Meteorological time series forecasting with pruned multi-layer perceptron and 2-stage Levenberg-Marquardt method

no code implementations • 8 Jul 2014 • Cyril Voyant, Wani W. Tamas, Marie Laure Nivet, Gilles Notton, Christophe Paoli, Aurélia Balu, Marc Muselli

Then a classical batch process based on LMA is used with the new MLP.

Time Series Time Series Forecasting

Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions

no code implementations • 29 Apr 2014 • Cyril Voyant, Marie Laure Nivet, Christophe Paoli, Marc Muselli, Gilles Notton

In this paper, we propose to study four meteorological and seasonal time series coupled with a multi-layer perceptron (MLP) modeling.

Time Series Time Series Forecasting

Numerical weather prediction or stochastic modeling: an objective criterion of choice for the global radiation forecasting

no code implementations • 22 Jan 2014 • Cyril Voyant, Gilles Notton, Christophe Paoli, Marie Laure Nivet, Marc Muselli, Kahina Dahmani

Numerous methods exist and were developed for global radiation forecasting.

Time series modeling with pruned multi-layer perceptron and 2-stage damped least-squares method

no code implementations • 8 Aug 2013 • Cyril Voyant, Wani W. Tamas, Christophe Paoli, Aurélia Balu, Marc Muselli, Marie Laure Nivet, Gilles Notton

Then a classical batch process based on LMA is used with the new MLP.

Time Series Time Series Analysis

Urban ozone concentration forecasting with artificial neural network in Corsica

no code implementations • 4 Jun 2013 • Wani W. Tamas, Gilles Notton, Christophe Paoli, Cyril Voyant, Marie Laure Nivet, Aurélia Balu

The purpose of this study is to build a predictor to realize predictions of ozone and PM10 at horizon d+1 in Corsica in order to be able to anticipate pollution peak formation and to take appropriated prevention measures.

Clustering