Neural network time series prediction based on multilayer perceptron

Oleg Rudenko; Oleksandr Bezsonov; Oleksandr Romanyk

doi:http://dx.doi.org/10.21511/dm.5(1).2019.03

Neural network time series prediction based on multilayer perceptron

Received December 1, 2018;

Accepted December 20, 2018;

Published May 7, 2019
Author(s)

Link to ORCID Index: https://orcid.org/0000-0003-0859-2015

Oleg Rudenko
,

Link to ORCID Index: https://orcid.org/0000-0001-6104-4275

Oleksandr Bezsonov
,

Link to ORCID Index: https://orcid.org/0000-0003-3278-1772

Oleksandr Romanyk
DOI
http://dx.doi.org/10.21511/dm.5(1).2019.03
Article Info
Volume 17 2019, Issue #1, pp. 23-34
TO CITE
Cited by
10 articles

2056 Views
458 Downloads

This work is licensed under a Creative Commons Attribution 4.0 International License

Until recently, the statistical approach was the main technique in solving the prediction problem. In the framework of static models, the tasks of forecasting, the identification of hidden periodicity in data, analysis of dependencies, risk assessment in decision making, and others are solved. The general disadvantage of statistical models is the complexity of choosing the type of the model and selecting its parameters. Computing intelligence methods, among which artificial neural networks should be considered at first, can serve as alternative to statistical methods. The ability of the neural network to comprehensively process information follows from their ability to generalize and isolate hidden dependencies between input and output data. Significant advantage of neural networks is that they are capable of learning and generalizing the accumulated knowledge. The article proposes a method of neural networks training in solving the problem of prediction of the time series. Most of the predictive tasks of the time series are characterized by high levels of nonlinearity and non-stationary, noisiness, irregular trends, jumps, abnormal emissions. In these conditions, rigid statistical assumptions about the properties of the time series often limit the possibilities of classical forecasting methods. The alternative methods to statistical methods can be the methods of computational intelligence, which include artificial neural networks. The simulation results confirmed that the proposed method of training the neural network can significantly improve the prediction accuracy of the time series.

view full abstract

Keywords
activation function, artificial neural network, simulation, time series, training algorithm
JEL Classification (Paper profile tab)
С45
References
41
Tables
0
Figures
1

- Figure 1. Результати моделювання

- Abbas, О. М. (2015). Neural networks in business forecasting. International journal of computer, 19(1), 114-128.
- Abbas, О. М. (2017). Business forecasting among neural networks and statistical methods (120 p.). LAP LAMBERT Academic Publishing.
- Amir, F. A., & Samir, I. S. (1999). A comparison between neural-network forecasting techniques – case study: river flow forecasting. IEEE Transactions on neural networks, 10(2), 402-409.
- Amjady, N., & Keynia, F. (2011). A new neural network approach to short term load forecasting of electrical power systems. Energies, 4(3), 488-503.
- Benesty, J., & Paleologu, C. (2011). On regularization in adaptive filtering. IEEE Transactions on audio, speech, and language processing, 19(6), 1734-1742.
- Bodyanskiy, Y. V., & Rudenko, O. G. (2004). Искусственные нейронные сети: архитектура, обучение, применение [Iskusstvennyye neyronnyye seti: arkhitektura, obucheniye, primeneniye] (372 p.). Kharkov: TELETEKH.
- Boks, D., & Dzhenkins, H. (1974). Анализ временных рядов прогноз и управление [Analiz vremennykh ryadov, prognoz i upravleniye] (406 p.). Moskva: Mir.
- Brown, R. G. (1959). Statistical forecasting for inventory control (232 р.). New York: McGraw-Hill.
- Chen, J.-F., Do, Q. H., Nguyen T. V. A., & Doan T. T. H. (2018). Forecasting monthly electricity demands by wavelet neuro-fuzzy system optimized by heuristic algorithms. Information, 9(31), 15.
- Chernodub, A. M. (2012). Навчання рекурентних нейронних мереж методом псевдорегуляризації для багатокрокового про- гнозування часових рядів [Navchannia rekurentnykh neironnykh merezh metodom psevdorehuliaryzatsii dlia bahatokrokovoho prohnozuvannia chasovykh riadiv]. Matematychni mashyny i systemy, 4, 41-51.
- Dalrymple, D. J. (1987). Sales forecasting practices: results of a united states survey. International journal of forecasting, 3, 379-392.
- Demidenko, Y. Z. (1981). Линейная и нелинейная регрессии [Lineynaya i nelineynaya regressii] (302 p.). Moskva: Finansy i statistika.
- Dogan, E., & Akgungor, A. (2013). Forecasting highway casualties under the effect of railway development policy in Turkey using artificial neural networks. Neural computing and applications, 22, 869-877.
- Eurostat (n.d.).
- Hippert, H. S., Pedreira, C. E., & Souza, R. C. (2001). Neural networks for short-term load forecasting: a review and evaluation. IEEE Transactions on power systems, 16(1), 44-55.
- Holt, C. C. (1957). Forecasting seasonal and trends by exponentially weighted moving averages (ONR Memorandum No. 52) (236 р.). Pittsburgh: Carnegie institute of technology.
- Hoptroff, R. G. (1993). The principles and practice of time series forecasting and business modeling using neural nets. Neural computing & applications, 1(1), 59-66.
- Jerome, T. C., Douglas, R. M, & Atlas, L. E. (1994). Neural networks and robust time series prediction. IEEE Transactions on neural networks, 5(2), 240-254.
- Kandananond, K. (2011). Forecasting electricity demand in thailand with an artificial neural network approach. Energies, 4(8), 1246-1257.
- Kazemi, S. M. R., Hoseini, S., Abbasian-Naghneh, M. M., & Habib, A. R. (2014). An evolutionary-based adaptive neuro-fuzzy inference system for intelligent short-term load forecasting. International transactions in operational research, 21(2), 311-326.
- Khaykin, S. (2006). Нейронные сети: полный курс [Neyronnyye seti: polnyy kurs] (1104 p.). Moskva: Vilyams.
- Klevecka, I. (2008). Pre-processing of input data of neural networks: the case of forecasting telecommunication network traffic. Telektronikk, 3(4), 168-178.
- Kruglov, V. V., & Borisov, V. V. (2002). Искусственные нейронные сети. Теория и практика [Iskusstvennyye neyronnyye seti. Teoriya i praktika] (382 p.). Moskva: Goryachaya liniya-Telekom.
- Ling, S. H., Leung, F. H. F., Lam, H. K., & Tam, P. K. S. (2003). Short-term electric load forecasting based on a neural fuzzy network. IEEE Transactions on industrial electronics, 50(6), 1305-1316.
- Maithili, A., Kumari R. V., & Rajamanickam S. (2012). Neural network towards business forecasting. IOSR Journal of engineering, 2(4), 831-836.
- Makhotilo, K. V. (1998). Разработка методик эволюционного синтеза нейросетевых компонентов систем управления [Razrabotka metodik evolyutsionnogo sinteza neyrosetevykh komponentov sistem upravleniya] (179 p.). Kharkov: Kharkovskiy gosudarstvennyy politekhnicheskiy universitet.
- Mandic, D. P., & Chambers, J. A. (2001). Recurrent neural networks for prediction: learning algorithms, architectures and stability (285 p.). England: John Wiley & Sons.
- Mohsen, H., & Yazdan, S. (2007). Artificial neural network approach for short term load forecasting for Illam region. World academy of science, engineering and technology, 1(4), 667-671.
- Osovskiy, S. (2002). Нейронные сети для обработки информации [Neyronnyye seti dlya obrabotki informatsii] (344 p.). Moskva: Finansy i statistika.
- Palit, A. K., & Popovic D. (2005). Computational intelligence in time series forecasting: theory and engineering applications (372 p.). Berlin: Springer.
- Pliss, I. P., Popov, S. V., & Rybalchenko, T. V. (2008). Нейросетевое прогнозирование нестационарных временных рядов энергопотребления в условиях структурной неопределенности [Neyrosetevoye prognozirovaniye nestatsionarnykh vremennykh ryadov energopotrebleniya v usloviyakh strukturnoy neopredelennosti]. Svitlotekhnika ta elektroenerhetyka, 3, 41-48.
- Raghupathi, W., Schkade L., & Bapi, R. (1991). A neural network application for bankruptcy prediction. In Proceedings of the 24th hawaii international conference on system sciences, 4, 147-155.
- Raybman, N. S., & Chadeyev, V. M. (1966). Адаптивные модели в системах управления [Adaptivnyye modeli v sistemakh upravleniya] (159 p.). Moskva: Sovetstkoye radio.
- Rudenko, O. H., & Bodyanskyy, E. V. (2002). Основы теории искусственных нейронных сетей [Osnovy teorii iskusstvennykh neyronnykh setey] (317 p.). Kharkov: TELETEKH.
- Shumilova, G. P., Gotman, N. E., Startseva, T. B. (2008). Прогнозирование электрических нагрузок при оперативном управлении электроэнергетическими системами на основе нейросетевых структур [Prognozirovaniye elektricheskikh nagruzok pri operativnom upravlenii elektroenergeticheskimi sistemami na osnove neyrosetevykh struktur] (77 p.). Syktyvkar: KNTS UrO RAN.
- Snytyuk, V. E. (2008). Прогнозирование. Модели, методы, алгоритмы [Prognozirovaniye. Modeli, metody, algoritmy] (364 p.). Kiyev: Maklaut.
- Tam, K. Y. (1991). Neural network models and the prediction of bank bankruptcy. Omega, The international journal of management science, 19, 429-445.
- Tikhonov, A. N., & Arsenin, V. Y. (1980). Методы решения некорректных задач [Metody resheniya nekorrektnykh zadach] (223 p.). Moskva: Nauka.
- Tzafestas, S., & Tzafestas, E. (2001). Computational intelligence techniques for short-term electric load forecasting. Journal of intelligent and robotic systems, 3, 7-68
- Yemelyanov, A. O., & Chernetsov, S. A. (2010). Нейросетевое прогнозирование уровня глюкозы в крови для больных инсулино- зависимым диабетом [Neyrosetevoye prognozirovaniye urovnya glyukozy v krovi dlya bolnykh insulinozavisimym diabetom]. In XII Vserossiyskaya nauchno-tekhnicheskaya konferentsiya «Neyroinformatika-2010» (pp. 326-334). Moskva: NIAU MIFI.
- Zhang, G. P. (Ed.) (2004). Neural networks in business forecasting (350 p.). Hershey: Idea Group Publishing.

< Prev Next >

Download Preview

Development Management

Please specify your request here

Neural network time series prediction based on multilayer perceptron

COOKIES
The cookie settings on this website are set to 'allow all cookies' to give you the best experience.

Please specify your request here

Neural network time series prediction based on multilayer perceptron

Identifying explosive behavioral trace in the CNX Nifty Index: a quantum finance approach

Financial sustainability of private higher education institutions: the case of publicly traded educational institutions

Portfolio optimization under mean-CVaR simulation with copulas on the Vietnamese stock exchange

COOKIES The cookie settings on this website are set to 'allow all cookies' to give you the best experience.

COOKIES
The cookie settings on this website are set to 'allow all cookies' to give you the best experience.