Applied Computational Intelligence in Engineering and Information Technology

Volume 1 of the series Topics in Intelligent Engineering and Informatics pp 83-94

Benchmark Based Comparison of Two Fuzzy Rule Base Optimization Methods

  • Zsolt Csaba JohanyákAffiliated withDepartment of Information Technology, Kecskemét College Email author 
  • , Olga PappAffiliated withDepartment of Information Technology, Kecskemét College

* Final gross prices may vary according to local VAT.

Get Access


Parameter optimization is a key step during the creation of a fuzzy rule based system. It also has a determining effect on the resulting system’s performance. In this chapter, we examine the performance of several fuzzy systems obtained by applying two different optimization methods. In each case we start from an initial rule base that is created using fuzzy c-means clustering of a sample data set. The first examined optimization approach is the cross-entropy method while the second one is a hill-climbing based technique. We compare them in case of four benchmarking problems.