Temporal-Hmine-Rev Algorithm for Mining Frequent Patterns in Temporal Databases

A temporal association rule is an association rule that holds during specific time intervals. The problem is to discover complete set of frequent patterns with respect to calendar schema from a set of time stamped transactions. This paper uses the data structure H-struct (Hyper-structure) of  Hmine-rev, and incorporated temporal aspects and it is called T-Hmine-rev (Temporal-Hmine-reverse). Hmine-rev is a revised algorithm of H-mine (Hyper-structure mining) which is used for mining frequent patterns and it does not need any adjustment of H-struct links structure like H-mine. Hmine-rev works well on sparse dataset and H-struct is used for fast mining on time-based dataset.