Granger Causality Analysis based on Neural Networks Architectures for bivariate cases

Alvaro D. Orjuela-Canon, Jan A. Freund, Andres Jutinico, Alexander Cerquera

Resultado de la investigación: Capítulo en Libro/Reporte/ConferenciaContribución a la conferencia

1 Cita (Scopus)

Resumen

This work deals with an analysis of Granger Causality computation based on artificial neural networks, including a nonlinear relation between the involved variables. Information about the training parameters are exhibited in order to visualize how the conditions of the chosen model to obtain the connectivity information depend on the architecture of network. Three chaotic maps with a bivariate case built from two time series were employed to see the effect of training parameters of the models. Nonlinear autoregressive and nonlinear autoregressive with exogenous inputs were used to forecast the time series, and then, obtain the causality information based on differences of errors between both approximations. Results show that the causality computation is sensible to neural network parameters previously untreated in a detailed mode
Idioma originalInglés estadounidense
Título de la publicación alojada2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781728169262
DOI
EstadoPublicada - jul. 24 2020
Evento2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, Reino Unido
Duración: jul. 19 2020jul. 24 2020

Serie de la publicación

NombreProceedings of the International Joint Conference on Neural Networks

Conferencia

Conferencia2020 International Joint Conference on Neural Networks, IJCNN 2020
País/TerritorioReino Unido
CiudadVirtual, Glasgow
Período7/19/207/24/20

Áreas temáticas de ASJC Scopus

  • Software
  • Inteligencia artificial

Palabras claves de autor

  • Concepto
  • autoregressive processes
  • causality
  • neural net architecture
  • time series

Huella

Profundice en los temas de investigación de 'Granger Causality Analysis based on Neural Networks Architectures for bivariate cases'. En conjunto forman una huella única.

Citar esto