Weight selection strategies for ordered weighted average based fuzzy rough sets

Sarah Vluymans, Neil MacParthaláin, Chris Cornelis, Yvan Saeys

Research output: Contribution to journalArticlepeer-review

27 Citations (SciVal)
146 Downloads (Pure)

Abstract

Fuzzy rough set theory models both vagueness and indiscernibility in data, which makes it a very useful tool for application to various machine learning tasks. In this paper, we focus on one of its robust generalisations, namely ordered weighted average based fuzzy rough sets. This model uses a weighted approach in the definition of the fuzzy rough operators. Although its efficacy and competitiveness with state-of-the-art machine learning approaches has been well established in several studies, its main drawback is the difficulty in choosing an appropriate weighting scheme. Several options exist and an adequate choice can greatly enhance the suitability of the ordered weighted average based fuzzy rough operators. In this work, we develop a clear strategy for the weighting scheme selection based upon the underlying characteristics of the data. The advantages of the approach are presented in a detailed experimental study focusing. Rather than to propose a classifier, our aim is to present a strategy to select a suitable weighting scheme for ordered weighted average based fuzzy rough sets in general. Our weighting scheme selection process allows users to take full advantage of the versatility offered by this model and performance improvements over the traditional fuzzy rough set approaches
Original languageEnglish
Pages (from-to)155-171
Number of pages17
JournalInformation Sciences
Volume501
Early online date09 Jun 2019
DOIs
Publication statusPublished - 01 Oct 2019

Keywords

  • Fuzzy rough set theory
  • Meta-learning
  • Ordered weighted average

Fingerprint

Dive into the research topics of 'Weight selection strategies for ordered weighted average based fuzzy rough sets'. Together they form a unique fingerprint.

Cite this