Comparison of adaptive algorithms for significant feature selection in neural network based solution of the inverse problem of electrical prospectingстатья

Информация о цитировании статьи получена из Scopus, Web of Science
Дата последнего поиска статьи во внешних источниках: 19 июля 2013 г.

Работа с статьей


[1] Comparison of adaptive algorithms for significant feature selection in neural network based solution of the inverse problem of electrical prospecting / S. Dolenko, A. Guzhva, I. Persiantsev et al. // International Conference on Artificial Neural Networks (ICANN-2009), Part 2. — Vol. 5769 of Lecture Notes in Computer Science. — Springer-Verlag Berlin Heidelberg, 2009. — P. 397–405. One of the important directions of research in geophysical electrical prospecting is solution of inverse problems (IP), in particular, the IP of magnetotellurics - the problem of determining the distribution of electrical conductivity in the thickness of earth by the values of electromagnetic field induced by ionosphere sources, observed on earth surface. Solution of this IP is hampered by very high dimensionality of the input data (в€ј10 3-10 4). Selection of the most significant features for each determined parameter makes it possible to simplify the IP and to increase the precision of its solution. This paper presents a comparison of two modifications of the developed algorithm for multi-step selection of significant features and the results of their application. В© 2009 Springer Berlin Heidelberg. [ DOI ]

Публикация в формате сохранить в файл сохранить в файл сохранить в файл сохранить в файл сохранить в файл сохранить в файл скрыть