New Fuzzy-Number Similarity Measures and Prioritized Information Fusion Mechanisms for Fuzzy Recommendation Problems.
| Autor: | Hsiao-Wei Kao, 高曉薇 |
|---|---|
| Rok vydání: | 2010 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 98 In this thesis, we propose a new method for measuring the degree of similarity between generalized fuzzy numbers based on standard deviation. Some properties of the proposed similarity measure are demonstrated, and 44 sets of generalized fuzzy numbers are applied to compare the proposed method with existing similarity measures. Furthermore, the proposed similarity measure is used to solve fuzzy recommendation problems. A decision maker’s evaluations of parameters or variables involve with real-world problems that can be represented by interval-valued fuzzy numbers. Therefore, we also present a new similarity measured method that based on the standard deviation operator to solve before similarity measurement between interval-valued fuzzy numbers. In addition, some properties of the proposed similarity measure have been demonstrated, and 17 sets of interval-valued fuzzy numbers are adopted to compare the proposed method with existing similarity measures. Furthermore, the proposed similarity measure is used to deal with fuzzy recommendation problems. Chen and Chen [23] and Hong et. al [40] presented new prioritized information fusion algorithm for handling fuzzy information retrieval problems. However, according to our research, these algorithms still have the following drawbacks. Thence, we present a new prioritized information fusion algorithm based on based on GMA operator and fuzzy-number similarity measure to deal with prioritized multi-criteria fuzzy decision-making problems and prioritized information filtering problems based on generalized fuzzy numbers. However, some researchers have pointed out that using interval-valued fuzzy numbers for representing linguistic terms improves flexibility. Thence, we also present a new prioritized information fusion algorithm for handling information filtering problems based on interval-valued fuzzy numbers. Furthermore, we use the proposed fusion algorithm for handling information filtering problems. The proposed prioritized information fusion algorithm can deal with information filtering problems in a more flexible manner. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|