Zobrazeno 1 - 10
of 16
pro vyhledávání: ''
Autor:
N.N. Karnik, Jerry M. Mendel
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
This paper introduces a robust fuzzy logic system, one that can handle rule uncertainties. We make use of type-2 fuzzy sets for this purpose. The development of a type-2 fuzzy logic system has led to a new operation that we call type-reduction. In th
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
The paper is concerned with fuzzy relational model identification. Two methods are proposed to estimate the parameters of such models. The first one is an optimization based methodology which uses sequential procedures of quadratic programming to ref
Autor:
João Moura Pires, Henri Prade
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
Fuzzy sets naturally model elastic constraints, the fuzzy constraints satisfaction problem (FCSP) enables the introduction of different kinds of flexibility. Levels of priority can be attached to constraints, and satisfaction levels can be fuzzily th
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
We (1996) have previously presented fuzzy rule generation methods by genetic algorithm (GA). In this paper, we propose three methods to determine rule pairs for crossover in GA for fuzzy rules generation in order to improve the search efficiency and
Autor:
Julie A. Dickerson, Jongbae Choi
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
Fuzzy set methods can be used for data fusion of uncertain sensor data. The expected output membership function (EOMF) method computes a fusability measure based on the sensor uncertainty. The EOMF is the expected fuzzy output based on the input data
Autor:
A. Krone, T. Slawinski
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
For complex problems of data-based fuzzy modelling the computing time plays an important role. Thus, reduction of the problem size by restricting the search to promising possibilities is justified. This paper presents a new method for extracting unid
Autor:
Tsau Young Lin
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
Fuzzy set theory on a universe of granules (crisp sets) are considered. In this setting, the grade of a membership can be interpreted in the most elementary fashion. A grade of 1/2 membership means exactly one half of the granule (in a suitable measu
Autor:
Hsin-Hui Lin, Wen-Fung Shaw
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
In traditional surveys, opinions collected from questionnaires are transformed into numeric values. To synthesize the opinions of a group, usually the mean and variance of the numeric ratings are computed. Instead of transforming opinions into number
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
We present an approach to the recognition of partially occluded objects employing fuzzy invariant values and fuzzy if-then-rules, called fuzzy invariant indexing (FII). Compared with traditional invariant indexing, the fuzzy method proposed here offe
Autor:
Joon Hee Han, Tae Yong Kim
Publikováno v:
1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).
Most edge detection methods have parameters (threshold values or standard deviation of Gaussian operator for smoothing) to be set. These parameter values have much influence on the output of the detectors. In this paper, we propose a method of automa