The drawback of indirect multi-step-ahead prediction is error accumulation. In order to tackle this problem and improve the capacity of adaptive time delay neural network (ATNN) for prediction, a three-stage prediction model SATNN based on spline interpolation and ATNN is presented. With spline interpolation and ATNN, the impact of last prediction errors that would be iterated into the model fo...

Sea clutter is a kind of ubiquitous interference in sea-detecting radars, which will definitely influence target detection. An accurate sea prediction method supposed to be beneficial while existing methods are based on the one-step-ahead prediction. In this paper, network (SCPNet) proposed achieve k-step-ahead characteristics clutter. The SCPNet takes sequence-to-sequence (Seq2Seq) structure a...

The aim of this paper is to prove the validity of an alternative prediction technique to another classical one, which is Box-Jenkins methodology, in order to produce multivariate prediction. In particular, one-step ahead forecasts will be obtained for two time series: thermic and hydraulic power production. These forecasts are based on the past values of those series.

There exists a wide range of paradigms, and a high number of different methodologies that are applied to the problem of time series prediction. Most of them are presented as a modified function approximation problem using input/output data, in which the input data are expanded using values of the series at previous steps. Thus, the model obtained normally predicts the value of the series at a t...

We consider the problem of multi-step ahead prediction in time series analysis using the non-parametric Gaussian process model. k-step ahead forecasting of a discrete-time nonlinear dynamic system can be performed by doing repeated one-step ahead predictions. For a state-space model of the form yt = f(yt−1, . . . , yt−L), the prediction of y at time t + k is based on the estimates ŷt+k−1, . . ....

[1] Prediction of the solar wind conditions in near-Earth space, arising from both quasi-steady and transient structures, is essential for space weather forecasting. To achieve forecast lead times of a day or more, such predictions must be made on the basis of remote solar observations. A number of empirical prediction schemes have been proposed to forecast the transit time and speed of coronal...

Mobile users typically experience better connectivity if their mobile device performs handover to an available WiFi network rather than using a cellular network. For a moving user the window of opportunity is limited and the timing of the handover is therefore crucial. In this work we propose two location-based look-ahead handover prediction algorithms that are based on the assumption that a da...

This study explores ambient air quality forecasts using the conventional time-series approach and a neural network. Sulfur dioxide and ozone monitoring data collected from two background stations and an industrial station are used. Various learning methods and varied numbers of hidden layer processing units of the neural network model are tested. Results obtained from the time-series and neural...

The paper addresses the problem of designing robust output feedback model predictive control to one-step ahead prediction horizon which ensures a parameter dependent quadratic stability and guaranteed cost for the case of linear polytopic systems.