frbs (version 1.0-0)

WM: WM model building

Description

This is the internal function that implements the model proposed by L.X. Wang and J.M. Mendel. Users do not need to call it directly, but just use frbs.learn and predict

Usage

WM(range.data, data.train, num.labels = 5, type.mf = 3,
    classification = FALSE)

Arguments

range.data

a matrix(2 x n) containing the range of the 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.

num.labels

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

type.mf

the type of the membership function. See frbs.learn.

classification

a boolean representing whether it is a classification problem or not.

Details

The fuzzy rule-based system for learning from L.X. Wang and J.M. Mendel's paper is implemented in this function. For the learning process, there are three stages: Step 1 divides the input and output spaces of the given numerical data into fuzzy regions. Step 2 generates fuzzy IF-THEN rules from the training data. Step 3 determines a degree of each rule. In the prediction phase, there are four steps: fuzzification, checking the rules, inference, and defuzzification.

References

L. X. Wang, "Fuzzy systems are universal approximators," in Proc. IEEE Int. Conf. Fuzzy Systems, San Diego, CA (1992).

L. X. Wang and J.M. Mendel, "Generating fuzzy rule by learning from examples", in Proc. 6th Int. Symp. Intelligent Control (Washington, DC), 1991, pp. 263-268; also IEEE Trans. Syst., Man, Cybern., vol. 22, No. 6, (1992).

L. X. Wang and J. M. Mendel, "Fuzzy basis function, universal approximation, and orthogonal least squares learning," IEEE Int. Conf. Neural Network, vol. 3 no. 5, pp. 807 - 814 (1992).

See Also

frbs.learn, predict and frbs.eng.