PRELIMINARY STUDY ON EGG RECOGNITION MODEL OF AEDES ALBOPICTUS BASED ON DEEP LEARNING

Journal Title: Acta Parasitologica et Medica Entomologica Sinica - Year 2024, Vol 31, Issue 1

Abstract

[Objective] In this study, a pictorial database of Aedes albopictus eggs was built to establish a model for the automatic recognition and counting of eggs of this mosquito species. [Methods] In total, 449 images of Ae. albopictus eggs from field strains in three districts of Shanghai and laboratory strains were collected. The eggs were manually calibrated using the Python environment labeling library, and the faster region-based convolution neural network (Faster R-CNN) was used to train the model with the tile overlap method. [Results] The results of model validation evaluation using accuracy, recall, and F-measure showed that after 15 training sessions, the loss gradually decreased with increasing training frequency and ultimately decreased to 0.000119. The mean accuracy (mAP) increased from 0.968 to 0.980 with increasing training frequency. The final model had an accuracy of up to 0.90, a recall rate of 0.97, and an F-measure of 0.93. [Conclusion] The established model achieved its function of assisting in egg identification and counting. With further optimization of the model and refining of its classification and recognition capabilities, it will serve as a simple and efficient auxiliary monitoring tool.

Authors and Affiliations

Min-hui ZHU, Lin-juan DONG, Dun-jia WANG, Yi-zhou CAI, Zhao-wen ZHANG, Yao LIU, Shi-peng HE, Yi-bin ZHOU

Keywords

Related Articles

SILENCING OF COXIELLA BURNETII DOTB BASED ON CRISPR INTERFERENCE

[Objective] A recombinant plasmid for CRISPR interference (CRISPRi) that incorporates dCas9 from Streptococcus pyogenes was constructed to investigate the function of Coxiella burnetii genes through a prompt, simple meth...

SURVEILLANCE ON MAJOR HUMAN PARASITIC DISEASES AND RESIDENT AWARENESS IN TONGZHOU DISTRICT, BEIJING FROM 2011 TO 2022

[Objective] To analyze the surveillance and investigation results of parasitic diseases in the Tongzhou district of Beijing from 2011 to 2022, and to provide scientific basis for formulating prevention and control measur...

A RAPID CRISPR/CAS13A SYSTEM-BASED METHOD FOR DETECTING SEVERE FEVER WITH THROMBOCYTOPENIA SYNDROME VIRUS

[Objective] To develop a rapid and sensitive on-site nucleic acid detection method based on the clustered regularly interspaced short palindromic repeats (CRISPR) system to detect severe fever with thrombocytopenia syndr...

PRELIMINARY STUDY ON EGG RECOGNITION MODEL OF AEDES ALBOPICTUS BASED ON DEEP LEARNING

[Objective] In this study, a pictorial database of Aedes albopictus eggs was built to establish a model for the automatic recognition and counting of eggs of this mosquito species. [Methods] In total, 449 images of Ae. a...

RESPONSE OF TICKS TO HOSTS′ SEMIOCHEMICALS AND ITS ROLE IN TICKS AND TICK-BORNE DISEASE CONTROL

As obligated blood-sucking arthropods, ticks have become a serious health burden to the public as they transmit various pathogens to humans and other host animals. The extent of harm caused by tick bites heavily relies o...

Download PDF file
  • EP ID EP753967
  • DOI 10-3969/j.issn.1005-0507-2024-01-003
  • Views 3
  • Downloads 0

How To Cite

Min-hui ZHU, Lin-juan DONG, Dun-jia WANG, Yi-zhou CAI, Zhao-wen ZHANG, Yao LIU, Shi-peng HE, Yi-bin ZHOU (2024). PRELIMINARY STUDY ON EGG RECOGNITION MODEL OF AEDES ALBOPICTUS BASED ON DEEP LEARNING. Acta Parasitologica et Medica Entomologica Sinica, 31(1), -. https://europub.co.uk/articles/-A-753967