Acoustic Identification of Aedes aegypti: Experimental Assessment of Different Machine Learning Techniques

• Kayuã Oleques Paim UFRGS
• Thaís Marcelle Dihl da Silva UFRGS
• Jaqueline Dilly UFRGS
• Anderson Rocha Tavares UFRGS
• Marielton dos Passos Cunha UNICAMP
• Onilda Santos da Silva UFRGS
• Mariana Recamonde-Mendoza UFRGS
• Rodrigo Brandão Mansilha UNIPAMPA
• Weverton Cordeiro UFRGS

DOI: https://doi.org/10.5753/semish.2025.6555

Resumo

Mosquito-borne diseases affect over 700 million people annually, demanding effective and scalable monitoring solutions. Traditional traps, while reliable, are costly and have limited coverage. Recent studies have shown that mosquito wingbeat audio can enable species identification using convolutional neural networks, but alternative machine learning (ML) models remain underexplored. This study compares five ML architectures – Residual Network, Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Conformer, and Audio Spectrogram Transformer (AST) – for classifying Aedes aegypti from audio data. Using public datasets and standardized preprocessing, we evaluate performance through cross-validation and multiple classification metrics. All architectures analyzed achieved accuracy and F1-scores above 88%, with particular emphasis on MLP and LSTM which, despite their simpler structures, showed competitive performance compared to other networks. These findings support the development of low-cost, audio-based mosquito monitoring systems.

Referências

Adhane, G. et al. (2022). On the use of uncertainty in classifying aedes albopictus mosquitoes. IEEE Journal of Selected Topics in Signal Processing, 16(2):224–233.

Ahmed, D. A. et al. (2022). Managing biological invasions: the cost of inaction. Biological Invasions, 24(7):1927–1946.

Balestrino, F., Iyaloo, D. P., Elahee, K. B., Bheecarry, A., Campedelli, F., Carrieri, M., and Bellini, R. (2016). A sound trap for aedes albopictus (skuse) male surveillance: response analysis to acoustic and visual stimuli. Acta tropica, 164:448–454.

Chen, Y., Why, A., Batista, G., Mafra-Neto, A., and Keogh, E. (2014). Flying insect classification with inexpensive sensors. Journal of Insect Behavior, 27(5):657–677.

Fernandes, M. S., Cordeiro, W., and Recamonde-Mendoza, M. (2021). Detecting aedes aegypti mosquitoes through audio classification with convolutional neural networks. Computers in Biology and Medicine, 129:104152.

Forsyth, J. et al. (2020). Source reduction with a purpose: Mosquito ecology and community perspectives offer insights for improving household mosquito management in coastal kenya. PLoS neglected tropical diseases, 14(5):e0008239.

Gong, Y., Chung, Y.-A., and Glass, J. R. (2021). Ast: Audio spectrogram transformer. ArXiv, abs/2104.01778.

Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., and Pang, R. (2020). Conformer: Convolution-augmented transformer for speech recognition. pages 5036–5040.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Comput., 9(8):1735–1780.

Johnson, B. J. and Ritchie, S. A. (2016). The siren’s song: Exploitation of female flight tones to passively capture male aedes aegypti (diptera: Culicidae). Journal of medical entomology, 53(1):245–248.

Kahn, M. C., Celestin, W., Offenhauser, W., et al. (1945). Recording of sounds produced by certain disease-carrying mosquitoes. Science (Washington), pages 335–6.

Kim, D., DeBriere, T., Cherukumalli, S., White, G., and Burkett-Cadena, N. (2021). Infrared light sensors permit rapid recording of wingbeat frequency and bioacoustic species identification of mosquitoes. Scientific Reports, 11.

Kiskin, I., Zilli, D., Li, Y., Sinka, M., Willis, K., and Roberts, S. (2020). Bioacoustic detection with wavelet-conditioned convolutional neural networks. Neural Computing and Applications, 32(4):915–927.

Leandro, A. S. et al. (2022). Citywide integrated aedes aegypti mosquito surveillance as early warning system for arbovirus transmission, brazil. Emerging Infectious Diseases, 28(4):707.

Li, Z., Zhou, Z., Shen, Z., and Yao, Q. (2005). Automated identification of mosquito (diptera: Culicidae) wingbeat waveform by artificial neural network. In IFIP International Conference on Artificial Intelligence Applications and Innovations, pages 483–489. Springer.

Motta, D. et al. (2019). Application of convolutional neural networks for classification of adult mosquitoes in the field. PLOS ONE, 14(1):1–18.

Mukundarajan, H., Hol, F. J. H., Castillo, E. A., Newby, C., and Prakash, M. (2017). Using mobile phones as acoustic sensors for high-throughput mosquito surveillance. Elife, 6:e27854.

Ouyang, T.-H., Yang, E.-C., Jiang, J.-A., and Lin, T.-T. (2015). Mosquito vector monitoring system based on optical wingbeat classification. Computers and Electronics in Agriculture, 118:47–55.

Paim, K. O. et al. (2024). Acoustic identification of ae. aegypti mosquitoes using smartphone apps and residual convolutional neural networks. Biomedical Signal Processing and Control, 95:106342.

Piczak, K. J. (2015). ESC: Dataset for Environmental Sound Classification. In 23rd Annual ACM Conference on Multimedia, pages 1015–1018. ACM Press.

Qureshi, A. I. (2018). Chapter 2 - mosquito-borne diseases. In Qureshi, A. I., editor, Zika Virus Disease, pages 27–45. Academic Press.

Su Yin, M. et al. (2022). A deep learning-based pipeline for mosquito detection and classification from wingbeat sounds. Multimedia Tools and Applications, 2022.

Townson, H. et al. (2005). Exploiting the potential of vector control for disease prevention. Bulletin of the World Health Organization, 83:942–947.

Vasconcelos, D., Nunes, N., Ribeiro, M., Prandi, C., and Rogers, A. (2019). Locomobis: a low-cost acoustic-based sensing system to monitor and classify mosquitoes. In 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC), pages 1–6. IEEE.

Waltz, E. et al. (2021). First genetically modified mosquitoes released in the united states. Nature, 593(7858):175–176.

Wei, X., Hossain, M., and Ahmed, K. A. (2022). A resnet attention model for classifying mosquitoes from wing-beating sounds. Scientific Reports, 12:10334.

Yin, M. S. et al. (2021). A lightweight deep learning approach to mosquito classification from wingbeat sounds. In Conference on Information Technology for Social Good, GoodIT ’21, page 37–42, New York, NY, USA. ACM.