DEEP LEARNING APPLIED TO MOSQUITOES AUDIO SIGNAL CLASSIFICATION

Keywords: Categorization, Spectrograms, Mosquitoes, Sound, Flight

Abstract

This study aims to classify sound signals emitted during the flight of mosquitoes of the species Culex quinquefasciatus and Anopholes Gambiae. To achieve this objective, Deep Learning techniques were employed, which involve machine learning through the input of data and complex learning models called deep artificial neural networks, which process information at abstract levels and allow the machine to extract more sophisticated patterns and features from the data. The input data used for the classification task consisted of spectrograms extracted from the audio files of both classes. These spectrograms were fed into six different convolutional neural network models. The highest accuracy achieved among the model's during training was 99.15%, and 98.87% on the test set, results obtained by the same model.

Downloads

Download data is not yet available.

References

BACOCHINA, Giovanni Araujo; THOM DE SOUZA, Rodrigo Clemente. Element-Wise Attention Layers: An Option for Optimization. Disponível em: https://ssrn.com/abstract=4460607
BRASIL. Ministério da Saúde. Situação Epidemiológica da Malária. Disponível em: https://www.gov.br/saude/pt-br/assuntos/saude-de-a-a-z/m/malaria/situacao-epidemiologica-da-malaria. Acesso em: 06 out. 2022.
BRASSOLATTI, Rejane Cristina; ANDRADE, Carlos Fernando S. Avaliação de uma intervenção educativa na prevenção da dengue. Ciência & Saúde Coletiva, v. 7, n. 2, p. 243-251, 2002. ISSN 1413-8123. DOI: 10.1590/S1413-81232002000200005.
CONSOLI, Rotraut A.G.B.; OLIVEIRA, Ricardo Lourenço de. Principais mosquitos de importância sanitária no Brasil. Rio de Janeiro: Editora Fiocruz, 1994. 228p.
CIZOTTO, André et al. Web pages from mockup design based on convolutional neural network and class activation mapping. Multimedia Tools and Applications, v. 82, mar. 2023. DOI: 10.1007/s11042-023-15108-3.
DAHMER DOS SANTOS, Luiz Fillipe et al. Thermographic image-based diagnosis of failures in electrical motors using deep transfer learning. Engineering Applications of Artificial Intelligence, v. 126, p. 107106, 2023. ISSN 0952-1976. DOI: https://doi.org/10.1016/j.engappai.2023.107106. Disponível em: https://www.sciencedirect.com/science/article/pii/S0952197623012903.
FERNANDES, Marcelo Schreiber; CORDEIRO, Weverton; RECAMONDE-MENDOZA, Mariana. Detecting Aedes aegypti mosquitoes through audio classification with convolutional neural networks. Computers in Biology and Medicine, v. 129, p. 104152, 2021. ISSN 0010-4825. DOI: https://doi.org/10.1016/j.compbiomed.2020.104152. Disponível em: https://www.sciencedirect.com/science/article/pii/S0010482520304832.
FOLEY, Desmond; RUEDA, Leopoldo; WILKERSON, Richard. Insight into Global Mosquito Biogeography from Country Species Records. Journal of Medical Entomology, v. 44, n. 8, p. 554-567, agosto de 2007. DOI: 10.1603/0022-2585(2007)44[554:IIGMBF]2.0.CO;2.
KISKIN, Ivan; ZILLI, Davide; LI, Yunpeng; SINKA, Marianne; WILLIS, Kathy; ROBERTS, Stephen. Bioacoustic detection with wavelet-conditioned convolutional neural networks. Neural Computing and Applications, v. 32, n. 4, p. 915-927, fevereiro de 2020. ISSN 1433-3058. DOI: 10.1007/s00521-018-3626-7.
LECUN, Yann; BENGIO, Yoshua; HINTON, Geoffrey. Deep learning. Nature, v. 521, n. 7553, p. 436-444, maio de 2015. ISSN 1476-4687. DOI: 10.1038/nature14539.
LIU, Xu-Ying; WU, Jianxin; ZHOU, Zhi-Hua. Exploratory Undersampling for Class-Imbalance Learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), v. 39, n. 2, p. 539-550, 2009. DOI: 10.1109/TSMCB.2008.2007853.
Published
2023-12-04
How to Cite
1.
de Oliveira Mathias AC, Montanher B, Beleti Junior CR, Mendes Santiago Junior R, Ferreira da Silva R, THOM DE SOUZA RC. DEEP LEARNING APPLIED TO MOSQUITOES AUDIO SIGNAL CLASSIFICATION . arqmudi [Internet]. 2023Dec.4 [cited 2025Nov.6];27(ESPECIAL3):38-6. Available from: https://periodicos.uem.br/ojs/index.php/ArqMudi/article/view/70546