Abstract In this paper, we propose a Gated Recurrent Unit(GRU) neural network traffic prediction algorithm based on transfer learning. By introducing two gate structures, such as reset and update gate, the GRU avoids problems of gradient disappearance explosion. It can effectively represent characteristics long correlation traffic, realize expression nonlinear, self-similar, other satellite tra...

In today’s world, using quantitative methods are very important for financial markets forecast, improvement of decisions and investments. In recent years, various time series forecasting methods have been proposed for financial markets forecasting. In each case, the accuracy of time series methods fundamental to make decision and hence the research for improving the effectiveness of forecasting...

The predictability of network traffic is a significant interest in many domains such as congestion control, admission control, and network management. An accurate traffic prediction model should have the ability to capture prominent traffic characteristics, such as long-range dependence (LRD) and self-similarity in the large time scale, multifractal in small time scale. In this paper we propose...

For a multivariate stationary process, we develop explicit representations for the finite predictor coefficient matrices, the finite prediction error covariance matrices and the partial autocorrelation function (PACF) in terms of the Fourier coefficients of its phase function in the spectral domain. The derivation is based on a novel alternating projection technique and the use of the forward a...

A time series of soft X-ray emission observed on 1974-2007 years (GOES) is analyzed. We show that in the periods of high solar activity 1977-1981, 19881992, 1999-2003 the energy statistics of soft X-ray solar flares for class M and C is well described by a FARIMA time series with Pareto innovations. The model is characterized by two effects. One of them is a long-range dependence (longterm memo...

The predictability of network traffic is a significant interest in many domains such as congestion control, admission control, and network management. An accurate traffic prediction model should have the ability to capture prominent traffic characteristics, such as long-range dependence (LRD) and self-similarity in the large time scale, multifractal in small time scale. In this paper we propose...