hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1002017

CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets

Adebukola Onashoga ; Department of Computer Science, Federal University of Agriculture, Abeokuta, Nigeria

Puni tekst: engleski, PDF (1 MB) str. 265-276 preuzimanja: 552* citiraj
APA 6th Edition
Onashoga, A. (2012). CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets. Journal of computing and information technology, 20 (4), 265-276. https://doi.org/10.2498/cit.1002017
MLA 8th Edition
Onashoga, Adebukola. "CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets." Journal of computing and information technology, vol. 20, br. 4, 2012, str. 265-276. https://doi.org/10.2498/cit.1002017. Citirano 17.04.2021.
Chicago 17th Edition
Onashoga, Adebukola. "CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets." Journal of computing and information technology 20, br. 4 (2012): 265-276. https://doi.org/10.2498/cit.1002017
Harvard
Onashoga, A. (2012). 'CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets', Journal of computing and information technology, 20(4), str. 265-276. https://doi.org/10.2498/cit.1002017
Vancouver
Onashoga A. CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets. Journal of computing and information technology [Internet]. 2012 [pristupljeno 17.04.2021.];20(4):265-276. https://doi.org/10.2498/cit.1002017
IEEE
A. Onashoga, "CLOLINK: An Adapted Algorithm for Mining Closed Frequent Itemsets", Journal of computing and information technology, vol.20, br. 4, str. 265-276, 2012. [Online]. https://doi.org/10.2498/cit.1002017

Sažetak
Mining of the complete set of frequent itemsets will lead to a huge number of itemsets. Fortunately, this problem can be reduced to the mining of closed frequent itemsets, which results in a much smaller number of itemsets. Methods for efficient mining of closed frequent itemsets have been studied extensively by many researchers using various strategies to prove their efficiencies such as Apriori-likemethods, FP growth algorithms, Tree projection and so on. However, when mining databases, these methods still encounter some performance bottlenecks like processing time, storage space and so on. This paper integrates the advantages of the strategies of H-Mine, a memory efficient algorithmfor mining frequent itemsets. The study proposes an algorithm named CLOLINK, which makes use of a compact data structure named L struct that links the items in the database dynamically during the mining process. An extensive experimental evaluation of the approach on real databases shows a better performance over the previous methods in mining closed frequent itemsets.

Ključne riječi
frequent pattern growth; closed frequent itemsets; data mining; mining methods and algorithm; CLOLINK

Hrčak ID: 99477

URI
https://hrcak.srce.hr/99477

Posjeta: 723 *