Title :
Innovative Design of Adaptive Hierarchical Fuzzy Logic Systems
Author :
Mohammadian, Masoud
Author_Institution :
Sch. of Inf. Sci. & Eng., Univ. of Canberra, ACT
Abstract :
In this paper the supervised and unsupervised fuzzy concept learning using evolutionary algorithms is considered. The paper explores the design and development of hierarchical fuzzy logic systems using an evolutionary algorithm. The development of hierarchical fuzzy logic systems is considered by a new method which determines the number of layers in the hierarchical fuzzy logic system. A hierarchical fuzzy logic system is developed to predict quarterly interest rates in Australia. The advantages and disadvantages of using hierarchical fuzzy logic systems for financial modelling is also considered. Finally evolutionary algorithm is then used to design a fuzzy logic system from a set of data in an unsupervised learning manner. Specifically it´s application to urban traffic control is considered
Keywords :
adaptive systems; economic forecasting; economic indicators; evolutionary computation; fuzzy logic; hierarchical systems; learning (artificial intelligence); adaptive hierarchical fuzzy logic system design; evolutionary algorithm; financial modelling; interest rate prediction; supervised fuzzy concept learning; unsupervised fuzzy concept learning; urban traffic control; Algorithm design and analysis; Australia; Economic indicators; Evolutionary computation; Fuzzy logic; Fuzzy sets; Fuzzy systems; Mathematical model; Predictive models; Unsupervised learning;
Conference_Titel :
Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-7695-2504-0
DOI :
10.1109/CIMCA.2005.1631612