Parallel Frequent Correlated Pattern Mining Using Time Series Data
Ramachandra V. Pujeri
Since, extraction of frequent itemsets from transaction database is crucial to several data mining task such as association rule generation, so frequent itemset mining is one of the most important concepts in data mining. Frequent pattern mining has been widely used for discovering association and correlation among real data sets. However, discovering interesting correlation among frequent periodic patterns is more complicated and majority of them are unnecessary or uninformative. Researchers designed an algorithm that uses FP-tree for finding periodicity and correlation among multiple longest common substrings in time series data. Researchers introduce a parallel version of the algorithm called Frequent Correlated Periodic Pattern Mining algorithm which takes O(kN) for finding periodicity and tested on a coarse-grained multi-computer (BSP/CGM) Model with synthetic and real data sets. The experiment results show that algorithm is noise resilient, efficient and scalable than existing techniques.