A deep learning-based pipeline for mosquito detection and classification from wingbeat sounds
Issued Date
2023-02-01
Resource Type
ISSN
13807501
eISSN
15737721
Scopus ID
2-s2.0-85132346978
Journal Title
Multimedia Tools and Applications
Volume
82
Issue
4
Start Page
5189
End Page
5205
Rights Holder(s)
SCOPUS
Bibliographic Citation
Multimedia Tools and Applications Vol.82 No.4 (2023) , 5189-5205
Suggested Citation
Yin M.S., Haddawy P., Ziemer T., Wetjen F., Supratak A., Chiamsakul K., Siritanakorn W., Chantanalertvilai T., Sriwichai P., Sa-ngamuang C. A deep learning-based pipeline for mosquito detection and classification from wingbeat sounds. Multimedia Tools and Applications Vol.82 No.4 (2023) , 5189-5205. 5205. doi:10.1007/s11042-022-13367-0 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/84229
Title
A deep learning-based pipeline for mosquito detection and classification from wingbeat sounds
Author's Affiliation
Other Contributor(s)
Abstract
Mosquito vector-borne diseases such as malaria and dengue constitute some of the most serious public health burdens in tropical and sub-tropical countries. Effective targeting of disease control efforts requires accurate estimates of mosquito vector population density. The traditional, and still most common, approach to this involves the use of traps along with manual counting and classification of mosquito species. This process is costly and labor-intensive, which hinders its widespread use. In this paper we present a software pipeline for detection and classification of mosquito wingbeat sounds. Since our target platform is low-cost IoT devices, we explore the tradeoff between accuracy and efficiency. When a fast binary mosquito detector precedes the classifier, we can reduce the computational demand compared with use of the classifier alone by a factor of 10. While the accuracy of traditional machine learning model drops from 90% to 64% when reducing the sample rate from 96 kHz to 8 kHz, our deep-learning models maintain an accuracy of almost 83%, even when additionally reducing the bit depth from 24 to 16 bits. We conclude that the combination of an efficient mosquito detector with a convolutional neural network provides for an excellent trade-off between accuracy and efficiency to detect, classify and count mosquitoes.