|
|
|
|
|
Research on Data Mining Technologies for Complicated Attributes Relationship in Digital Library Collections |
|
PP: 1173-1178 |
|
Author(s) |
|
Yumin Zhao,
Zhendong Niu,
Xueping Peng,
|
|
Abstract |
|
We present here the research work on data mining technologies for complicated attributes relationship in digital library
collections. Firstly our work and ideology is introduced as the research background of this paper. Digital library evaluation is an
important topic in information systems domain. We creatively import data mining technologies into it to get an intelligent decision
support. But traditional data prediction algorithm didn’t work well. This is the problem which would be solved in this paper. Secondly
related preliminary research is introduced. We researched on attributes of digital library collections, proposed a parallel discretization
algorithm based on z-score theory, and by the discretization algorithm discovered a complicated condition attribute relation among
attributes, it is the reason why traditional data prediction algorithm didn’t work well. At last a stratified decision tree algorithm for
value prediction about digital collection is put forward as the ultimate solution to solve the problem. Stratified attribute concept is
imported in this algorithm. It can expand the selection of splitting attribute in decision tree from flat information to stereoscopic
information, eliminate the influence of complicated condition attribute relationship, nested use existing decision tree algorithms, and
solve the bottleneck of data mining application in digital library evaluation. |
|
|
|
|
|