A SURVEY ON DATA PARTITIONING AND CLUSTER ENSEMBLE TECHNIQUES
Journal Title: Elysium Journal of Engineering Research and Management - Year 2016, Vol 4, Issue 6
Abstract
Data mining methods are used to discover the knowledge from the databases. Association rule mining, classification and clustering techniques are applied for the knowledge discovery process. The data clustering method is also called as data partitioning method. The similar data values are partitioned under the clustering process. The data similarity is measured with distance or similarity measures. The data partitioning process is carried out with the partition and hierarchical models. High dimensional data clustering is a complex task. The cluster ensemble approaches are adapted to reduce the complexity level of high dimensional data clustering process. K-means, K- Medoids and Partion around Medoids (PAM) clustering algorithms are applied for the data clustering process. The survey is conducted to analyze the various techniques and cluster ensemble methods. Cluster results evaluation methods are also analyzed in the survey.
Authors and Affiliations
Dennis Ebenezer D, Suganya M.
Keywords
Related Articles
- EP ID EP369371
- DOI -
- Views 96
- Downloads 0
SENSOR BASED AUTHENTICATION USING ACCELEROMETER SENSOR
In Some Application or Web services Password offer their users lots of possibilities and a feeling of freedom. Eventually, this cause some new security threats like Sensitive data might be stolen and abused,...
USER INTEREST FOR PERSONALISED SEARCH BASED ON AUTOMATIC IDENTIFICATION
The quality of several search services on the Internet is enhanced by the personalized web search (PWS). Due to the user’s unwillingness to reveal their individual information, while search has become...
ND-MPR protocol for achieving delay free transmission in MANET
The MANET have the tendency to provide the end to end reliable path and multipath routing. It is important to provide reliable connection for sending data to destination in Mobile Adhoc Network. For achieving better Qo...
AUTOMATED FORMATION OF DOMAIN MODULE FROM PLAIN TEXTBOOKS USING DOM-SORTZE SYSTEM
The uprising of information and communication skills mutually enriches the teaching and learning processes. Expertise-supported learning scheme uses the Domain Module proved to be helpful in many observi...
FiDoop: Parallel Mining of Frequent Item sets Using MapReduce
Due to the exponential increase of real-time data monitoring systems, the extraction of frequent item (Frequent item set mining) set from large uncertain database is the challenging task. The existing parallel mining alg...