Classification of Tropical Disease-carrying Mosquitoes Using Deep Learning and SHAP

  • Vinicius L. N. Fonseca UFAM
  • Fagner Cunha UFAM
  • Larissa Andrade UFAM
  • Juan G. Colonna UFAM
  • David De Yong UNRC

Resumo


In this paper, we present a novel technique for identifying mosquitoes that carry tropical diseases using Deep Learning and SHAP for model interpretability. We propose an end-to-end deep (E2E) Convolutional Neural Network (CNN) architecture that leverages mosquito wingbeat sounds to extract relevant features. To achieve high-performance audio processing, we integrate Kapre, an audio processing library optimized for GPU execution. Our approach also incorporates SHAP to provide a transparent explanation of the model’s predictions, enabling us to identify and characterize the time-frequency patterns that the model emphasizes. Ultimately, our research aims to support disease control initiatives by providing an automated means of identifying disease-carrying mosquito species, which has the potential to improve public health in tropical regions.

Referências

H. Caraballo and K. King. Emergency department management of mosquito-borne illness: malaria, dengue, and west nile virus. Emergency medicine practice, 16(5):1–23, 2014.

Y. Chen, A. Why, G. Batista, A. Mafra-Neto, and E. Keogh. Flying insect detection and classification with inexpensive sensors. JoVE (Journal of Visualized Experiments), page e52111, 2014.

K. Choi, D. Joo, and J. Kim. Kapre: On-gpu audio preprocessing layers for a quick implementation of deep neural network models with keras. In Machine Learning for Music Discovery Workshop at 34th International Conference on Machine Learning. ICML, 2017.

E. Fanioudakis, M. Geismar, and I. Potamitis. Mosquito wingbeat analysis and classification using deep learning. In 2018 26th European Signal Processing Conference (EUSIPCO), pages 2410–2414. IEEE, 2018.

A. Fleishman, C. Eberly, D. Klein, and M. McKown. Tutorial: Accurate Bioacoustic Species Detection from Small Numbers of Training Clips Using the Biophony Model. https://github.com/microsoft/acoustic-bird-detection, 2020.

H. Kampen, J. M. Medlock, A. G. Vaux, C. J. Koenraadt, A. J. Van Vliet, F. Bartumeus, A. Oltra, C. A. Sousa, S. Chouin, and D. Werner. Approaches to passive mosquito surveillance in the eu. Parasites & vectors, 8:1–13, 2015.

K. Ko, S. Park, and H. Ko. Convolutional feature vectors and support vector machine for animal sound classification. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 376–379. IEEE, 2018.

B. Logan et al. Mel frequency cepstral coefficients for music modeling. In Ismir, volume 270, page 11. Plymouth, MA, 2000.

R. Lühken, W. P. Pfitzner, J. Börstler, R. Garms, K. Huber, N. Schork, S. Steinke, E. Kiel, N. Becker, E. Tannich, et al. Field evaluation of four widely used mosquito traps in central europe. Parasites & Vectors, 7:1–11, 2014.

S. M. Lundberg and S.-I. Lee. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.

C. Molnar. Interpretable machine learning. Lulu.com, 2020. I. Nolasco, A. Terenzi, S. Cecchi, S. Orcioni, H. L. Bear, and E. Benetos. Audio-based identification of beehive states. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8256–8260. IEEE, 2019.

S. Ntalampiras. Automatic acoustic classification of insect species based on directed acyclic graphs. The Journal of the Acoustical Society of America, 145(6):EL541–EL546, 2019.

I. Potamitis and I. Rigakis. Novel noise-robust optoacoustic sensors to identify insects through wingbeats. IEEE Sensors Journal, 15(8):4621–4631, 2015.

M. T. Ribeiro, S. Singh, and C. Guestrin. ”why should i trust you?”explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016.

F. J. Rohlf and J. W. Archie. A comparison of fourier methods for the description of wing shape in mosquitoes (diptera: Culicidae). Systematic Zoology, 33(3):302–317, 1984.

R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626, 2017.

D. Smilkov, N. Thorat, B. Kim, F. Viégas, and M. Wattenberg. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825, 2017.

M. Sundararajan, A. Taly, and Q. Yan. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR, 2017.
Publicado
27/06/2023
FONSECA, Vinicius L. N.; CUNHA, Fagner; ANDRADE, Larissa; COLONNA, Juan G.; YONG, David De. Classification of Tropical Disease-carrying Mosquitoes Using Deep Learning and SHAP. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 23. , 2023, São Paulo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 25-34. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2023.229406.

Artigos mais lidos do(s) mesmo(s) autor(es)