PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Prediction of corrections for the Polish time scale UTC(PL) using artificial neural networks

Treść / Zawartość
Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
In this paper, the effectiveness of using Artificial Neural Networks (ANNs) for predicting the corrections of the Polish time scale UTC(PL) (Universal Coordinated Time) is presented. In particular, prediction results for the different types of neural networks, i.e., the MLP (MultiLayer Perceprton), the RBF (Radial Basis Function) and the GMDH (Group Method of Data Handling) are shown. The main advantages and disadvantages of using such types of neural networks are discussed. The prediction of corrections is performed using two methods: the time series analysis method and the regression method. The input data were prepared suitable for the above mentioned methods, based on two time series, ts1 and ts2. The designation of prediction errors for specified days and the influence of data quantity for the prediction error are considered. The paper consists of five sections. After Introduction, in Sec. 2, the theoretical background for different types of neural networks is presented. Section 3 shows data preparation for the appropriate type of neural network. The experimental results are presented in Sec. 4. Finally, Sec. 5 concludes the paper.
Rocznik
Strony
589--594
Opis fizyczny
Bibliogr. 21 poz., wykr., tab., rys.
Twórcy
autor
  • Institute of Control and Computation Engineering, University of Zielona Gora, 50 Podgorna St., 65-246 Zielona Gora, Poland
  • Institute of Electrical Metrology, Faculty of Electrical Engineering, Computer Science and Telecommunications, University of Zielona Gora, 50 Podgorna St., 65-246 Zielona Gora, Poland
autor
  • Institute of Electrical Metrology, Faculty of Electrical Engineering, Computer Science and Telecommunications, University of Zielona Gora, 50 Podgorna St., 65-246 Zielona Gora, Poland
autor
  • Institute of Control and Computation Engineering, University of Zielona Gora, 50 Podgorna St., 65-246 Zielona Gora, Poland
Bibliografia
  • [1] W. Miczulski and Ł. Sobolewski, “Influence of the GMDH neural network data preparation method on UTC(PL) correction prediction results”, Metrol. Meas. Syst. 19 (1), 123-132 (2012).
  • [2] A. Czubla, J. Konopka, and J. Nawrocki, “Realization of atomic SI second definition in context UTC(PL) and TA(PL)”, Metrol. Meas. Syst. (2), 149-159 (2006).
  • [3] G. Panfilo and P. Tavella, “Atomic clock prediction based on stochastic differential equations”, Metrology 45, 108-116 (2008).
  • [4] L.G. Bernier, “Use of the Allan deviation and linear prediction for the determination of the uncertainty on time calibrations against predicted timescales”, IEEE Trans. on Instrumentationand Measurement 52 (2), 483-486 (2003).
  • [5] J.A. Davis, S.L. Shemar, and P.B.Whibberley, “A Kalman filter UTC(k) prediction and steering algorithm”, Proc. Joint Conf. IEEE Int. Frequency Control and the Eur. Frequency and TimeForum (FCS) 1, CD-ROM (2011).
  • [6] M. Luzar, A. Czajkowski, M. Witczak, and J. Korbicz, “Actuators and sensors fault diagnosis with dynamic, state-space neural networks”, Proc. 17th Int. Conf. Methods and Modelsin Automation and Robotics 1, CD-ROM (2012).
  • [7] S. Koziel, S. Ogusrtov, and S. Szczepański, “Rapid atenna design optimization using shape-preserving response prediction”, Bull. Pol. Ac.: Tech. 60 (1), 143-149 (2012).
  • [8] J. Stolarek, “Adaptive synthesis of a wavelet transform using fast neural network”, Bull. Pol. Ac.: Tech. 59 (1), 9-13 (2011).
  • [9] J. Gocławski, J. Sekulska-Nalewajko, and E. Kuźniak , “Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses”, Int. J.Applied Mathematics and Computer Science 22 (3), 669-684 (2012).
  • [10] J. Tan, R. Dong, H. Chen, and H. He, “Neural network based identification of hysteresis in human meridian systems”, Int. J. Applied Mathematics and Computer Science 22 (3), 685-694 (2012).
  • [11] M. Mrugalski, “An unscented Kalman filter in designing dynamic GMDH neural networks for robust fault detection”, Int. J. Applied Mathematics and Computer Science 23 (1), 157-169 (2013).
  • [12] W. Miczulski and M. Cepowski, “Influence of type of neural network and selection of data pre-processing method on UTCUTC( PL) prediction result”, Measurements, Automation andMonitoring 11, 1330-1332 (2010).
  • [13] K. Siwek, S. Osowski and R. Szupiluk, “Ensemble neural network approach for accurate load forecasting in a power system”, Int. J. Applied Mathematics and Computer Science 19 (2), 303-315 (2009).
  • [14] S.J. Farlow, Self-organizing Methods in Modelling: GMDHtypeAlgorithms, CRC Press, London, 1984.
  • [15] M. Huk, “Backpropagation generalized delta rule for the selective attention Sigma-if artificial neural network”, Int. J. AppliedMathematics and Computer Science 22 (2), 449-459 (2012).
  • [16] A.G. Ivakhenko and J.A. Mueller, “Self-organizing of nets of active neurons”, System Analysis Modeling Simulation 20, 93-106 (1995).
  • [17] M. Mrugalski, E. Arinton, and J. Korbicz, “Dynamic GMDH type neural-networks”, Proc. 6th Conf. Neural Networks andSoft Computing: NNSC’03 1, 698-703 (2003).
  • [18] W. Duch, J. Korbicz, L. Rutkowski, and R. Tadeusiewicz, Biocybernetics and Biomedical Engineering: Neural Networks, EXIT, Warsaw, 2000, (in Polish).
  • [19] T. Masters, Practical Neural Networks Recipes in C++, Academic Press, New York, 1993.
  • [20] M. Luzar, “GMDH Toolbox for Matlab” (in Polish), Proc. 12th Int. PhD Workshop - OWD 28, 85-90 (2010).
  • [21] M. Luzar, M. Witczak, “A GMDH toolbox for neural networkbased modeling”, Proc. 8th Int. Workshop on Advanced Controland Diagnosis - ACD 1, 202-206 (2010)
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-1f58343d-183e-4cfd-8a0a-1232c44c745d
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.