The researchers have focused on extracting timeincluded knowledge that reveals the behavior of item sets, such as finding thepatterns that are more present on a specific time period; finding the specifictime points, where the frequency of an item set before or after a time pointincreases or decreases significantly, etc. Many previous works also considerthe time points in Frequent Pattern Mining (FPM) studies and presented temporalmining algorithms (TPM). All these TPM based works included time as an element,but nowhere in these works how dynamically is a frequent pattern P changing itsbehavior in the database D. The authors Wan and An presented “Transitional Patterns” whichrepresent item sets whose support significantly changes from one time point toanother time point in the database. Primarily Wan and a focused on finding timepoints at which negative (or positive) transitional patterns decreases (orincreases) their support significantly with the change of time. TP-Minealgorithm has the limitation of when we add new transactions to the databaseand by reapplying the TP-Mine algorithm on the updated database, alreadyidentified time points may not valid on the updated database. The motive ofthis paper is to address the limitation existing in the TP-Mine algorithmproposed by Wan and An and it is done by redefining the definition oftransitional pattern and proposing an efficient two scan algorithm for finding redefined transitional patterns inparallel to the extraction of frequent patterns.
Keywords – Data mining, Association rule, frequent pattern, AlternativeTransitional Patterns, Major and Minor Landmarks.