Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependency problems. The intuitive explanation for this behavior is that the output memories of a NARX ne...

The present study investigates the prediction efficiency of nonlinear system-identification models, in assessing the behavior of a coupled structure-passive vibration controller. Two system-identification models, including Nonlinear AutoRegresive with eXogenous inputs (NARX) and adaptive neuro-fuzzy inference system (ANFIS), are used to model the behavior of an experimentally scaled three-story...

The paper presents the application of support vector regression (SVR) to accurate forecasting of the tangential displacement of a concrete dam. The SVR nonlinear autoregressive model with exogenous inputs (NARX) was developed and tested using experimental data collected during fourteen years. A total of 573 data were used for training of the SVR model whereas the remaining 156 data were used to...

Great effect of three way catalytic convertor (TWC) performance on oxygen sensor output voltage has made the sensor (located after catalyst) as the main signal in almost all today’s TWC monitoring algorithms. In this paper output voltage of nonlinear oxygen sensor is estimated using a nonlinear autoregressive with exogenous inputs (NARX) model. The estimation uses ECU calculated exhaust gas flo...

This study examines modeling and simulation of the transient thermal behavior of a solar collector adsorber tube. The data used for model setup and validation were taken experimentally during the start-up procedure of a solar collector adsorber tube. ANN models are developed based on the nonlinear autoregressive with exogenous input NARX model and are implemented using the MATLAB® tools includi...

* corresponding author: [email protected] Abstract This paper presents a comparison study between radial basis function neural network (RBFNN), feed forward multilayer perceptron neural network (MLPNN) and adaptive neuro-fuzzy (ANFIS) technique to model the activated sludge process (ASP). All of these techniques are based on the nonlinear autoregressive with eXogenous input (NARX) structure. The...

Foreign exchange market is one of the most complex dynamic market with high volatility, non linear and irregularity. As the globalization spread to the world, exchange rates forecasting become more important and complicated. Many external factors influence its volatility. To forecast the exchange rates, those external variables can be used and usually chosen based on the correlation to the pred...

This paper provides a formulation for using the delta-operator in the modelling of non-linear systems. It is shown that a unique representation of a deterministic non-linear auto-regressive with exogenous input (NARX) model can be obtained for polynomial basis functions using the delta-operator and expressions are derived to convert between the shiftand deltadomain. A delta-NARX model is applie...

This paper describes an approach to predict non-verbal cues from speech-related features. Our previous investigations of audiovisual speech showed that there are strong correlations between the two modalities. In this work we developed two models using different kinds of Recurrent Artificial Neural Networks: Elman and NARX, to predict parameters of activity for head motion using linguistic and ...

Model identification of polynomial NARX models involves a lengthy and computationally intensive procedure for selecting the model structure among a possibly large set of candidate regressors. If the model structure is under-parameterized to reduce the burden of the model selection phase, unsatisfactory results are generally obtained. This inaccuracy problem can be somewhat circumvented by focus...