Title :
Fuzzy systems design via ensembles of ANFIS
Author :
Lima, Clodoaldo Ap M ; Coelho, André L V ; Von Zuben, Fernando J.
Author_Institution :
Dept. of Comput. Eng. & Ind. Autom., State Univ. of Campinas, Brazil
fDate :
6/24/1905 12:00:00 AM
Abstract :
Neurofuzzy networks have become a powerful alternative strategy to develop fuzzy systems, since they are capable of learning and providing IF-THEN fuzzy rules in linguistic or explicit form. Amongst such models, ANFIS is recognized as a reference framework, mainly for its flexible and adaptive character. In this paper, we extend ANFIS theory by experimenting with a multi-net approach wherein two or more differently structured ANFIS instances are coupled to play together. Ensembles of ANFIS (E-ANFIS) enhance ANFIS performance skills and alleviate some of its computational bottlenecks. Moreover, they promote the automatic configuration of different ANFIS units and the a posteriori selective combination of their outputs. Experiments conducted to assess E-ANFIS generalization capability are also presented
Keywords :
adaptive systems; fuzzy neural nets; fuzzy systems; generalisation (artificial intelligence); identification; inference mechanisms; learning (artificial intelligence); prediction theory; ANFIS ensembles; adaptive-network-based fuzzy inference system; approximation problems; automatic configuration; fuzzy systems design; generalization capability; identification problems; if-then fuzzy rules; multi-net approach; neurofuzzy networks; prediction problems; selective output combination; Automation; Computer industry; Computer networks; Concurrent computing; Fuzzy reasoning; Fuzzy systems; Neural networks; Power engineering and energy; Power engineering computing; Power system modeling;
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.2002.1005042