Publication result detail

Comparison of stability measures for feature selection

DROTÁR, P.; SMÉKAL, Z.

Original Title

Comparison of stability measures for feature selection

English Title

Comparison of stability measures for feature selection

Type

Paper in proceedings (conference paper)

Original Abstract

The feature selection is inevitable part of machine learning techniques in biomedical engineering and bioinformatics. Feature selection methods are used to select the most discriminative features, e.g. for disease classification. even if there are plenty of feature selection methods the stability of these algorithms is still open question. Another issue with assessing stability of feature selection is that there are several stability measures providing different views on stability.

English abstract

The feature selection is inevitable part of machine learning techniques in biomedical engineering and bioinformatics. Feature selection methods are used to select the most discriminative features, e.g. for disease classification. even if there are plenty of feature selection methods the stability of these algorithms is still open question. Another issue with assessing stability of feature selection is that there are several stability measures providing different views on stability.

Keywords

feature selection, feature selection stability, bioinformatics, machine learning

Key words in English

feature selection, feature selection stability, bioinformatics, machine learning

Authors

DROTÁR, P.; SMÉKAL, Z.

RIV year

2016

Released

22.01.2015

Publisher

IEEE

Location

USA

ISBN

978-1-4799-8220-2

Book

IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2015

Pages from

71

Pages to

75

Pages count

5

URL

BibTex

@inproceedings{BUT114023,
  author="Peter {Drotár} and Zdeněk {Smékal}",
  title="Comparison of stability measures for feature selection",
  booktitle="IEEE 13th International Symposium on Applied Machine Intelligence and Informatics (SAMI), 2015",
  year="2015",
  pages="71--75",
  publisher="IEEE",
  address="USA",
  doi="10.1109/SAMI.2015.7061849",
  isbn="978-1-4799-8220-2",
  url="https://ieeexplore.ieee.org/document/7061849"
}