A New Method for Complexity Reduction of Neuro-fuzzy Systems with Application to Differential Stroke Diagnosis

  • Authors:
  • Krzysztof Cpałka;Olga Rebrova;Leszek Rutkowski

  • Affiliations:
  • Department of Computer Engineering, Czestochowa University of Technology, Poland and Department of Artificial Intelligence, Academy of Humanities and Economics in Łódź, Poland;Institute of Neurology, Russian Academy of Medical Sciences, Russia;Department of Computer Engineering, Czestochowa University of Technology, Poland and Department of Artificial Intelligence, Academy of Humanities and Economics in Łódź, Poland

  • Venue:
  • ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the paper we propose a new method for designing and reduction of neuro-fuzzy systems for stroke diagnosis. The concept of the weighted parameterized triangular norms is applied and neuro-fuzzy systems based on fuzzy S-implications are derived. In subsequent stages we reduce the linguistic model. The results are implemented to solve the problem of stroke diagnosis.