This paper is concerned with a method for multiple attribute decision making under fuzzy environment, in which the preference values take the form of triangular fuzzy numbers. Based on the idea that the attribute with a larger deviation value among alternatives should be assessed a larger weight, a
On the handling of fuzziness for continuous-valued attributes in decision tree generation
โ Scribed by Wang Xizhao; Jiarong Hong
- Publisher
- Elsevier Science
- Year
- 1998
- Tongue
- English
- Weight
- 603 KB
- Volume
- 99
- Category
- Article
- ISSN
- 0165-0114
No coin nor oath required. For personal study only.
โฆ Synopsis
In this paper, fuzziness existing in the process of generating decision trees by discretizing continuous-valued attributes is considered. In a sense a better way to express this fuzziness via fuzzy numbers is presented using possibility theory. The fact that selection of membership functions in a class of symmetric distributions does not influence the decision tree generation is proved. The validity of using the tree to classify future examples is explained. On the basis of likelihood possibility maximization, the existing algorithm is revised. The revised algorithm leads to more reasonable and more natural decision trees.
๐ SIMILAR VOLUMES
By personal inventory decisions we mean the decisions on quantity purchased which are made daily in such activities as grocery shopping. This topic has previously been introduced only at the conceptual level. Hence our main purpose is to provide a quantitative discussion. Some specific models are pu
In science and engineering, there are ''paradoxical'' cases in which we have some ลฝ arguments in favor of some statement A so the degree to which A is known to be true is ลฝ . . positive nonzero , and we have some arguments in favor of its negation ! A, and we do not have enough information to tell w
In this paper, the population attributable fraction is studied using the potential responses framework of Rubin's causal model. This framework facilitates de"nition of a general measure of population attributable e!ect which can accommodate many-valued and multivariate exposures as well as many-valu