Mining Regular Patterns in Transactional Databases

Abstract

SUMMARYThe frequency of a pattern may not be a sufficient criterion for identifying meaningful patterns in a database. The temporal regularity of a pattern can be another key criterion for assessing the importance of a pattern in several applications. A pattern can be said regular if it appears at a regular user-defined interval in the database. Even though there have been some efforts to discover periodic patterns in time-series and sequential data, none of the existing studies have provided an appropriate method for discovering the patterns that occur regularly in a transactional database. Therefore, in this paper, we introduce a novel concept of mining regular patterns from transactional databases. We also devise an efficient tree-based data structure, called a Regular Pattern tree (RP-tree in short), that captures the database contents in a highly compact manner and enables a pattern growth-based mining technique to generate the complete set of regular patterns in a database for a user-defined regularity threshold. Our performance study shows that mining regular patterns with an RP-tree is time and memory efficient, as well as highly scalable.

Mining Productive-associated Periodic Frequent Pattern in Body Sensor Data for Smart Home Care

“…For instance, the periodicity measure in [27], which is susceptible to noise in the database, might often report the noised maximal period of a pattern as its regular period. Additionally, as we mentioned earlier, the methods in [25] and [26] often generate regular (periodic) frequent patterns that occur in the whole database with totally distinct periods.…”

“…Recently, Tanbeer et al [26] developed a regular pattern tree to exactly mine regular patterns from transactional databases. This approach requires two database scans and uses the maximum occurrence interval of a pattern in a database to measure a pattern's periodicity.…”

“…algorithms because the approaches in [24][25][26] try to discover those patterns that are frequent and have complete cyclic repetitions in the entire database. Most of these algorithms use a maximum periodicity threshold to discover periodic patterns, which measures pattern periodicity based on the largest amount of time difference or number of timeslots between two occurrences of a pattern.…”

Parallel and distributed frequent-regular patternmining using vertical format in large databases

“…Recently, Tanbeer et. al [4] introduced a new problem to mine regular patterns in a database which follows a temporal regularity in the occurrence behavior of a pattern. They proposed a tree-based data structure called RP-tree which captures user-given maximum regularity threshold and mines regular patterns from the database with two database scans.…”

“…Tanbeer et al [4], [5] proposed a new problem of discovering regular patterns which follow temporal regularity of a pattern in a transactional database. A pattern is said to be a regular pattern when its occurrence behavior is less than or equal to user given maximum regularity threshold (i.e., max_reg).…”