Tide variations are affected not only by periodic movement of celestial bodies but also time-varying interference from the external environment. To improve accuracy tide prediction, a modular level prediction model (HA-NARX) is proposed. This divides data into two parts: astronomical tide-generating forces and nonastronomical various environmental factors. Final results obtained using nonlinear...

This paper deals with a new approach to detect the structure (i.e. determination of the number of hidden units) of a feedforward neural network (FNN). This approach is based on the principle that any FNN could be represented by a Volterra series such as a nonlinear inputoutput model. The new proposed algorithm is based on the following three steps: first, we develop the nonlinear activation fun...

We present two new empirical models of radiation belt electron flux at geostationary orbit. GOES-15 measurements 0.8 MeV electrons were used to train a Nonlinear Autoregressive with Exogenous input (NARX) neural network for both modeling values and an upper boundary condition scaling factor (BF). The model utilizes feedback delay 2 time steps (i.e., 5 min steps) the most efficient number hidden...

Estimating and forecasting suspended sediments concentrations in streams constitutes a valuable asset for sustainable land management. This research presents the development of non-linear autoregressive exogenous neural network (NARX) sediment at exit Francia Creek watershed (Valparaiso, Chile). Details are presented on input data selection, splitting, selection model architecture, determinatio...

The extreme values of high tides are generally caused by a combination astronomical and meteorological causes, as well the conformation sea basin. One place where tide have considerable practical interest is city Venice. MOSE (MOdulo Sperimentale Elettromeccanico) system was created to protect Venice from flooding highest tides. Proper operation protection requires an adequate forecast model ti...

The main aim of this paper is to establish a reliable model of a process behavior both for the steady-state and unsteady-state regimes. The use of this accurate model allows distinguishing a normal mode from an abnormal one. Therefore the neural black-box identification by means of a NARX (Nonlinear Auto-Regressive with eXogenous) model has been chosen. It shows the choice and the performance o...

In this paper, the common centralized DEA models are extended to the bi-level centralized resource allocation (CRA) models based on revenue efficiency. Based on the Karush–Kuhn–Tucker (KKT) conditions, the bi-level CRA model is reduced to a one-level mathematical program subject to complementarity constraints (MPCC). A recurrent neural network is developed for solving this one-level mathematica...

This paper deals with the identification of MIMO cement mill process using Non-linear Autoregressive with Exogenous Inputs (NARX) models with wavelet network. NARX identification, based on a sequence of input/output samples, collected from a real cement mill process is used for black-box modeling of non-linear cement mill process. The NARX model is considered for two inputs and two outputs of s...

Representation learning over dynamic graphs has attracted much attention because of its wide applications. Recently, sequential probabilistic generative models have achieved impressive results they can model data distributions. However, modeling the distribution is still extremely challenging. Existing methods usually ignore mutual interference stochastic states and deterministic states. Beside...