frbs (version 1.0-0)

frcs: frcs model building

Description

This is the internal function that implements the fuzzy rule-based classification system (frcs) model. Users do not need to call it directly, but just use frbs.learn and predict. This method is suitable only for classification problems.

Usage

frcs(range.data, data.train, label.inp, num.class,
    type.mf)

Arguments

range.data

a matrix(2 x n) containing the range of the normalized data, where n is the number of variables, and first and second rows are the minimum and maximum values, respectively.

data.train

a matrix(m x n) of data for the training process, where m is the number of instances and n is the number of variables; the last column is the output variable.

label.inp

a matrix(1 x n) whose elements represent the number of labels (fuzzy terms), where n is the number of variables.

num.class

an integer number representing the number of labels (fuzzy terms).

type.mf

the type of the shape of the membership functions.

Details

This method is adopted from Hisao Ishibuchi and Tomoharu Nakashima's paper and Oscar Cordon, Maria Jose del Jesus and Francisco Herrera's paper. The difference of a usual FRBS and this method is on the consequent part. The consequent part of frcs is a class with a certainty grade (i.e. rule weight). This method uses the techniques of Wang and Mendel for determining the antecedent part. Whereas on the consequent part, the value is associated to a class of the training data. After getting the fuzzy IF-THEN rules, we calculate a certainty grade (CF) for each rule. The prediction phase of this model is conducted by the internal function frcs.eng.

References

Hisao Ishibuchi and Takashi Yamamoto, "Rule weight specification in fuzzy rule-based classification systems," IEEE Transactions on Fuzzy Systems, Vol. 13, No. 4 (2005).

Hisao Ishibuchi and Tomoharu Nakashima, "Effect of rule weights in fuzzy rule-based classification systems", IEEE Transactions on Fuzzy Systems, Vol. 9, No. 4 (2001).

Oscar Cordon, Maria Jose del Jesus and Francisco Herrera, "A proposal on reasoning methods in fuzzy rule-based classification systems", International Journal of Approximate Reasoning 20, pp. 21 - 45 (1999).

Tomoharu N., Yasuyuki Y., Hisao Isibuchi, "Learning fuzzy IF-THEN rules for pattern classification with weighted training patterns," Proceedings of Joint 4th Conference of the European Society for Fuzzy Logic and Technology and the 11th Rencontres Francophones sur la Logique Floue et ses Applications, (2005).

See Also

frcs.eng, frbs.learn, and predict