Learning Fuzzy Rule Based Classifier in High Performance Computing Environment

-- An approach to estimate the number of rules by spectral analysis of the training dataset has been recently proposed [1]. This work presents an analysis of such a method in high performance computing environment. Two approaches for parallel implementation of the method were studied considering the structure selection genetic algorithm and the spectral decomposition. The results show that both approaches have allowed to reduce considerably the overall processing time. Keywords -- Fuzzy rule-based classifier; genetic algorithm; spectral clustering; high performance computing.

• Type: Journal
• Year: 2009
• Where: EUSFLAT
• Authors: Vinicius da F. Vieira, Alexandre Evsukoff, Beatriz S. L. P. de Lima, Sylvie Galichet
• Keywords: EUSFLAT 2009, Fuzzy Logic, Fuzzy Rule-based Classifier, Genetic Algorithm, Selection Genetic Algorithm