Multi-objective feature selection in music genre and style recognition tasks

Vatolkin I., Preuß M., Rudolph G.


Abstract
Feature selection is an important prerequisite for music classification which in turn is becoming more and more ubiquitous since entering the digital music age. Automated classification into genres or even personal categories is currently envisioned even for standard mobile devices. However, classifiers often fail to work well with all available features, and simple greedy methods often fail to select good feature sets, making feature selection for music classification a natural field of application for evolutionary approaches in general, and multi-objective evolutionary algorithms in particular. In this work, we study the potential of applying such a multi-objective evolutionary optimization algorithm for feature selection with different objective sets. The result is promising, thus calling for deeper investigations of this approach. Copyright 2011 ACM.

Keywords
Feature selection; Multi-objective optimization of data mining; Music information retrieval



Publication type
Conference Paper

Peer reviewed
Yes

Publication status
Published

Year
2011

Conference
13th Annual Genetic and Evolutionary Computation Conference, GECCO'11

Venue
Dublin, irl

Start page
411

End page
418

Pages range
411-418

Volume
null

Language
English

ISBN
9781450305570

DOI

Full text

Affiliation
Universitat Dortmund