Kuo-Yu Huang

SMCA: a general model for mining asynchronous periodic patterns in temporal databases

Mining periodic patterns in time series databases is an important data mining problem with many applications. Previous studies have considered synchronous periodic patterns where misaligned occurrences are not allowed. However, asynchronous periodic pattern mining has received less attention and only been discussed for a sequence of symbols where each time point contains one event. In this paper, we propose a more general model of asynchronous periodic patterns from a sequence of symbol sets where a time slot can contain multiple events. Three parameters min/spl I.bar/rep, max/spl I.bar/dis, and global/spl I.bar/rep are employed to specify the minimum number of repetitions required for a valid segment of nondisrupted pattern occurrences, the maximum allowed disturbance between two successive valid segments, and the total repetitions required for a valid sequence. A 4-phase algorithm is devised to discover periodic patterns from a time series database presented in vertical format. The experiments demonstrate good performance and scalability with large frequent patterns.

Efficient mining of frequent episodes from complex sequences

Discovering patterns with great significance is an important problem in data mining discipline. An episode is defined to be a partially ordered set of events for consecutive and fixed-time intervals in a sequence. Most of previous studies on episodes consider only frequent episodes in a sequence of events (called simple sequence). In real world, we may find a set of events at each time slot in terms of various intervals (hours, days, weeks, etc.). We refer to such sequences as complex sequences. Mining frequent episodes in complex sequences has more extensive applications than that in simple sequences. In this paper, we discuss the problem on mining frequent episodes in a complex sequence. We extend previous algorithm MINEPI to MINEPI+ for episode mining from complex sequences. Furthermore, a memory-anchored algorithm called EMMA is introduced for the mining task. Experimental evaluation on both real-world and synthetic data sets shows that EMMA is more efficient than MINEPI+.

Mining Periodic Patterns in Sequence Data

Periodic pattern mining is the problem that regards temporal regularity. There are many emerging applications in periodic pattern mining, including web usage recommendation, weather prediction, computer networks and biological data. In this paper, we propose a Progressive Timelist-Based Verification (PTV) method to the mining of periodic patterns from a sequence of event sets. The parameter min_rep, is employed to specify the minimum number of repetitions required for a valid segment of non-disrupted pattern occurrences. We also describe a partitioning approach to handle extra large/long data sequence. The experiments demonstrate good performance and scalability with large frequent patterns.

PROWL: An Efficient Frequent Continuity Mining Algorithm on Event Sequences

Mining association rule in event sequences is an important data mining problem with many applications. Most of previous studies on association rules are on mining intra-transaction association, which consider only relationship among the item in the same transaction. However, intra-transaction association rules are not a suitable for trend prediction. Therefore, inter-transaction association is introduced, which consider the relationship among itemset of multiple time instants. In this paper, we present PROWL, an efficient algorithm for mining inter-transaction rules. By using projected window method and depth first enumeration approach, we can discover all frequent patterns quickly. Finally, an extensive experimental evaluation on a number of real and synthetic database shows that PROWL significantly outperforms previous method.

COBRA: closed sequential pattern mining using bi-phase reduction approach

In this work, we study the problem of closed sequential pattern mining. We propose a novel approach which extends a frequent sequence with closed itemsets instead of single items. The motivation is that closed sequential patterns are composed of only closed itemsets. Hence, unnecessary item extensions which generates non-closed sequential patterns can be avoided. Experimental evaluation shows that the proposed approach is two orders of magnitude faster than previous works with a modest memory cost.

COCOA: compressed continuity analysis for temporal databases

A continuity is a kind of inter-transaction association which describes the relationships among different transactions. Since it breaks the boundaries of transactions, the number of potential itemsets and the number of rules will increase drastically. In this paper we consider the problem of discovering frequent compressed continuity patterns, which have the same power as mining the complete set of frequent continuity patterns. We devised a three-phase algorithm, COCOA, for frequent compressed continuity mining.

Efficient Discovery of Frequent Continuities by Projected Window List Technology

Mining frequent patterns is a fundamental problem in data mining research. A continuity is a kind of causal relationship which describes a definite temporal factor with exact position between the records. Since continuities break the boundaries of records, the number of potential patterns will increase drastically. An alternative approach is to mine compressed or closed frequent continuities (CFC). Mining CFCs has the same power as mining the complete set of frequent patterns, while substantially reducing redundant rules to be generated and increasing the effectiveness of mining. In this paper, we propose a method called projected window list (PWL) technology for the mining of frequent continuities. We present a series of frequent continuity mining algorithms, including PROWL+, COCOA and ClosedPROWL. Experimental evaluation shows that our algorithm is more efficient than previously works.

Efficient mining strategy for frequent serial episodes in temporal database

Discovering patterns with great significance is an important problem in data mining discipline. A serial episode is defined to be a partially ordered set of events for consecutive and fixed-time intervals in a sequence. Previous studies on serial episodes consider only frequent serial episodes in a sequence of events (called simple sequence). In real world, we may find a set of events at each time slot in terms of various intervals (called complex sequence). Mining frequent serial episodes in complex sequences has more extensive applications than that in simple sequences. In this paper, we discuss the problem on mining frequent serial episodes in a complex sequence. We extend previous algorithm MINEPI to MINEPI+ for serial episode mining from complex sequences. Furthermore, a memory-anchored algorithm called EMMA is introduced for the mining task.