Title :
Fuzzy systems identification with Orthogonal Matching Pursuit
Author :
Shmilovici, Armin ; Maimon, Oded
Author_Institution :
Dept. of Ind. Eng., Tel Aviv Univ., Israel
Abstract :
A recursive algorithm is described for computing the representation of functions with respect to a nonorthogonal and possibly overcomplete dictionary of elementary building blocks. This algorithm, which follows the Orthogonal Matching Pursuit algorithm, is used for the identification of fuzzy systems where the membership functions are the basic building blocks. The algorithm is demonstrated on the identification of the Glycolytic chaotic time series
Keywords :
chaos; fuzzy set theory; fuzzy systems; identification; time series; Glycolytic chaotic time series; Orthogonal Matching Pursuit algorithm; elementary building blocks; function representation; fuzzy systems identification; membership functions; nonorthogonal dictionary; overcomplete dictionary; recursive algorithm; Buildings; Fuzzy sets; Fuzzy systems; Humans; Industrial engineering; Inference algorithms; Matching pursuit algorithms; Postal services; Pursuit algorithms; Uncertainty;
Conference_Titel :
Fuzzy Systems, 1996., Proceedings of the Fifth IEEE International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3645-3
DOI :
10.1109/FUZZY.1996.552777