Influence of the GMDH neural network data preparation method on UTC(PL) correction prediction results

• Autorzy: Miczulski W. , Sobolewski Ł.
• Języki publikacji: EN

Abstrakty

EN

The article presents results of the influence of the GMDH (Group Method of Data Handling) neural network input data preparation method on the results of predicting corrections for the Polish timescale UTC(PL). Prediction of corrections was carried out using two methods, time series analysis and regression. As appropriate to these methods, the input data was prepared based on two time series, ts1 and ts2. The implemented research concerned the designation of the prediction errors on certain days of the forecast and the influence of the quantity of data on the prediction error. The obtained results indicate that in the case of the GMDH neural network the best quality of forecasting for UTC(PL) can be obtained using the time-series analysis method. The prediction errors obtained did not exceed the value of š 8 ns, which confirms the possibility of maintaining the Polish timescale at a high level of compliance with the UTC.

Słowa kluczowe

EN

GMDH neural network; national timescale; atomic clock; time series analysis

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2012
• Tom: Vol. 19, nr 1
• Strony: 123--132
• Opis fizyczny: Bibliogr. 6 poz., rys., tab., wykr.

Twórcy

autor

Miczulski W.

autor

Sobolewski Ł.

• University of Zielona Góra, Faculty of Electrical Engineering, Computer Science and Telecommunications, Institute of Electrical Metrology, ul. Podgórna 50, 65-246 Zielona Góra, Poland,

Bibliografia

• [1] Czubla, A., Konopka, J., Nawrocki, J. (2006). Realization of atomic SI second definition in context UTC(PL) and TA(PL). Metrology and Measurement Systems, 2, 149-159.
• [2] Panfilo, G., Tavella, P. (2008). Atomic clock prediction based on stochastic differential equations. Metrology, 45, 108-116.
• [3] Bernier, L.G. (2003). Use of the Allan Deviation and Linear Prediction for the Determination of the Uncertainty on Time Calibrations Against Predicted Timescales. IEEE Transactions on Instrumentation and Measurement, 52(2), 483-486.
• [4] Miczulski, W., Cepowski, M. (2010). Influence of type of neural network and selection of data preprocessing method on UTC-UTC(PL) prediction result. The Measurements, Automation and Monitoring, 11, 1330-1332. (in Polish)
• [5] Farlow, S.J. (1984). Self-organizing Methods in Modelling: GMDH-type Algorithms, 54, New York: Marcel Dekker Inc.
• [6] Masters, T. (1993). Practical neural networks recipes in C++. Academic Press, Inc.