Skip to main navigation Skip to search Skip to main content

The data dimensionality reduction in the classification process through greedy backward feature elimination

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

The article presents the author’s algorithm of dimensionality reduction of used data set, realized through Greedy Backward Feature Elimination. Results of the dimensionality reduction are verified in the process of classification for 2 selected data sets. These data sets contain the data for the realization of the multiclass classification. The article presents not only a description of the algorithm but also an example and the results of classification, carried out by selected classifier before and after the process of dimensionality reduction. At the end of article, a summary and the possibility of further work are provided.

Original languageEnglish
Title of host publicationMan-Machine Interactions 5 - 5th International Conference on Man-Machine Interactions, ICMMI 2017
EditorsAleksandra Gruca, Tadeusz Czachorski, Katarzyna Harezlak, Stanislaw Kozielski, Agnieszka Piotrowska, Tadeusz Czachorski
PublisherSpringer Verlag
Pages397-407
Number of pages11
ISBN (Print)9783319677910
DOIs
Publication statusPublished - 2018
Event5th International Conference on Man-Machine Interactions, ICMMI 2017 - Krakow, Poland
Duration: 3 Oct 20176 Oct 2017

Publication series

NameAdvances in Intelligent Systems and Computing
Volume659
ISSN (Print)2194-5357

Conference

Conference5th International Conference on Man-Machine Interactions, ICMMI 2017
Country/TerritoryPoland
CityKrakow
Period3/10/176/10/17

Keywords

  • Algorithm
  • Classification
  • DIGITS
  • Dimensionality reduction
  • Feature selection
  • Kappa
  • Multiclass
  • UCI
  • URBAN
  • WEKA

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Computer Science

Fingerprint

Dive into the research topics of 'The data dimensionality reduction in the classification process through greedy backward feature elimination'. Together they form a unique fingerprint.

Cite this