Title :
Efficient data-driven modeling with fuzzy relational rule network
Author :
Gaweda, Adam E. ; Zurada, Jacek M. ; Aronhime, Peter B.
Author_Institution :
Dept. of Electr. & Comput. Eng., Louisville Univ., KY, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
An algorithmic approach for efficient identification of a fuzzy relational rule network (FR2N) from data is presented. FR2N uses a relational input partition for human-understandable modeling of linear interactions between the input variables. Mutual subsethood has been used to estimate the optimal interaction structure. An analytical relationship between the mutual subsethood measure and one of the parameters of the membership functions is derived. The use of this relationship results in a dramatic speed-up of the identification process
Keywords :
covariance matrices; fuzzy neural nets; fuzzy set theory; identification; probability; statistical analysis; algorithmic approach; data-driven modelling; fuzzy relational rule network; human-understandable modeling; identification; linear interactions; mutual subsethood; optimal interaction structure; relational input partition; Clustering algorithms; Covariance matrix; Electronic mail; Fuzzy neural networks; Fuzzy sets; Input variables; Linear approximation; Partitioning algorithms; Scattering parameters; Tree graphs;
Conference_Titel :
Fuzzy Systems, 2002. FUZZ-IEEE'02. Proceedings of the 2002 IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7280-8
DOI :
10.1109/FUZZ.2002.1004982
