Napredna pretraga

Pregled bibliografske jedinice broj: 660621

A Differential Evolution Approach to Dimensionality Reduction for Classification Needs


Martinović, Goran; Bajer, Dražen; Zorić, Bruno
A Differential Evolution Approach to Dimensionality Reduction for Classification Needs // International Journal of Applied Mathematics and Computer Science, 24 (2014), 1; 111-122 doi:10.2478/amcs-2014-0009 (međunarodna recenzija, članak, znanstveni)


Naslov
A Differential Evolution Approach to Dimensionality Reduction for Classification Needs

Autori
Martinović, Goran ; Bajer, Dražen ; Zorić, Bruno

Izvornik
International Journal of Applied Mathematics and Computer Science (1641-876X) 24 (2014), 1; 111-122

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Classification; differential evolution; feature subset selection; k-nearest neighbour algorithm; wrapper method

Sažetak
The feature selection problem often occurs in pattern recognition, and more specific, classification. Although these patterns could contain a large number of features, some of them could prove to be irrelevant, redundant or even detrimental to classification accuracy. Thus, it is important to remove these kinds of features which in turn leads to problem dimensionality reduction and could eventually improve the classification accuracy. In this paper an approach to dimensionality reduction based on differential evolution which represents a wrapper and explores the solution space is presented. The solutions, subsets of the whole feature set, are evaluated using the k-nearest neighbour algorithm. High quality solutions found during execution of the differential evolution fill the archive. A final solution is obtained by conducting k-fold cross validation on the archive solutions and selecting the best. Experimental analysis was conducted on several standard test sets. Classification accuracy of the k-nearest neighbour algorithm using the full feature set and the accuracy of the same algorithm using only the subset provided by the proposed approach and some other optimization algorithms which were used as wrappers are compared. The analysis has shown that the proposed approach successfully determines good feature subsets which may increase classification accuracy.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
165-0361621-2000 - Distribuirano računalno upravljanje u transportu i industrijskim pogonima (Željko Hocenski, )
165-0362980-2002 - Postupci raspoređivanja u samoodrživim raspodijeljenim računalnim sustavima (Goran Martinović, )

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Uključenost u ostale bibliografske baze podataka:


  • ACM DL
  • Adv. Tech. DB with Aerosp.
  • Appl. Mech. Rev.
  • BazTech
  • Compendex
  • Comp. Abs. Int. DB
  • Comp. & Comm. Sec. Abs.
  • Comp. and Inf. Sys. Abs.
  • CI to Stat
  • Current Math. Pub.
  • DBLP CS Bibl.
  • DL Zielona Góra
  • Earthquake Eng. Abs.
  • EBSCO
  • Google Scholar
  • High Tech Res. DB
  • INSPEC
  • JCR/Sci. Ed.
  • Math. Rev.
  • MathSciNet
  • Mech. & Transp. Eng.Abs.
  • Polish D. Math. L.
  • SCI Exp.
  • Scopus
  • Summon
  • Techn. Res. DB
  • VINITI
  • ZB MATH


Citati