Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0226115-171936 Statistics This thesis had been viewed 1061 times. Download 164 times. Author Yu-Cheng Chen Author's Email Address firstname.lastname@example.org Department Information Management Year 2014 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 37 Title Crossover Strategic Particle Swarm Optimization with Local Search for Solving Data Clustering Problem Keyword Particle Swarm Optimization (PSO) Evolution Computing (EC) Swarm Intelligence (SI) Hybrid Algorithm Data Clustering Data Clustering Hybrid Algorithm Swarm Intelligence (SI) Evolution Computing (EC) Particle Swarm Optimization (PSO) Abstract Structured and unstructured data implicitly contain valuable vast information which utilize
Decision Support System (DSS) and prediction data model for Business Intelligence (BI) in
any fields of science and commercial business. Data classification and clustering problem both
are very important research in data-mining technology. This paper aims at data clustering
problem with a hybrid particle swarm algorithm intends to improve its performance. By which
algorithm identifies similar properties or characters of data objects to aggregate different
clusters. Our proposed CSPSO-LS algorithm mainly use PSO as its evolution framework with
strategic crossover operation ideas from Genetic Algorithm, which hybrids Simulated
Annealing Algorithm as local search method for solving data clustering optimization problem.
In our experiments, the 5 datasets which we are intended to use are selected from the real cases
of UCI are easily available at http://archive.ics.uci.edu/ml/datasets.html, in which are 5
different dimensions and numbers of data objects. In experimental results of datasets for
proposed algorithm, we compare with in nearly a decade of researchers, our proposed CSPSOLS
algorithm comes out better performance as results. We also point some discussions and research direction on proposed CSPSO-LS algorithm.
Advisor Committee Huei-Huang Chen - advisor
Yu-Chen Kao - co-chair
Files Date of Defense 2015-01-14 Date of Submission 2015-03-02