Probabilistic Frequent Itemsets Mining Based on Expectation Bound over Uncertain Database

Frequent itemsets discovery is popular in database communities recently. Because real data is often affected by noise, in this paper, we study to find frequent itemsets over probabilistic database under the Possible World Semantics. It is challenging because there may be exponential number of possib...

Full description

Saved in:
Bibliographic Details
Main Authors: Lihai Nie, Zhiyang Li, Heng Qi, Weijiang Liu, Wenyu Qu
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Data mining
Frequency measurement
Itemsets
Probabilistic Frequent Patterns
Probabilistic logic
Semantics
Support expectation bound
Uncertain Database
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Frequent itemsets discovery is popular in database communities recently. Because real data is often affected by noise, in this paper, we study to find frequent itemsets over probabilistic database under the Possible World Semantics. It is challenging because there may be exponential number of possible worlds for probabilistic database. Although several efficient algorithms are proposed in the literature, it is hard to mine frequent itemsets in large uncertain database due to the high time consuming. To address this issue, we propose an efficient algorithm to mine probabilistic frequent itemsets. A pruning strategy is also presented to accelerate the process of generating candidates. Extensive experiments have been done on synthetic and real databases, demonstrating that the proposed method preforms better than state-of-art methods in most cases.
ISSN:2375-527X
DOI:10.1109/ISPAN-FCST-ISCC.2017.92