Use of Significant Feature Selection Adaptive Algorithms in Neural Network Based Solution of the Inverse Problem of Electrical Prospectingстатья

Дата последнего поиска статьи во внешних источниках: 28 мая 2015 г.

Работа с статьей

[1] Use of significant feature selection adaptive algorithms in neural network based solution of the inverse problem of electrical prospecting / A. G. Guzhva, S. A. Dolenko, E. A. Obornev et al. // 9th International Conference "Pattern Recognition and Image Analysis: New Information Technologies" (PRIA-9-2008): Conference Proceedings. — Vol. 1. — Nizhni Novgorod, 2008. — P. 215–218. 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 (∼10^3-10^4). 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 report presents a developed algorithm for multi-step selection of significant features and the results of its application.

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