Using a Neurofuzzy Approach in a Medical Application

  • Authors:
  • Constantinos Koutsojannis;Ioannis Hatzilygeroudis

  • Affiliations:
  • Department of Computer Engineering & Informatics, School of Engineering, University of Patras, 26500 Rion, Patras, Hellas, Greece;Department of Computer Engineering & Informatics, School of Engineering, University of Patras, 26500 Rion, Patras, Hellas, Greece

  • Venue:
  • KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Today hybrid computing is a popular framework for solving complex problems such as in medical domain. Hybrid intelligent systems are systems that combine two or more intelligent techniques. Medicine and health care are closely related domains, where the types of problems faced are suitable for application of hybrid intelligent techniques. In this paper we present the initial evaluation of FUzzy NEUrule System which is a Neuro Fuzzy approach based on fuzzy Adaline neurons and uses Differential Evolution for optimization of membership functions. According to our previous Neuro-fuzzy approaches and a well-defined hybrid system HYMES, FUNEUS is an attempt to the direction for integration of neural and fuzzy components with Differential evolution. Despite the fact that it remains difficult to compare neurofuzzy systems conceptually and evaluate their performance, early experimental results in a medical database proved a promising performance and the need for further evaluation in other medical applications.