Application of Nonlinear Autoregressive Neural Network with Exogen for Modeling Demographic Dynamics in Large Urban Agglomeration

AUTHOR(S):

Dmitry Tarasov, Alexander Sergeev, Ashat Sydikhov

TITLE

Application of Nonlinear Autoregressive Neural Network with Exogen for Modeling Demographic Dynamics in Large Urban Agglomeration

PDF

ABSTRACT

This work aims to study the possibility of using artificial neural networks (ANN) for the analysis of time series in special fields. The modeling of demographic dynamics of large urban agglomeration by ANN is conducted on the example of the city of Ekaterinburg, Russia. The prognosis of changes in the population and its sex-age composition, as well as the contribution of the migration factor, are carried out with help of a nonlinear autoregressive exogenous neural network from the Matlab package. The deviation of the forecast results from real data is 3%.

KEYWORDS

Artificial neural networks, Time series, Forecasting, Agglomeration, Population, Russia

REFERENCES

[1] Gladyshev AI, Zhukov AO Advantages and disadvantages of simulation modeling using neural networks // Bulletin of the Russian New University. Series: Mathematical modeling in economics and management. 2013. № 4. P. 53- 55.(In Russian. Гладышев А. И., Жуков А. О. Достоинства и недостатки имитационного моделирования с использованием нейронных сетей // Вестник Российского нового университета. Серия: Математическое моделирование в экономике и управлении. 2013. № 4. С. 53– 55).

[2] Vishnevsky A. G. Population of Russia 2009: the seventeenth annual demographic report // National. Issled. University Higher School of Economics. Ed. home of the Higher School of Economics, 2011. 295-303. (In Russian. Вишневский А. Г. Население России 2009: семнадцатый ежегодный демографический доклад // Нац. исслед. ун-т «Высшая школа экономики». Изд. дом Высшей школы экономики, 2011. 295–303).

[3] O. Folorunso, A. T. Akinwale, O. E. Asiribo and T. A. Adeyemo “Population prediction using artificial neural network”, African Journal of Mathematics and Computer Science Research Vol. 3(8), 155–162.

[4] Chao Wang, Runhe Shi, Wei Wei, Chaoshun Liu, Tao Qi, Wei Gao "Population dynamics in Yangtze River delta: a neural-network and spatial statistical analysis," Proc. SPIE 8513, Remote Sensing and Modeling of Ecosystems for Sustainability IX, 85130.

[5] Learning long-term dependencies is not as difficult with NARX networks / L. Tsungan, B. G. Horne, P. Tino, C. L. Giles. Massachusetts Institute of Technology. 1996. Р. 577–582.

[6] Federal State Statistics Service: methodological explanations (In Russian. Федеральная служба государственной статистики: методические пояснения). URL: http://www.gks.ru/freedoc/new_site/population /demo/metod/met-dem.htm (24.04.2014).

Cite this paper

Dmitry Tarasov, Alexander Sergeev, Ashat Sydikhov. (2018) Application of Nonlinear Autoregressive Neural Network with Exogen for Modeling Demographic Dynamics in Large Urban Agglomeration. International Journal of Control Systems and Robotics, 3, 22-25