|ИВМ СО РАН||Поиск||English|
|Ресурсы :: статьи|
Recovering data gaps through neural network methodsGorban A., Rossiev A.,
Institute of Computational Modeling, Krasnoyarsk, RussiaMakarenko N., Kuandykov Y.,
Institute of Mathematics, Almaty, KazakhstanDergachev V.
Ioffe Physical and Technical Institute, St. Petersburg, Russia
International Journal of Geomagnetism and Aeronomy, 2002, Vol. 3, No. 2, December 2002
AbstractA new method is presented to recover the lost data in geophysical time series. It is clear that gaps in data are a substantial problem in obtaining correct outcomes about phenomenon in time series processing. Moreover, using the data with irregular coarse steps results in the loss of prime information during analysis. We suggest an approach to solving these problems, that is based on the idea of modeling the data with the help of small-dimension manifolds, and it is implemented with the help of a neural network. We use this approach on real data and show its proper use for analyzing time series of cosmogenic isotopes. In addition, multifractal analysis was applied to the recovered 14C concentration in the Earth's atmosphere.
DownloadsFull text of the article (ftp server ICM SB RAS) [pdf, 204 Kb, in english]
|Дата обновления 18/02/2003||Webmaster|