Application of the fuzzy min-max neural network classifier to problems with continuous and discrete attributes

The fuzzy min-max classification network constitutes a promising pattern recognition approach that is based on hyberbox fuzzy sets and can be incrementally trained requiring only one pass through the training set. The definition and operation of the model considers only attributes assuming continuous values. Therefore, the application of the fuzzy min-max network to a problem with continuous and discrete attributes, requires the modification of its definition and operation in order to deal with the discrete dimensions. Experimental results using the modified model on a difficult pattern recognition problem establishes the strengths and weaknesses of the proposed approach