Modelos de Classificação de Imagens Empregando Projeto Automático de Redes Neurais Convolucionais com Algoritmos Evolucionários
Resumo
Este estudo avaliou dois algoritmos evolucionários, o Population-Based Incremental Learning (PBIL) e o Genetic Algorithms (GA) na busca automatizada de arquiteturas de redes Multi-Layer Perceptron (MLP) e Convolutional Neural Network (CNN) para o problema de classificação multiclasse de imagens. Nos experimentos, a combinação de PBIL com CNN (PBIL-CNN) alcançou a maior acurácia, e a combinação GA-CNN apresentou bom equilíbrio entre desempenho e tempo de execução. A combinação PBIL-MLP foi a mais eficaz na busca por redes MLP, sendo melhor que a combinação GA-MLP. Os experimentos com PBIL apresentaram resultados mais promissores, mas os experimentos com GA apresentaram bons resultados com menos tempo de processamento.
Palavras-chave:
Algoritmos Evolucionários, Redes Neurais, Classificação de Imagens
Referências
R. C. Gonzalez and R. E. Woods, Digital Image Processing, Global Edition. Pearson Education, 2018.
J. Patterson and A. Gibson, Deep learning: A practitioner’s approach. O’Reilly Media, 2017.
G. F. Miller, P. M. Todd, and S. U. Hegde, “Designing neural networks using genetic algorithms.” in ICGA, vol. 89, 1989, pp. 379–384.
A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing, 2nd ed., ser. Natural computing series. Springer, Jul. 2015.
L. Ricardo, Algoritmos genéticos: uma importante ferramenta da inteligência computacional. Brasport, 2008.
S. Baluja and R. Caruana, “Removing the genetics from the standard genetic algorithm,” in Machine Learning Proceedings 1995. Elsevier, 1995, pp. 38–46.
A. H. Pratomo, N. H. Cahyana, and S. N. Indrawati, “Optimizing cnn hyperparameters with genetic algorithms for face mask usage classification,” Science in Information Technology Letters, vol. 4, no. 1, pp. 54–64, 2023.
A. Al-Hyari and M. Abu-Faraj, “Hyperparameters optimization of convolutional neural networks using evolutionary algorithms,” in 2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA). IEEE, 2022, pp. 1–6.
S. Lee, J. Kim, H. Kang, D.-Y. Kang, and J. Park, “Genetic algorithm based deep learning neural network structure and hyperparameter optimization,” Applied Sciences, vol. 11, no. 2, p. 744, 2021.
X. Xiao, M. Yan, S. Basodi, C. Ji, and Y. Pan, “Efficient hyperparameter optimization in deep learning using a variable length genetic algorithm,” arXiv preprint arXiv:2006.12703, 2020.
A. Krizhevsky, “Learning multiple layers of features from tiny images,” Tech. Rep., 2009.
R. Kruse, C. Borgelt, F. Klawonn, C. Moewes, M. Steinbrecher, and P. Held, Computational Intelligence, 2013rd ed., ser. Texts in computer science. London, England: Springer, Mar. 2013.
M. Abadi et al., “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2015, software available from tensorflow.org. [Online]. Available: [link]
F. Chollet, “Keras,” [link], 2015.
. F.-A. Fortin, F.-M. De Rainville, M.-A. Gardner, M. Parizeau, and C. G. ", “DEAP: Evolutionary algorithms made easy,” Journal of Machine Learning Research, vol. 13, pp. 2171–2175, jul 2012.
J. Patterson and A. Gibson, Deep learning: A practitioner’s approach. O’Reilly Media, 2017.
G. F. Miller, P. M. Todd, and S. U. Hegde, “Designing neural networks using genetic algorithms.” in ICGA, vol. 89, 1989, pp. 379–384.
A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing, 2nd ed., ser. Natural computing series. Springer, Jul. 2015.
L. Ricardo, Algoritmos genéticos: uma importante ferramenta da inteligência computacional. Brasport, 2008.
S. Baluja and R. Caruana, “Removing the genetics from the standard genetic algorithm,” in Machine Learning Proceedings 1995. Elsevier, 1995, pp. 38–46.
A. H. Pratomo, N. H. Cahyana, and S. N. Indrawati, “Optimizing cnn hyperparameters with genetic algorithms for face mask usage classification,” Science in Information Technology Letters, vol. 4, no. 1, pp. 54–64, 2023.
A. Al-Hyari and M. Abu-Faraj, “Hyperparameters optimization of convolutional neural networks using evolutionary algorithms,” in 2022 International Conference on Emerging Trends in Computing and Engineering Applications (ETCEA). IEEE, 2022, pp. 1–6.
S. Lee, J. Kim, H. Kang, D.-Y. Kang, and J. Park, “Genetic algorithm based deep learning neural network structure and hyperparameter optimization,” Applied Sciences, vol. 11, no. 2, p. 744, 2021.
X. Xiao, M. Yan, S. Basodi, C. Ji, and Y. Pan, “Efficient hyperparameter optimization in deep learning using a variable length genetic algorithm,” arXiv preprint arXiv:2006.12703, 2020.
A. Krizhevsky, “Learning multiple layers of features from tiny images,” Tech. Rep., 2009.
R. Kruse, C. Borgelt, F. Klawonn, C. Moewes, M. Steinbrecher, and P. Held, Computational Intelligence, 2013rd ed., ser. Texts in computer science. London, England: Springer, Mar. 2013.
M. Abadi et al., “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2015, software available from tensorflow.org. [Online]. Available: [link]
F. Chollet, “Keras,” [link], 2015.
. F.-A. Fortin, F.-M. De Rainville, M.-A. Gardner, M. Parizeau, and C. G. ", “DEAP: Evolutionary algorithms made easy,” Journal of Machine Learning Research, vol. 13, pp. 2171–2175, jul 2012.
Publicado
22/10/2025
Como Citar
SANTOS, Antony Kevin Ferreira; CAMPOS, Gustavo Augusto Lima de; ARAÚJO, Thelmo Pontes de; BARROS, Ana Luiza Bessa de Paula; SILVA, Thalyson Gomes Nepomuceno da.
Modelos de Classificação de Imagens Empregando Projeto Automático de Redes Neurais Convolucionais com Algoritmos Evolucionários. In: CONGRESSO LATINO-AMERICANO DE SOFTWARE LIVRE E TECNOLOGIAS ABERTAS (LATINOWARE), 22. , 2025, Foz do Iguaçu/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 465-472.
DOI: https://doi.org/10.5753/latinoware.2025.16482.
