DocumentCode :
3633123
Title :
Applying a pattern length constraint on the FP-Growth algorithm
Author :
Cornelia Gyorodi;Robert Gyorodi;Mihai Dersidan;Livia Bandici
Author_Institution :
Department of Computer Science, Faculty of Electrical Engineering and Information Technology, University of Oradea, Str. Universitatii 1, 410087, Romania
fYear :
2009
Firstpage :
183
Lastpage :
186
Abstract :
With the ever-growing database sizes, we have enormous quantities of data, but unfortunately we cannot use raw data in our day-to-day reasoning/decisions. We desperately need knowledge. This knowledge is in most cases in the gathered data, but the extraction of it is a very time and resources consuming operation. In this paper we propose an improvement of the FP-Growth algorithm that focuses on applying a pattern-length constraint on the FP-Growth algorithm. This is, mining only frequent patterns with their length belonging in an interval selected by the user. The algorithm with this constraint applied can be used when only patterns with specific lengths are interesting for the user. The main advantage of running the algorithm with the length limitation instead of the classic FP-Growth algorithm is that the running time of the former is smaller, thus, the required information can be obtained in a shorter time.
Keywords :
"Data mining","Association rules","Iterative algorithms","Transaction databases","Computer science","Information technology","Economic forecasting","Medical diagnosis","Forward contracts","Tree data structures"
Publisher :
ieee
Conference_Titel :
Soft Computing Applications, 2009. SOFA ´09. 3rd International Workshop on
Print_ISBN :
978-1-4244-5054-1
Type :
conf
DOI :
10.1109/SOFA.2009.5254855
Filename :
5254855
Link To Document :
بازگشت