Optimal rule-based granular systems from data streams

Daniel Leite, Goran Andonovski, Igor Skrjanc, Fernando Gomide

Research output: Contribution to journalArticlepeer-review

28 Scopus citations

Abstract

We introduce an incremental learning method for the optimal construction of rule-based granular systems from numerical data streams. The method is developed within a multiobjective optimization framework considering the specificity of information, model compactness, and variability and granular coverage of the data. We use α-level sets over Gaussian membership functions to set model granularity and operate with hyperrectangular forms of granules in nonstationary environments. The resulting rule-based systems are formed in a formal and systematic fashion. They can be useful in time series modeling, dynamic system identification, predictive analytics, and adaptive control. Precise estimates and enclosures are given by linear piecewise and inclusion functions related to optimal granular mappings.

Original languageEnglish
Article number8691724
Pages (from-to)583-596
Number of pages14
JournalIEEE Transactions on Fuzzy Systems
Volume28
Issue number3
DOIs
StatePublished - Mar 2020
Externally publishedYes

Keywords

  • Adaptive systems
  • evolving systems
  • granular computing
  • information specificity
  • online data stream

Fingerprint

Dive into the research topics of 'Optimal rule-based granular systems from data streams'. Together they form a unique fingerprint.

Cite this