Predicting the Lithuanian Timescale UTC(LT) by means of GMDH neural network

Journal Title: Bulletin of the Military University of Technology - Year 2017, Vol 66, Issue 4

Abstract

The aim of the study is to examine the effectiveness of applying GMDH-type neural network and the developed procedure for predicting UTC(k) timescales, which are characterized with high dynamics of changes of the input data. The research is carried out on the example of the Lithuanian Timescale UTC(LT). The obtained research results have shown that GMDH-type neural network with a developed predicting procedure enables us to receive good prediction results for the UTC(LT). Better prediction quality was obtained using time series which are built only on the basis of deviations determined by the BIPM according to the UTC and UTC Rapid scales. Keywords: electrical engineering, UTC(k) timescale, atomic clock, predicting [UTC – UTC(k)], GMDH neural network

Authors and Affiliations

Łukasz Sobolewski

Keywords

Related Articles

Obrona przed bronią masowego rażenia. Rozwiązania techniczne i funkcjonalne w ochronie indywidualnej w Wojskach Obrony Terytorialnej

W pracy scharakteryzowano obronę przed bronią masowego rażenia, jako system zabezpieczenia wojsk w przypadku zagrożenia skażeniami (zakażeniami) w ujęciu funkcjonalnym i zadaniowym. Przedstawiono podstawowe wyposażenie t...

Main problems of the evaluation and selection of advanced weapon systems exemplified by a multi-role combat aircraft

This paper presents a selection of issues related to the methods of evaluation and selection of advanced weapon systems for armed forces. The paper’s focus is ranking in the form of typical Multidimensional Comparative A...

Collective protection against contamination

The paper describes general rules for the use of collective protection against contamination. There are presented certain recommendations for functional and operational requirements in the case of collective protection m...

Ultra szybkie statyczne pozycjonowanie GNSS z zastosowaniem systemów GPS i Galileo

Środowisko naukowe podejmowało już niejednokrotnie problem łącznego wykorzystania obserwacji z niezależnych systemów GNSS, jednak przedmiotem badań był najczęściej model luźnej integracji. Istnienie dwóch korespondującyc...

New generation concretes including reactive powder concretes

Based on a broad literature review, this paper presents characteristics of new generation composites on the basis of cements which are applied in engineering structures and in rehabilitation of structures. The role of ce...

Download PDF file
  • EP ID EP257247
  • DOI 10.5604/01.3001.0010.8179
  • Views 66
  • Downloads 0

How To Cite

Łukasz Sobolewski (2017). Predicting the Lithuanian Timescale UTC(LT) by means of GMDH neural network. Bulletin of the Military University of Technology, 66(4), 31-41. https://europub.co.uk/articles/-A-257247