Extracting Repitative Patterns from Fuzzy Temporal Data

Association rules mining from temporal dataset is to find associations between items that hold within certain time frame but not throughout the dataset. This problem involves first discovering frequent itemsets which are frequent at certain time intervals and then extracting association rules from such frequent itemsets. In practice, we may have datasets having imprecise or fuzzy time attributes, we term such datasets as fuzzy temporal datasets. In such datasets, as the time of transaction is imprecise, we may have frequent itemsets that are frequent in certain fuzzy time intervals. The algorithm [1] finds all such frequent itemsets along with a collection of list of fuzzy time intervals where each frequent itemset is having an associated list of fuzzy time intervals where it is frequent. The list of fuzzy time intervals may show some interesting features e.g. the itemsets may be repetitive in nature. In this paper we propose a method of finding all repetitive frequent itemsets. The method's efficacy is demonstrated with experimental results.