In this paper, we propose some improvements for the problem of time series prediction with neural networks where a medium-term prediction horizon is needed. In particular, the ionospheric prediction service of the french Centre National d' Etudes des T el ecommunica-tions needs a six-month ahead prediction of a sunspots related time series which has a strong innuence on wave propagation in iono...

this paper presents a fuzzy approach to the prediction of highly nonlinear timeseries.the optimized mamdani-type fuzzy system denoted sqp-flc is applied forthe input-output modeling of measured data. in order to tune fuzzy membershipfunctions, a sequential quadratic programming (sqp) method is employed. theproposed method is evaluated and validated on a highly complex time series, dailygold pri...

This paper uses minute-by-minute British electricity demand observations to evaluate methods for prediction from 10 to 30 minutes ahead. Such very short lead times are important for the real-time scheduling of electricity generation. We consider methods designed to capture both the intraday and the intraweek seasonal cycles in the data, including ARIMA modelling, an adaptation of Holt-Winters e...

We introduce and discuss a local method to learn one-step-ahead predictors for iterated time series forecasting. For each single one-step-ahead prediction, our method selects among diierent alternatives a local model representation on the basis of a local cross-validation procedure. In the literature , local learning is generally used for function estimation tasks which do not take temporal beh...

We consider the problem of power demand forecasting in residential micro-grids. Several approaches using ARMA models, support vector machines, and recurrent neural networks that perform one-step ahead predictions have been proposed in the literature. Here, we extend them to perform multi-step ahead forecasting and we compare their performance. Toward this end, we implement a parallel and effici...

We study the predictive power of autoregressive moving average models when forecasting demand in two shared computational networks, PlanetLab and Tycoon. Demand in these networks is very volatile, and predictive techniques to plan usage in advance can improve the performance obtained drastically. Our key finding is that a random walk predictor performs best for one-step-ahead forecasts, whereas...

Predicting accurate trajectories with limited intent information is a challenge faced by air traffic management decision support tools in operation today. One such tool is the FAA’s Terminal Proximity Alert system which is intended to assist controllers in maintaining safe separation of arrival aircraft during final approach. In an effort to improve the performance of such tools, two final appr...

Interpandemic or seasonal influenza A, currently subtypes H3N2 and H1N1, exacts an enormous annual burden both in terms of human health and economic impact. Incidence prediction ahead of season remains a challenge largely because of the virus' antigenic evolution. We propose a forecasting approach that incorporates evolutionary change into a mechanistic epidemiological model. The proposed model...

A simulated annealing (SA) based variable weighted forecast model is proposed to combine and weigh local chaotic model, artificial neural network (ANN), and partial least square support vector machine (PLS-SVM) to build a more accurate forecast model. The hybrid model was built and multistep ahead prediction ability was tested based on daily MSW generation data from Seattle, Washington, the Uni...

A daily peak load forecasting technique that uses artificial neural network presented in this paper. A neural network of used to predict the daily peak load for a period available using one step ahead prediction load to the actual load. The ith index is used as load for the ith day of the year following networks are trained by the back propagation algorithm. from the Nigerian national electric ...