Multi-objective evolutionary fuzzy systems

  • Authors:

  • Pietro Ducange;Francesco Marcelloni

  • Affiliations:

  • Dipartimento di Ingegneria dell'Informazione, Elettronica, Informatica, Telecomunicazioni, University of Pisa, Pisa, Italy;Dipartimento di Ingegneria dell'Informazione, Elettronica, Informatica, Telecomunicazioni, University of Pisa, Pisa, Italy

  • Venue:
  • WILF'11 Proceedings of the 9th international conference on Fuzzy logic and applications
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Several methods have been proposed to automatically generate fuzzy rule-based systems (FRBSs) from data. At the beginning, the unique objective of these methods was to maximize the accuracy with the result of often neglecting the most distinctive feature of the FRBSs, namely their interpretability. Thus, in the last years, the automatic generation of FRBSs from data has been handled as a multiobjective optimization problem, with accuracy and interpretability as objectives. Multi-objective evolutionary algorithms (MOEAs) have been so often used in this context that the FRBSs generated by exploiting MOEAs have been denoted as multi-objective evolutionary fuzzy systems. In this paper, we introduce a taxonomy of the different approaches which have been proposed in this framework. For each node of the taxonomy, we describe the relevant works pointing out the most interesting features. Finally, we highlight current trends and future directions.