Analysis of tree-based uncertain frequent pattern mining techniques without pattern losses.

Saved in:

Bibliographic Details
Title:	Analysis of tree-based uncertain frequent pattern mining techniques without pattern losses.
Authors:	Lee, Gangin¹ ganginlee@sju.ac.kr, Yun, Unil¹ unilyun@gmail.com, Lee, Kyung-Min² kml@otsc.tamu.edu
Source:	Journal of Supercomputing. Nov2016, Vol. 72 Issue 11, p4296-4318. 23p.
Subjects:	Performance of supercomputers, Telnet (Computer network protocol), Intranets (Computer networks), Data mining, Performance evaluation
Abstract:	Various large-scale data have been generated in a variety of application fields, since the Internet began to be widely used. Accordingly, researchers have developed various data mining methods for pervasive human-centric computing to deal with the data and discover interesting knowledge. Frequent pattern mining is one of the main issues in data mining, which finds meaningful pattern information from databases. In this area, not only precise data but also uncertain data can be generated depending on environments of data generation. Since the concept of uncertain frequent pattern mining was proposed to overcome the limitations of traditional approaches that cannot deal with uncertain data with existential probabilities of items, several relevant methods have been developed. In this paper, we introduce and analyze state-of-the-art methods based on tree structures, and propose a new uncertain frequent pattern mining approach. We also compare algorithm performance and discuss characteristics of them. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Supercomputing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Various large-scale data have been generated in a variety of application fields, since the Internet began to be widely used. Accordingly, researchers have developed various data mining methods for pervasive human-centric computing to deal with the data and discover interesting knowledge. Frequent pattern mining is one of the main issues in data mining, which finds meaningful pattern information from databases. In this area, not only precise data but also uncertain data can be generated depending on environments of data generation. Since the concept of uncertain frequent pattern mining was proposed to overcome the limitations of traditional approaches that cannot deal with uncertain data with existential probabilities of items, several relevant methods have been developed. In this paper, we introduce and analyze state-of-the-art methods based on tree structures, and propose a new uncertain frequent pattern mining approach. We also compare algorithm performance and discuss characteristics of them. [ABSTRACT FROM AUTHOR]
ISSN:	09208542
DOI:	10.1007/s11227-016-1847-z