Title :
Fitting fuzzy measures by linear programming. Programming library fmtools
Author_Institution :
Sch. of Eng. & Inf. Technol., Deakin Univ., Melbourne, VIC
Abstract :
We discuss the problem of learning fuzzy measures from empirical data. Values of the discrete Choquet integral are fitted to the data in the least absolute deviation sense. This problem is solved by linear programming techniques. We consider the cases when the data are given on the numerical and interval scales. An open source programming library which facilitates calculations involving fuzzy measures and their learning from data is presented.
Keywords :
data analysis; fuzzy systems; learning (artificial intelligence); linear programming; discrete Choquet integral; least absolute deviation sense; linear programming; open source programming library; programming library fmtools; Decision making; Expert systems; Fitting; Fuzzy logic; Impedance matching; Least squares methods; Libraries; Linear programming; Open wireless architecture; Quadratic programming;
Conference_Titel :
Fuzzy Systems, 2008. FUZZ-IEEE 2008. (IEEE World Congress on Computational Intelligence). IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-1818-3
Electronic_ISBN :
1098-7584
DOI :
10.1109/FUZZY.2008.4630471
