We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Analysis of tree-based uncertain frequent pattern mining techniques without pattern losses.
- Authors
Lee, Gangin; Yun, Unil; Lee, Kyung-Min
- 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.
- Subjects
PERFORMANCE of supercomputers; TELNET (Computer network protocol); INTRANETS (Computer networks); DATA mining; PERFORMANCE evaluation
- Publication
Journal of Supercomputing, 2016, Vol 72, Issue 11, p4296
- ISSN
0920-8542
- Publication type
Article
- DOI
10.1007/s11227-016-1847-z