmented reality; classification; machine learning; Mosquito larvae