MosquitoSong+: A noise-robust deep learning model for mosquito classification from wingbeat sounds
1
Issued Date
2024-10-01
Resource Type
eISSN
19326203
Scopus ID
2-s2.0-85208130191
Pubmed ID
39475971
Journal Title
PLoS ONE
Volume
19
Issue
10 October
Rights Holder(s)
SCOPUS
Bibliographic Citation
PLoS ONE Vol.19 No.10 October (2024)
Suggested Citation
Supratak A., Haddawy P., Yin M.S., Ziemer T., Siritanakorn W., Assawavinijkulchai K., Chiamsakul K., Chantanalertvilai T., Suchalermkul W., Sa-Ngamuang C., Sriwichai P. MosquitoSong+: A noise-robust deep learning model for mosquito classification from wingbeat sounds. PLoS ONE Vol.19 No.10 October (2024). doi:10.1371/journal.pone.0310121 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/101961
Title
MosquitoSong+: A noise-robust deep learning model for mosquito classification from wingbeat sounds
Corresponding Author(s)
Other Contributor(s)
Abstract
In order to assess risk of mosquito-vector borne disease and to effectively target and monitor vector control efforts, accurate information about mosquito vector population densities is needed. The traditional and still most common approach to this involves the use of traps along with manual counting and classification of mosquito species, but the costly and labor-intensive nature of this approach limits its widespread use. Numerous previous studies have sought to address this problem by developing machine learning models to automatically identify species and sex of mosquitoes based on their wingbeat sounds. Yet little work has addressed the issue of robust classification in the presence of environmental background noise, which is essential to making the approach practical. In this paper, we propose a new deep learning model, MosquitoSong+, to identify the species and sex of mosquitoes from raw wingbeat sounds so that it is robust to the environmental noise and the relative volume of the mosquito’s flight tone. The proposed model extends the existing 1D-CNN model by adjusting its architecture and introducing two data augmentation techniques during model training: noise augmentation and wingbeat volume variation. Experiments show that the new model has very good generalizability, with species classification accuracy above 80% on several wingbeat datasets with various background noise. It also has an accuracy of 93.3% for species and sex classification on wingbeat sounds overlaid with various background noises. These results suggest that the proposed approach may be a practical means to develop classification models that can perform well in the field.