Term Prediction

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 108189 Experts worldwide ranked by ideXlab platform

Amaury Lendasse - One of the best experts on this subject based on the ideXlab platform.

  • Methodology for long-Term Prediction of time series
    Neurocomputing, 2007
    Co-Authors: Antti Sorjamaa, Jin Hao, Nima Reyhani, Amaury Lendasse
    Abstract:

    In this paper, a global methodology for the long-Term Prediction of time series is proposed. This methodology combines direct Prediction strategy and sophisticated input selection criteria: k-nearest neighbors approximation method (k-NN), mutual information (MI) and nonparametric noise estimation (NNE). A global input selection strategy that combines forward selection, backward elimination (or pruning) and forward-backward selection is introduced. This methodology is used to optimize the three input selection criteria (k-NN, MI and NNE). The methodology is successfully applied to a real life benchmark: the Poland Electricity Load dataset.

  • Long-Term Prediction of Time Series Using State-Space Models
    Lecture Notes in Computer Science, 2006
    Co-Authors: Elia Liitiäinen, Amaury Lendasse
    Abstract:

    State-space models offer a powerful modelling tool for time series Prediction. However, as most algorithms are not optimized for long-Term Prediction, it may be hard to achieve good Prediction results. In this paper, we investigate Gaussian linear regression filters for parameter estimation in state-space models and we propose new long-Term Prediction strategies. Experiments using the EM-algorithm for training of nonlinear state-space models show that significant improvements are possible with no additional computational cost.

  • ICANN (2) - Long-Term Prediction of time series using state-space models
    Artificial Neural Networks – ICANN 2006, 2006
    Co-Authors: Elia Liitiäinen, Amaury Lendasse
    Abstract:

    State-space models offer a powerful modelling tool for time series Prediction. However, as most algorithms are not optimized for long-Term Prediction, it may be hard to achieve good Prediction results. In this paper, we investigate Gaussian linear regression filters for parameter estimation in state-space models and we propose new long-Term Prediction strategies. Experiments using the EM-algorithm for training of nonlinear state-space models show that significant improvements are possible with no additional computational cost.

In-hwan Yang - One of the best experts on this subject based on the ideXlab platform.

  • uncertainty and updating of long Term Prediction of prestress forces in psc box girder bridges
    Computers & Structures, 2005
    Co-Authors: In-hwan Yang
    Abstract:

    The purpose of the present paper is to propose a method of uncertainty analysis and sensitivity analysis of the effects of creep and shrinkage in prestressed concrete (PSC) box girder bridges. Also, a method to reduce the uncertainty of long-Term Prediction of time-dependent effects due to creep and shrinkage of concrete is developed. The study deals with the uncertainties in the long-Term Prediction of creep and shrinkage effects using sampling method. Partial rank correlation coefficient and standardized rank regression coefficient computed on the ranks of the observations are examined to quantify the sensitivity of the outputs to each of the input variables. Updating of long-Term Prediction is achieved using Bayesian statistical inference. The proposed theory is applied to long-Term Prediction of prestress force of an actual PSC box girder bridge. The numerical results indicate that the creep model uncertainty factor and relative humidity appear to be the most dominant factors with regard to the model output uncertainty. The present study indicates that the width of mean+/-two standard deviation for updated Predictions of prestress forces with nine measurement information is about half of that of mean+/-two standard deviation for prior Prediction of prestress forces. Therefore, the adoption of an approach developed in this study would reduce the uncertainties of Prediction of time-dependent effects due to creep and shrinkage and improve greatly the long-Term serviceability of PSC box girder bridges.

  • Realistic Long-Term Prediction of Prestress Forces in PSC Box Girder Bridges
    Journal of Structural Engineering, 2001
    Co-Authors: In-hwan Yang
    Abstract:

    The purpose of the present paper is to propose a method to give a more accurate Prediction of time-dependent prestress force changes due to creep and shrinkage of concrete in prestressed concrete (PSC) structures. Updating of long-Term Prediction of prestress forces is achieved using Bayesian statistical inference. By Bayesian statistics, prior Predictions of time-dependent effects due to creep and shrinkage of concrete are used with the information obtained from in-site measurements to develop updated Predictions, or posterior Predictions. The prior Prediction contains the uncertainties with regard to creep and shrinkage of concrete. The present study also deals with the uncertainties in the long-Term Prediction of creep and shrinkage effects using a sampling method. The proposed theory is applied to long-Term Prediction of prestress forces of an actual PSC box girder bridge. The present study indicates that the width of mean ± two standard deviation for posterior Predictions of prestress forces with nine measurement information is about half that of mean ± two standard deviation for prior Predictions of prestress forces. Therefore, the present numerical results prove that a more accurate long-Term Prediction of prestress force changes in PSC structures due to creep and shrinkage of concrete can be achieved by employing the proposed method.

M Benghanem - One of the best experts on this subject based on the ideXlab platform.

  • least squares support vector machine for short Term Prediction of meteorological time series
    Theoretical and Applied Climatology, 2013
    Co-Authors: A Mellit, Massi A Pavan, M Benghanem
    Abstract:

    The Prediction of meteorological time series plays very important role in several fields. In this paper, an application of least squares support vector machine (LS-SVM) for short-Term Prediction of meteorological time series (e.g. solar irradiation, air temperature, relative humidity, wind speed, wind direction and pressure) is presented. In order to check the generalization capability of the LS-SVM approach, a K-fold cross-validation and Kolmogorov–Smirnov test have been carried out. A comparison between LS-SVM and different artificial neural network (ANN) architectures (recurrent neural network, multi-layered perceptron, radial basis function and probabilistic neural network) is presented and discussed. The comparison showed that the LS-SVM produced significantly better results than ANN architectures. It also indicates that LS-SVM provides promising results for short-Term Prediction of meteorological data.

Elia Liitiäinen - One of the best experts on this subject based on the ideXlab platform.

  • Long-Term Prediction of Time Series Using State-Space Models
    Lecture Notes in Computer Science, 2006
    Co-Authors: Elia Liitiäinen, Amaury Lendasse
    Abstract:

    State-space models offer a powerful modelling tool for time series Prediction. However, as most algorithms are not optimized for long-Term Prediction, it may be hard to achieve good Prediction results. In this paper, we investigate Gaussian linear regression filters for parameter estimation in state-space models and we propose new long-Term Prediction strategies. Experiments using the EM-algorithm for training of nonlinear state-space models show that significant improvements are possible with no additional computational cost.

  • ICANN (2) - Long-Term Prediction of time series using state-space models
    Artificial Neural Networks – ICANN 2006, 2006
    Co-Authors: Elia Liitiäinen, Amaury Lendasse
    Abstract:

    State-space models offer a powerful modelling tool for time series Prediction. However, as most algorithms are not optimized for long-Term Prediction, it may be hard to achieve good Prediction results. In this paper, we investigate Gaussian linear regression filters for parameter estimation in state-space models and we propose new long-Term Prediction strategies. Experiments using the EM-algorithm for training of nonlinear state-space models show that significant improvements are possible with no additional computational cost.

Yusen Wang - One of the best experts on this subject based on the ideXlab platform.

  • Short-Term Prediction for wind power based on temporal convolutional network
    Energy Reports, 2020
    Co-Authors: Ruijin Zhu, Wenlong Liao, Yusen Wang
    Abstract:

    Abstract The fluctuation and inTermittence of wind power bring great challenges to the operation and control of the distribution network. Accurate short-Term Prediction for wind power is helpful to avoid the risk caused by the uncertainties of wind powers. To improve the accuracy of short-Term Prediction for wind power, the temporal convolutional network (TCN) is proposed in this paper. The proposed method solves the problem of long-Term dependencies and performance degradation of deep convolutional model in sequence Prediction by dilated causal convolutions and residual connections. The simulation results show that the training process of TCN is very stable and it has strong generalization ability. Furthermore, TCN shows higher forecasting accuracy than existing predictors such as the support vector machine, multi-layer perceptron, long short-Term memory network, and gated recurrent unit network.