|
Title:
|
AN APPROACH FOR THE CONCEPTUAL MODELING OF CLUSTERING MINING IN THE KDD PROCESS |
|
Author(s):
|
Jose Zubcoff , Juan Trujillo |
|
ISBN:
|
978-972-8924-40-9 |
|
Editors:
|
Jörg Roth, Jairo Gutiérrez and Ajith P. Abraham (series editors: Piet Kommers, Pedro Isaías and Nian-Shing Chen) |
|
Year:
|
2007 |
|
Edition:
|
Single |
|
Keywords:
|
Clustering, data mining, KDD, conceptual modeling, data warehouse, multidimensional modeling. |
|
Type:
|
Short Paper |
|
First Page:
|
119 |
|
Last Page:
|
123 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Clustering analysis is usually applied as an isolated method to not easily understandable flat files. This approach carries
out three main drawbacks: (i) the pre-processing stage is not reusable between different data mining techniques, (ii) the
analysts must focus on the low-level implementation details, and (iii) the analysts is missing the opportunity of learn
previous knowledge about domain. Data warehousing techniques are widely used to solve the first issue. However, there
is still a lack of methods to accomplish the design of data mining in a suitable manner integrated into the Knowledge
Discovery in Databases (KDD) process. In this paper we propose a conceptual model for Clustering allowing designers to
focus on the data mining domain abstracting from platform specific issues. Furthermore, it reduces developing time and
cost, avoiding duplication of the time-consuming preprocessing steps. In addition, analysts can take advantage of the
previous KDD stages. This is achieved by using an existing model of the data warehouse. In addition, this assures a proof
understanding of data: the more information the user has about the data at hand, the more likely the user would be able to
perform the data mining process. To show the feasibility of this proposal, we have implemented the conceptual modeling
of Clustering in a case study using a commercial database system. |
|
|
|
|
|
|
