|
Abstract
|
Article Information:
Performance Comparison of Clustering Techniques
Sambourou Massinanke and Lu Zhimao
Corresponding Author: Sambourou Massinanke
Submitted: January 29, 2013
Accepted: March 14, 2013
Published: February 05, 2014 |
Abstract:
|
Data mining consists to extracting or “mining” information from large quantity of data. Clustering is one of the most significant research areas in the domain of data mining. Clustering signifies making groups of objects founded on their features where the objects of the same groups are similar and those belonging in different groups are not similar. This study reviews two Clustering Algorithms of the representative clustering techniques: K-modes and K-medoids algorithms. The two algorithms are experimented and evaluated on partitioning Y-STR data. All these algorithms are compared according to the following factors: certain number times of run, precision and recall. The global results show that K-mode clustering is better than the k-medoid in clustering Y-STR data.
Key words: Data clustering, k-medoids clustering and data of Y-STR, k-modes clustering, , , ,
|
|
Abstract
|
PDF
|
HTML |
|
Cite this Reference:
Sambourou Massinanke and Lu Zhimao, . Performance Comparison of Clustering Techniques. Research Journal of Applied Sciences, Engineering and Technology, (5): 963-969.
|
|
|
|
 |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
 |
| Information |
|
|
|
|
| Sales & Services |
|
|
|
|
