Artificial Neural Networks Applications for Total Ozone Time Series

Autor:	Beatriz Monge-Sanz, Nicolás J. Medrano-Marqués
Rok vydání:	2003
Předmět:	Nonlinear system Artificial neural network Series (mathematics) Computer science business.industry Artificial intelligence Total ozone Missing data business Algorithm
Zdroj:	Artificial Neural Nets Problem Solving Methods ISBN: 9783540402114 IWANN (2)
DOI:	10.1007/3-540-44869-1_102
Popis:	One of the main problems that arises when dealing with time series is the existence of missing values which have to be completed previously to every statistical treatment. Here we present several models based on neural networks (NNs) to fill the missing periods of data within a total ozone (TO) time series. These non linear models have been compared with linear techniques and better results are obtained by using the non linear ones. A neural network scheme suitable for TO monthly values prediction is also presented.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::9d1a1a4eff9c6631fb676c0fb97f9465 https://doi.org/10.1007/3-540-44869-1_102 Zobrazit plný text záznamu