Redes neuronales para pronóstico de series de tiempo hidrológicas del Caribe colombiano
Contenido principal de artículos
Palabras clave:
Redes neuronales, Series de tiempo, Series de tiempo hidrológicas, Pronóstico
Resumen
El modelado de series de tiempo hidrológicas ha recibido fuerte atención debido a la necesidad de estudiar el comportamiento de dichas series y predecir su comportamiento futuro. En esta medida las redes neuronales han demostrado ser una herramienta potente para el modelado de series de tiempo debido a sus capacidades de aprendizaje y adaptación que facilita la toma de decisiones asertivas. El objetivo de este artículo es desarrollar un modelo de redes neuronales y analizar su efectividad a la hora de hacer predicciones de la altitud de las olas medidas en seis diferentes puntos del caribe colombiano. La evidencia experimental demuestra que la mejor configuración de modelo de redes neuronales difiere para cada ubicación, no obstante, los niveles de error obtenidos en la predicción son muy precisos.
Citas
1. Hernandez S., Cesar A.; Pedraza M., Luis Fernando; Escobar Diaz, Andres Aplicaciones De Las Series De Tiempo En Modelos De Tráfico Para Una Red De Datos
2. Sánchez, Paola; Velásquez, Juan D. Problemas de investigación en la predicción de series de tiempo con redes neuronales artificiales Revista Avances en Sistemas e Informática, vol. 7, núm. 3, diciembre, 2010, pp. 67-73.
3. C. Montgomery, L. A. Johnson y J. S. Gardiner, Forecasting & Time Series Analysis, Segunda ed., Singapure: Mc-Graw-Hill, Inc., 1990.
4. R. Gençay y T. Liu, Nonlinear mode-lling and prediction with feedforward and recurrent networks, Physica D: Nonlinear Phenomena, vol. 108, nº 1-2, pp. 119-134 , 1997.
5. B. L. Bowerman, R. T. O’Connell y A. Koehler, Forecasting, Time Series, and Regression: An Applied Approach, Cuarta ed., Ohio: Cengage Learning Brooks Cole, 2006.
6. Hornik, K.,Stinchicombe,M., y White, H. 1989.Multilayer eedforward Networks are Universal Approximators. En: Neural Networks, Vol. 2, No. 5, pp. 359¬366.
7. Z. Tang and P. A. Fishwick, “Feedforward Neural Nets as Models for Time Series Forecasting,” ORSA J. Comput., vol. 5, no. 4, pp. 374–385, 1993.
8. Sanchéz, Paola Andrea, José Rafael García González, Carlos Hernán Fajardo-Toro and Paloma María Teresa Martínez Sánchez. "Designing a Neural Network Model for Time Series Forecasting." Theoretical and Applied Mathematics in International Business. IGI Global, 2020. 259-284. doi:10.4018/978-1-5225-8458-2.ch012
9. R. Hafezi, J. Shahrabi, and E. Hadavandi, “A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price,” Appl. Soft Comput. J., vol. 29, pp. 196–210, 2015.
10. Castillo, E., Cobo, A., Gutiérrez, J.M., Pruneda, R.E.: Introducción a las Redes Funcionales con Aplicaciones. Un Nuevo Paradigma Neuronal. Editorial Paraninfo S.A. Madrid. España. pp.5-8; 8-16; 21-24, 30-34, 53-100. (1999)
11. S. Mishra and S. K. Patra, "Short term load forecasting using a novel recurrent neural network," International Journal of Computational Intelligence: Theory and Practice, vol. 4, no. 1, pp. 39-45, 2009.
12. P. Franses and D. Van Dijk, Non-linear time series models in empirical finance. UK: Cambridge University Press, 2000.
13. S. Crone and N. Kourentzes, "Input-variable Specification for Neural Networks - An Analysis of Forecasting low and high Time Series Frequency," Proceedings of the International Joint Conference on Neural Networks, IJCNN’09, p. inress, 2009.
14. I. Kaastra and M. Boyd, "Designing a neural network for forecasting financial and economic series," Neurocomputing, no. 10, pp. 215-236, 1996.
15. K. Hornik, "Approximation capability of multilayer feedforward networks," Neural Networks, vol. 4, pp. 251-257, 1991.
16. K. Hornik, M. Stinchicombe, and H. White, "Multilayer Feedforward Networks are Universal Approximators," Neural Networks, vol. 2, no. 5, pp. 359-366, 1989.
17. D. Srinivasan, A. C. Liew, and C. S. Chang, "A neural network short-term load forecaster," Electric Power Systems Research, vol. 28, p. 227–234, 1994.
18. X. Zhang, "Time series analysis and prediction by neural networks," Optimization Methods and Software, vol. 4, p. 151–170, 1994.
19. D. L. Chester, "Why two hidden layers are better than one?," Proceedings of the International Joint Conference on Neural Networks, p. 1265–1268, 1990.
20. I. Kaastra and M. Boyd, "Designing a neural network for forecasting financial and economic series," Neurocomputing, no. 10, pp. 215-236, 1996.
21. G. Cybenko, "Approximation by superpositions of a sigmoidal function," Mathematics of Control: Signals and Systems, vol. 2, p. 202–314, 1989.
22. J. Zhang, G. G. Walte, Y. Miao, and W. N. Wayne, "Wavelet neural networks for function learning," IEEE Transactions on Signal Processing, vol. 43, no. 6, p. 1485–1497, 1995.
23. C. C. Klimasauskas, "Applying neural networks," in Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance. Chicago: Probus, 1993, pp. 64-65.
24. L. Ait Gougam, M. Tribeche, and F. Mekideche-Chafa, "A systematic investigation of a neural network for function approximation," Neural Networks, vol. 21, pp. 1311-1317, 2008.
25. M. Lehtokangas, "Modelling with constructive backpropagation," Neural Networks, vol. 12, no. 4-5, p. NeuralNetworks, 1999.
26. M. Cottrell, B. Girard, Y. Girard, M. Mangeas, and C. Muller, "Neural modeling for time series: a statistical stepwise method for weight elimination," IEEE Transactions on Neural Networks, vol. 6, no. 6, p. 1355–1364, 1995.
27. D. L. Chester, "Why two hidden layers are better than one?," Proceedings of the International Joint Conference on Neural Networks, p. 1265–1268, 1990.
28. Sánchez, P. A., & García, J. R. (2017). A New Methodology for Neural Network Training Ensures Error Reduction in Time Series Forecasting. Journal of Computational Science, 13(7), 211–217. doi:10.3844/jcssp.2017.211.217
29. Sánchez, P. A., & García, J. R. (2018). Autoregressive Moving Average Recurrent Neural Networks Applied to the Modelling of Colombian Exchange Rate. International Journal of Artificial Intelligence, 16(2), 194–207.
30. A. Viloria and W. Quintero, "Gestión de información sat río Manzanares", Investigación e Innovación en Ingenierías, vol. 4, no. 2, p. 128, 2016. DOI: https://doi.org/10.17081/invinno.4.2.2493
31. A. Jiménez Coronado, "Estrategia de competitividad y emprendimiento, una revisión de la literatura", Investigación e Innovación en Ingenierías, vol. 4, no. 2, p. 104, 2016. DOI: https://doi.org/10.17081/invinno.4.2.2492
32. J. Guillot and A. Viloria, "Estudio Sobre el Abastecimiento Constante de Energía Eólica", Investigación e Innovación en Ingenierías, vol. 3, no. 2, 2015. DOI: https://doi.org/10.17081/invinno.3.2.2028
33. R. Piteres, M. Cabarcas., y H. Gaspar, “El recurso humano factor de competitividad en el sector salud”, Investigación e Innovación en Ingenierías, vol. 6, n°. 1, pp. 93 - 101., 2018 DOI: https://doi.org/10.17081/invinno.6.1.2778
34. C.A. Gutiérrez, R. Almeida., y W. Romero, “Diseño de un modelo de migración acloud computing para entidades públicas de salud”, Investigación e Innovación en Ingenierías, vol. 6, n°. 1, pp. 10 - 26., 2018. DOI: https://doi.org/10.17081/invinno.6.1.2772
2. Sánchez, Paola; Velásquez, Juan D. Problemas de investigación en la predicción de series de tiempo con redes neuronales artificiales Revista Avances en Sistemas e Informática, vol. 7, núm. 3, diciembre, 2010, pp. 67-73.
3. C. Montgomery, L. A. Johnson y J. S. Gardiner, Forecasting & Time Series Analysis, Segunda ed., Singapure: Mc-Graw-Hill, Inc., 1990.
4. R. Gençay y T. Liu, Nonlinear mode-lling and prediction with feedforward and recurrent networks, Physica D: Nonlinear Phenomena, vol. 108, nº 1-2, pp. 119-134 , 1997.
5. B. L. Bowerman, R. T. O’Connell y A. Koehler, Forecasting, Time Series, and Regression: An Applied Approach, Cuarta ed., Ohio: Cengage Learning Brooks Cole, 2006.
6. Hornik, K.,Stinchicombe,M., y White, H. 1989.Multilayer eedforward Networks are Universal Approximators. En: Neural Networks, Vol. 2, No. 5, pp. 359¬366.
7. Z. Tang and P. A. Fishwick, “Feedforward Neural Nets as Models for Time Series Forecasting,” ORSA J. Comput., vol. 5, no. 4, pp. 374–385, 1993.
8. Sanchéz, Paola Andrea, José Rafael García González, Carlos Hernán Fajardo-Toro and Paloma María Teresa Martínez Sánchez. "Designing a Neural Network Model for Time Series Forecasting." Theoretical and Applied Mathematics in International Business. IGI Global, 2020. 259-284. doi:10.4018/978-1-5225-8458-2.ch012
9. R. Hafezi, J. Shahrabi, and E. Hadavandi, “A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price,” Appl. Soft Comput. J., vol. 29, pp. 196–210, 2015.
10. Castillo, E., Cobo, A., Gutiérrez, J.M., Pruneda, R.E.: Introducción a las Redes Funcionales con Aplicaciones. Un Nuevo Paradigma Neuronal. Editorial Paraninfo S.A. Madrid. España. pp.5-8; 8-16; 21-24, 30-34, 53-100. (1999)
11. S. Mishra and S. K. Patra, "Short term load forecasting using a novel recurrent neural network," International Journal of Computational Intelligence: Theory and Practice, vol. 4, no. 1, pp. 39-45, 2009.
12. P. Franses and D. Van Dijk, Non-linear time series models in empirical finance. UK: Cambridge University Press, 2000.
13. S. Crone and N. Kourentzes, "Input-variable Specification for Neural Networks - An Analysis of Forecasting low and high Time Series Frequency," Proceedings of the International Joint Conference on Neural Networks, IJCNN’09, p. inress, 2009.
14. I. Kaastra and M. Boyd, "Designing a neural network for forecasting financial and economic series," Neurocomputing, no. 10, pp. 215-236, 1996.
15. K. Hornik, "Approximation capability of multilayer feedforward networks," Neural Networks, vol. 4, pp. 251-257, 1991.
16. K. Hornik, M. Stinchicombe, and H. White, "Multilayer Feedforward Networks are Universal Approximators," Neural Networks, vol. 2, no. 5, pp. 359-366, 1989.
17. D. Srinivasan, A. C. Liew, and C. S. Chang, "A neural network short-term load forecaster," Electric Power Systems Research, vol. 28, p. 227–234, 1994.
18. X. Zhang, "Time series analysis and prediction by neural networks," Optimization Methods and Software, vol. 4, p. 151–170, 1994.
19. D. L. Chester, "Why two hidden layers are better than one?," Proceedings of the International Joint Conference on Neural Networks, p. 1265–1268, 1990.
20. I. Kaastra and M. Boyd, "Designing a neural network for forecasting financial and economic series," Neurocomputing, no. 10, pp. 215-236, 1996.
21. G. Cybenko, "Approximation by superpositions of a sigmoidal function," Mathematics of Control: Signals and Systems, vol. 2, p. 202–314, 1989.
22. J. Zhang, G. G. Walte, Y. Miao, and W. N. Wayne, "Wavelet neural networks for function learning," IEEE Transactions on Signal Processing, vol. 43, no. 6, p. 1485–1497, 1995.
23. C. C. Klimasauskas, "Applying neural networks," in Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance. Chicago: Probus, 1993, pp. 64-65.
24. L. Ait Gougam, M. Tribeche, and F. Mekideche-Chafa, "A systematic investigation of a neural network for function approximation," Neural Networks, vol. 21, pp. 1311-1317, 2008.
25. M. Lehtokangas, "Modelling with constructive backpropagation," Neural Networks, vol. 12, no. 4-5, p. NeuralNetworks, 1999.
26. M. Cottrell, B. Girard, Y. Girard, M. Mangeas, and C. Muller, "Neural modeling for time series: a statistical stepwise method for weight elimination," IEEE Transactions on Neural Networks, vol. 6, no. 6, p. 1355–1364, 1995.
27. D. L. Chester, "Why two hidden layers are better than one?," Proceedings of the International Joint Conference on Neural Networks, p. 1265–1268, 1990.
28. Sánchez, P. A., & García, J. R. (2017). A New Methodology for Neural Network Training Ensures Error Reduction in Time Series Forecasting. Journal of Computational Science, 13(7), 211–217. doi:10.3844/jcssp.2017.211.217
29. Sánchez, P. A., & García, J. R. (2018). Autoregressive Moving Average Recurrent Neural Networks Applied to the Modelling of Colombian Exchange Rate. International Journal of Artificial Intelligence, 16(2), 194–207.
30. A. Viloria and W. Quintero, "Gestión de información sat río Manzanares", Investigación e Innovación en Ingenierías, vol. 4, no. 2, p. 128, 2016. DOI: https://doi.org/10.17081/invinno.4.2.2493
31. A. Jiménez Coronado, "Estrategia de competitividad y emprendimiento, una revisión de la literatura", Investigación e Innovación en Ingenierías, vol. 4, no. 2, p. 104, 2016. DOI: https://doi.org/10.17081/invinno.4.2.2492
32. J. Guillot and A. Viloria, "Estudio Sobre el Abastecimiento Constante de Energía Eólica", Investigación e Innovación en Ingenierías, vol. 3, no. 2, 2015. DOI: https://doi.org/10.17081/invinno.3.2.2028
33. R. Piteres, M. Cabarcas., y H. Gaspar, “El recurso humano factor de competitividad en el sector salud”, Investigación e Innovación en Ingenierías, vol. 6, n°. 1, pp. 93 - 101., 2018 DOI: https://doi.org/10.17081/invinno.6.1.2778
34. C.A. Gutiérrez, R. Almeida., y W. Romero, “Diseño de un modelo de migración acloud computing para entidades públicas de salud”, Investigación e Innovación en Ingenierías, vol. 6, n°. 1, pp. 10 - 26., 2018. DOI: https://doi.org/10.17081/invinno.6.1.2772
Barra lateral de artículos
Enviado
Mar 18, 2020
Publicado
Jul 1, 2019
Detalles de artículo
Sección
ARTÍCULOS
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.