Completo - Open Access.

Idioma principal | Segundo idioma

USE OF ARTIFICIAL NEURAL NETWORKS FOR MULTILAYER WAVEGUIDE ANALYSIS

USE OF ARTIFICIAL NEURAL NETWORKS FOR MULTILAYER WAVEGUIDE ANALYSIS

Silva Neto, Arlindo José da ; Cerqueira, Roney das Mercês ; Sisnando, Anderson Dourado ;

Completo:

" The need to optimize processes has led to the construction of methods capable of performing tasks with more consistency and accuracy. The present work proposes the optimization of a multilayer waveguide through computational algorithms. Neural Networks were developed with different configurations and trained with different methods: Cross Validation and Standard Training. The architecture consists of 7 inputs parameters and one output, with 3 hidden layers. The neural network with the best performance presented a Mean Square Error of 1.070×10-11, regression 0.999996 and 16.25 seconds of processing, highlighting the Tansig activation function, evaluated as the best function among those used."

Completo:

" The need to optimize processes has led to the construction of methods capable of performing tasks with more consistency and accuracy. The present work proposes the optimization of a multilayer waveguide through computational algorithms. Neural Networks were developed with different configurations and trained with different methods: Cross Validation and Standard Training. The architecture consists of 7 inputs parameters and one output, with 3 hidden layers. The neural network with the best performance presented a Mean Square Error of 1.070×10-11, regression 0.999996 and 16.25 seconds of processing, highlighting the Tansig activation function, evaluated as the best function among those used."

Palavras-chave: Artificial Neural Networks, Multilayer Waveguide, Optimization,

Palavras-chave: Artificial Neural Networks, Multilayer Waveguide, Optimization,

DOI: 10.5151/siintec2024-393211

Referências bibliográficas
  • [1] "1 AGRAWAL, G. P. Sistemas de comunicação por fibra óptica. tradução: José Rodolfo
  • [2] Souza. Rio de Janeiro, Brasil: Elsevier, 2014.
  • [3] 2AL-AMRI, Amal M. Recent Progress in Printed Photonic Devices: A Brief Review of Materials,
  • [4] Devices, and Applications. Polymers, v. 15, n. 15, p. 3234, 2023.
  • [5] 3 LUDERMIR, Teresa Bernarda. Inteligência Artificial e Aprendizado de Máquina: estado atual
  • [6] e tendências. Estudos Avançados, v. 35, n. 101, p. 85–94, 2021.
  • [7] 4 BABICHEVA, Viktoriia E. et al. Finite-width plasmonic waveguides with hyperbolic multilayer
  • [8] cladding. Optics Express, v. 23, n. 8, p. 9681, 2015.
  • [9] 5 HAYKIN, Simon S. Neural networks: Princípios e prática. 2nd eded. Upper Saddle River,
  • [10] N.J: Prentice Hall, 2001.
  • [11] 6 BABICHEVA, Viktoriia E. Long-range propagation of plasmon and phonon polaritons in
  • [12] hyperbolic-metamaterial waveguides. Journal of Optics, v. 19, n. 12, p. 124013, 2017.
  • [13] 7 RODRIGUEZ-ESQUERRE, V. F.; CAETANO DA SILVA, Juarez; LIU, Zhaowei. Propagation
  • [14] properties of metallic dielectric cladded waveguides. In: SPIE NANOSCIENCE +
  • [15] ENGINEERING, 2016, San Diego, California, United States. (Nader Engheta, Mikhail A.
  • [16] Noginov, & Nikolay I. Zheludev, Org.) Anais [...]. San Diego, California, United States: 20
  • [17] p. 99181Z. Disponível em:
  • [18] .
  • [19] Acesso em: 9 ago. 2024.
  • [20] 8 ARAÚJO DE FIGUEIREDO, Davi; RODRIGUEZ-ESQUERRE, Vitaly F.; CAETANO DA
  • [21] SILVA, Juarez. Guided modes analysis in metamaterial bounded optical waveguides. In:
  • [22] METAMATERIALS, METADEVICES, AND METASYSTEMS 2017, 2017, San Diego, United
  • [23] States. (Nader Engheta, Mikhail A. Noginov, & Nikolay I. Zheludev, Org.) Metamaterials,
  • [24] Metadevices, and Metasystems 2017. San Diego, United States: SPIE, 2017. p. 98.
  • [25] Disponível em: . Acesso em: 9 ago. 2024."
Como citar:

Silva Neto, Arlindo José da; Cerqueira, Roney das Mercês; Sisnando, Anderson Dourado; "USE OF ARTIFICIAL NEURAL NETWORKS FOR MULTILAYER WAVEGUIDE ANALYSIS", p. 1204-1210 . In: . São Paulo: Blucher, 2024.
ISSN 2357-7592, DOI 10.5151/siintec2024-393211

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações