Font Size: a A A

Vague Clustering Algorithm And Its Application

Posted on:2011-01-09Degree:MasterType:Thesis
Country:ChinaCandidate:L ChenFull Text:PDF
GTID:2208360308471644Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
Since the theory of Fuzzy Sets was proposed by professor L.A.Zadeh, it has been successfully applied in many areas. In the real world, there exists quite most of information that is fuzzy but can not be expressed and processed, by Fuzzy Sets Theory, while Vague Sets can handle and express more fuzzy information. The study of approximate reasoning basedon Vague Sets will provide a new tool to the computer simulation of fuzzy logical and thought reasoning mechanism of human being.In article, the relationship of Vague Set and Fuzzy Set is analyzed and Vague sets and Fuzzy sets into a comparative study of methods. Methods for transforming Vague sets into Fuzzy sets are analyzed to measure Fuzzy information ignorance in this paper. It is found to be a many-to-one mapping relation to transform a vague set into aFuzzy set. Finally, a new transformation method is presented. The relationship between entropy of Vague sets and similarity measures is analyzed. It is found that they are not matched completely. The impact factors of entropy for Vague sets are discussed. A novel definition of entropy isproposed and a new computing method is presented. Some new similarity measures based on entropy between Vague sets are proposed. Compared with existing methods, the method suggested in article can depict the entropy of vague set by the similar degree between its and its complement just as ordinary Fuzzy set.The Fuzzy theory provides a powerful analysis tool for soft classification. It has been used to deal with clustering problems since it was presented. Fuzzy cluster analysis includes two main contents: the cluster algorithm and the similarity measure between two patterns. Finally, Vague similarity matrix is established through applying grey correlation analysis method, and clustering analysis can be processed on the basis of vague similarity matrix. By full useing multi-dimension features of Vague set including negative, the positive and unknown, the clustering analysis method provides a powerful tool to Vague sets applications intelligent information processing and on the pattern recognition.
Keywords/Search Tags:Vague Sets, Transformation method, Vague entropy, Similarity measure, Clustering analyze
PDF Full Text Request
Related items