The landscape contest at ICPR 2010

  • Authors:
  • Núria Macià;Tin Kam Ho;Albert Orriols-Puig;Ester Bernadó-Mansilla

  • Affiliations:
  • Grup de Recerca en Sistemes Intel-ligents, La Salle - Universitat Ramon Llull, Barcelona, Spain;Statistics and Learning Research Department, Bell Laboratories, Alcatel-Lucent, Murray Hill, NJ;Grup de Recerca en Sistemes Intel-ligents, La Salle - Universitat Ramon Llull, Barcelona, Spain;Grup de Recerca en Sistemes Intel-ligents, La Salle - Universitat Ramon Llull, Barcelona, Spain

  • Venue:
  • ICPR'10 Proceedings of the 20th International conference on Recognizing patterns in signals, speech, images, and videos
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The landscape contest provides a new and configurable framework to evaluate the robustness of supervised classification techniques and detect their limitations. By means of an evolutionary multiobjective optimization approach, artificial data sets are generated to cover reachable regions in different dimensions of data complexity space. Systematic comparison of a diverse set of classifiers highlights their merits as a function of data complexity. Detailed analysis of their comparative behavior in different regions of the space gives guidance to potential improvements of their performance. In this paper we describe the process of data generation and discuss performances of several well-known classifiers as well as the contestants' classifiers over the obtained data sets.