[Back to Results | New Search]

URN	etd-0630113-100203
Author	Chien-Hung Tung
Author's Email Address	No Public.
Statistics	This thesis had been viewed 5576 times. Download 0 times.
Department	Computer Science and Engineering
Year	2012
Semester	2
Degree	Master
Type of Document
Language	zh-TW.Big5 Chinese
Title	An Elastic Net Algorithm for Clustering
Date of Defense	2013-07-03
Page Count	52
Keyword	data clustering KGA k-means GKA elastic net non-linearly separable
Abstract	This paper presents an effective elastic net-based clustering algorithm for complex and non-linearly separable data. The basic idea of the proposed algorithm is simple and can be summarized into two steps: (1) assign patterns to groups based on the attraction and tension between the elastic nodes in a ring and the neighbors of the patterns and (2) merge the groups based on the distances between the elastic nodes. 　 　To evaluate the performance of the proposed method, we compare it with several state-of-the-art clustering methods in solving the data clus tering problem. The simulation results show that the proposed algorithm outperforms the other clustering algorithms compared in terms of the accuracy rate. The results also show that the proposed algorithm works well for complex datasets, especially non-linearly separable data.
Advisory Committee	Chu-Sing Yang - chair Tzung-Pei Hong - co-chair Chun-Wei Tsai - co-chair Ming-Chao Chiang - advisor
Files	etd-0630113-100203.pdf Indicate in-campus at 99 year and off-campus access at 99 year.
Date of Submission	2013-07-30

[Back to Results | New Search]