In this paper we propose DCP, a new algorithm for solv- ing the Frequent Set Counting problem, which enhances Apriori. Our goal was to optimize the initial iterations of Apriori, i.e. the most time consuming ones when datasets characterized by short or medium length frequent patterns are considered. The main improvements regard the use of an innovative method for storing candidate set of items and counting their support, and the exploitation of eective pruning techniques which signicantly reduce the size of the dataset as execution progresses.
Enhancing the apriori algorithm for frequent set counting
Palmerini P;Perego R
2001
Abstract
In this paper we propose DCP, a new algorithm for solv- ing the Frequent Set Counting problem, which enhances Apriori. Our goal was to optimize the initial iterations of Apriori, i.e. the most time consuming ones when datasets characterized by short or medium length frequent patterns are considered. The main improvements regard the use of an innovative method for storing candidate set of items and counting their support, and the exploitation of eective pruning techniques which signicantly reduce the size of the dataset as execution progresses.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
prod_91446-doc_141235.pdf
solo utenti autorizzati
Descrizione: Enhancing the apriori algorithm for frequent set counting
Tipologia:
Versione Editoriale (PDF)
Dimensione
198.15 kB
Formato
Adobe PDF
|
198.15 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.