.png){kind=icon}
Return
Mining inter-sequence patterns with Itemset constraints
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-04514-7.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nowadays, raw data is rarely used directly. In real world applications, data is often processed, and the necessary knowledge extracted, depending on the purpose of the user. Applying constraints in pattern mining is a major factor in reducing the resulting patterns to help decision support systems work efficiently. In 2018, a constraint-based approach was developed to discover inter-sequence patterns. However, this method only focused on the constraints with single items. The task of discovering constraint-based inter-sequential patterns is our target in this work. We propose the DBV-ISPMIC algorithm, a DBV-PatternList based structure, for mining inter-sequential patterns with itemset constraints. The proposed algorithm utilizes an organized search tree structure stored as dynamic bit vectors to quickly compute the support of patterns. In addition, we also develop a property and, based on it, an improved algorithm is proposed to reduce checking candidates. Finally, we develop the pDBV-ISPMIC algorithm as a parallel method of the DBV-ISPMIC algorithm. Empirical evaluations show that DBV-ISPMIC has better performance than the post-processing algorithms in experimental databases and pDBV-ISPMIC is better than DBV-ISPMIC with regard to the runtime.
Keywords:
Data mining
Frequent sequence
Frequent inter-sequence
Constraints
Journal
IF:
3.5
Papers:
7.6K
Citations:
1.7W
Organization
Cited Papers
ShareSave
Mining frequent closed inter-sequence patterns efficiently using dynamic bit vectors.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
ShareSaveShareSave
Mining constrained inter-sequence patterns: a novel approach to cope with item constraintsAPPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
ShareSaveShareSaveShareSave
View more