Back to Search
Start Over
Mining frequent closed itemsets from a landmark window over online data streams
- Source :
-
Computers & Mathematics with Applications . Mar2009, Vol. 57 Issue 6, p927-936. 10p. - Publication Year :
- 2009
-
Abstract
- Abstract: The frequent closed itemsets determine exactly the complete set of frequent itemsets and are usually much smaller than the later. However, mining frequent closed itemsets from a landmark window over data streams is a challenging problem. To solve the problem, this paper presents a novel algorithm (called FP-CDS) that can capture all frequent closed itemsets and a new storage structure (called FP-CDS tree) that can be dynamically adjusted to reflect the evolution of itemsets’ frequencies over time. A landmark window is divided into several basic windows and these basic windows are used as updating units. Potential frequent closed itemsets in each basic window are mined and stored in FP-CDS tree based on some proposed strategies. Extensive experiments are conducted to validate the proposed method. [Copyright &y& Elsevier]
Details
- Language :
- English
- ISSN :
- 08981221
- Volume :
- 57
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- Computers & Mathematics with Applications
- Publication Type :
- Academic Journal
- Accession number :
- 36810921
- Full Text :
- https://doi.org/10.1016/j.camwa.2008.10.060