A clustering algorithm by fuzzy rule base and convex-set prototype
碩士 === 國立臺灣科技大學 === 電機工程系 === 89 === In this thesis, we propose an effective clustering method that based on fuzzy rule base and convex-set prototype. We use various measures and fuzzy rule base to determine convex cluster expansion and merging. By heuristics and experiences, we establish the fuzzy...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2001
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/19765156651040464456 |
| Summary: | 碩士 === 國立臺灣科技大學 === 電機工程系 === 89 === In this thesis, we propose an effective clustering method that based on fuzzy rule base and convex-set prototype. We use various measures and fuzzy rule base to determine convex cluster expansion and merging. By heuristics and experiences, we establish the fuzzy rule base. The advantages of the proposed method have threefold: 1) The convex-set prototype is flexible, therefore it is more fittable for various cluster shape; 2) A prior knowledg of the number of clusters in the data set is not necessary; and 3) The fuzzy-rule based clustering is easy to adjust and implement. This algorithm has been implemented, analyzed and tested on nine data sets. This experimental results show that the proposed method has better performance than other fuzzy clustering algorithms.
|
|---|