Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

IWANN
2005
Springer

favoriteEmaildiscussreport

140views Neural Networks» more IWANN 2005»

Direct and Recursive Prediction of Time Series Using Mutual Information Selection

13 years 9 months ago

Direct and Recursive Prediction of Time Series Using Mutual Information Selection

Download www.cis.hut.fi

Abstract. This paper presents a comparison between direct and recursive prediction strategies. In order to perform the input selection, an approach based on mutual information is used. The mutual information is computed between all the possible input sets and the outputs. Least Squares Support Vector Machines are used as non-linear models to avoid local minima problems. Results are illustrated on the Poland electricity load benchmark and they show the superiority of the direct prediction strategy.

Yongnan Ji, Jin Hao, Nima Reyhani, Amaury Lendasse

Real-time Traffic

IWANN 2005 | Mutual Information | Possible Input Sets | Recursive Prediction Strategies |

claim paper

Related Content

» Mutual Information and kNearest Neighbors Approximator for Time Series Prediction

» Methodology for longterm prediction of time series

» Time series prediction using DirRec strategy

» MULP A MultiLayer Perceptron Application to LongTerm OutofSample Time Series Prediction

» Causality analysis of LFPs in microelectrode arrays based on mutual information

» Lag selection for regression models using highdimensional mutual information

» A Feature Selection Method for Air Quality Forecasting

» Representing Image Search Performance Using Time Series Models

» PAQ Time Series Forecasting for Approximate Query Answering in Sensor Networks

Post Info
More Details (n/a)

Added	28 Jun 2010
Updated	28 Jun 2010
Type	Conference
Year	2005
Where	IWANN
Authors	Yongnan Ji, Jin Hao, Nima Reyhani, Amaury Lendasse

Comments (0)