下載電子全文宣告This thesis is authorized to indicate in-campus access only
You can not download at the moment.
Your IP address is 18.104.22.168
The defense date of the thesis is 2008-08-14
The current date is 2019-05-24
This thesis will be accessible at off-campus not accessible
URN etd-0812108-164612 Statistics This thesis had been viewed 1906 times. Download 23 times. Author Shin-chia Hunag Author's Email Address No Public. Department Computer Science and Enginerring Year 2007 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 68 Title Dynamic Clustering Using Differential Evolution Keyword dynami data clustering differential evolution differential evolution data clustering dynami Abstract Data clustering is one of the important issues on the data mining techniques which is the process of considering as the number of cluster and the center of cluster. Most of data clustering algorithms are prior known of the number of cluster but dynamic clustering is able to find the optimal number of cluster and center of cluster dynamically by algorithms. This research is used differential evolution algorithm to perform data clustering which is called as dynamic clustering using differential evolution (DCDE). This algorithm is accessed the number of cluster of solution vectors first by normal distribution and then updating the center of cluster of every solution vectors by differential evolution. Finally, we combine cluster validity index to estimate the results of dynamic clustering to make the solution vectors move to the optimal number of cluster of the subspace constantly. This paper uses eight artificial data sets and four real-world data sets to test. The experimental results show that DCDE is able to find the accurate number of cluster and better and more stable center of cluster with unknown the accurate number of cluster. Advisor Committee Prof. Jin-Cherng Lin - advisor
Files Date of Defense 2008-07-29 Date of Submission 2008-08-14