Title :
Theoretical foundations of sequential patterns
Author :
Li, Tianrui ; Yang, Ning ; Ma, Jun ; Xu, Yang
Author_Institution :
Dept. of Math., Southwest Jiaotong Univ., Chengdu, China
Abstract :
Previous work on sequential pattern discovery was mainly focused on studying scalable algorithms while less on its theoretical foundations. Based on Galois closed operator, identifier set, sequential set in sequential database together with their binary relation constituted a context. The relation between fixed point and closed sequential pattern was established. To mine all frequent closed sequential patterns is equal to build fixed point lattice and mine all points on it that satisfy support constraint, which serves as theoretical foundations of sequential patterns and makes it possible to use the existing fixed point and lattice theories to support more effective sequential pattern mining tasks.
Keywords :
data mining; lattice theory; pattern recognition; sequential estimation; set theory; Galois closed operator; closed sequential patterns; fixed point lattice; identifier set; lattice theory; sequential database; sequential pattern discovery; sequential pattern mining tasks; sequential set; Constraint theory; Databases; Lattices; Mathematics;
Conference_Titel :
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
Print_ISBN :
0-7803-8273-0
DOI :
10.1109/WCICA.2004.1342310