Please use this identifier to cite or link to this item:
https://elib.bsu.by/handle/123456789/158764| Title: | Reduction of feature space dimension based on separability criterion |
| Authors: | Nemirko, A. |
| Keywords: | ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика ЭБ БГУ::ОБЩЕСТВЕННЫЕ НАУКИ::Информатика ЭБ БГУ::ТЕХНИЧЕСКИЕ И ПРИКЛАДНЫЕ НАУКИ. ОТРАСЛИ ЭКОНОМИКИ::Медицина и здравоохранение |
| Issue Date: | 2016 |
| Publisher: | Minsk: Publishing Center of BSU |
| Abstract: | Linear transformation of data in multidimensional feature space based on Fisher's criterion is considered. The case of two classes is studied. We derived expressions for recurrent calculation of weight vectors which form new features. Examples offered shows that the newly found features which represent the data more accurately make it possible to achieve linear separability of classes which remains impossible using the technique of principal components and the classic Fisher's linear discriminant. |
| URI: | http://elib.bsu.by/handle/123456789/158764 |
| Appears in Collections: | 2016. PATTERN RECOGNITION AND INFORMATION PROCESSING (PRIP’2016) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Nemirko.pdf | 531,79 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.