Artificial Neural Networks Applications for Total Ozone Time Series

Authors:
Beatriz Monge-Sanz;Nicolás Medrano-Marqués
Affiliations:
GDE--Área de Electrónica, Departamento de Ingeniería Electrónica y Comunicaciones, Facultad de Ciencias, Universidad de Zaragoza, Zaragoza, Spain 50009;GDE--Área de Electrónica, Departamento de Ingeniería Electrónica y Comunicaciones, Facultad de Ciencias, Universidad de Zaragoza, Zaragoza, Spain 50009
Venue:
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Year:
2009

Citing 1
Cited 0

Neural Nets for Adaptive Filtering and Adaptive Pattern Recognition

Computer

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.