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

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

Keywords

• electrical engineering
• UTC(k) timescale
• atomic clock
• predicting [UTC - UTC(k)]
• GMDH neural network