Evoluindo Arquiteturas para Previsão de Séries Temporais via Neuroevolução Gramatical
Resumo
Este trabalho apresenta a SANDL (Structured Artificial Neural Network Definition Language), uma linguagem declarativa e hierárquica para descrever arquiteturas de redes neurais artificiais. A partir dessa linguagem, propõe-se um sistema de Grammatical Neuroevolution (GNE) para projetar e otimizar automaticamente arquiteturas voltadas à previsão de séries temporais multivariadas, substituindo o projeto manual por um processo de descoberta automatizado. Avaliada em um conjunto sintético de séries temporais multivariadas, a abordagem superou um modelo estatístico tradicional, gerando arquiteturas eficientes e adaptadas a dependências complexas.Referências
Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Elsken, T., Metzen, J. H., and Hutter, F. (2019). Neural architecture search: A survey. Journal of Machine Learning Research, 20(55):1–21.
Galván, E. and Mooney, P. (2021). Neuroevolution in deep neural networks: Current trends and future challenges. IEEE Transactions on Artificial Intelligence, 2(6):476–493.
Khalid, A. and Sarwat, A. I. (2021). Unified univariate-neural network models for lithium-ion battery state-of-charge forecasting using minimized akaike information criterion algorithm. Ieee Access, 9:39154–39170.
Lim, B. and Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209.
Sivadasan, E., Sundaram, N. M., and Santhosh, R. (2025). Deep learning for energy forecasting using gated recurrent units and long short-term memory. Journal of Intelligent Systems & Internet of Things, 14(1).
Soltanian, K., Ebnenasir, A., and Afsharchi, M. (2022). Modular grammatical evolution for the generation of artificial neural networks. Evolutionary computation, 30(2):291–327.
Stanley, K. O., Clune, J., Lehman, J., and Miikkulainen, R. (2019). Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1):24–35.
Wang, H., Lei, Z., Zhang, X., Zhou, B., and Peng, J. (2019). A review of deep learning for renewable energy forecasting. Energy Conversion and Management, 198:111799.
Winter, B. D. and Teahan, W. J. (2025). Task-specific activation functions for neuroevolution using grammatical evolution. arXiv:cs.NE,e2503.10879.
Elsken, T., Metzen, J. H., and Hutter, F. (2019). Neural architecture search: A survey. Journal of Machine Learning Research, 20(55):1–21.
Galván, E. and Mooney, P. (2021). Neuroevolution in deep neural networks: Current trends and future challenges. IEEE Transactions on Artificial Intelligence, 2(6):476–493.
Khalid, A. and Sarwat, A. I. (2021). Unified univariate-neural network models for lithium-ion battery state-of-charge forecasting using minimized akaike information criterion algorithm. Ieee Access, 9:39154–39170.
Lim, B. and Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209.
Sivadasan, E., Sundaram, N. M., and Santhosh, R. (2025). Deep learning for energy forecasting using gated recurrent units and long short-term memory. Journal of Intelligent Systems & Internet of Things, 14(1).
Soltanian, K., Ebnenasir, A., and Afsharchi, M. (2022). Modular grammatical evolution for the generation of artificial neural networks. Evolutionary computation, 30(2):291–327.
Stanley, K. O., Clune, J., Lehman, J., and Miikkulainen, R. (2019). Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1):24–35.
Wang, H., Lei, Z., Zhang, X., Zhou, B., and Peng, J. (2019). A review of deep learning for renewable energy forecasting. Energy Conversion and Management, 198:111799.
Winter, B. D. and Teahan, W. J. (2025). Task-specific activation functions for neuroevolution using grammatical evolution. arXiv:cs.NE,e2503.10879.
Publicado
16/10/2025
Como Citar
ANDRADE, Jefferson O.; OLIVEIRA, Heitor M. de; CORONEL, Caio Cesar O.; SANTOS, Luiz Felipe E. dos; KOMATI, Karin S..
Evoluindo Arquiteturas para Previsão de Séries Temporais via Neuroevolução Gramatical. In: ESCOLA REGIONAL DE INFORMÁTICA DO ESPÍRITO SANTO (ERI-ES), 10. , 2025, Espírito Santo/ES.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 51-60.
DOI: https://doi.org/10.5753/eries.2025.15990.
