Istituto di Scienza e Tecnologie dell'Informazione     
Giannotti F., Nanni M., Pedreschi D. Efficient mining of temporally annotated sequences. In: 2006 SIAM Conference on Data Mining (Bethesda, Washington D.C., USA, 20-22 April 2006). Proceedings, vol. PR124 pp. 348 - 359. Joydeep Ghosh, Diane Lambert, David Skillicorn and Jaideep Srivastava (eds.). SIAM, 2006.
Sequential patterns mining received much attention in recent years, thanks to its various potential application domains. A large part of them represent data as collections of time-stamped itemsets, e.g., customers' purchases, logged web accesses, etc. Most approaches to sequence mining focus on sequentiality of data, using time-stamps only to order items and, in some cases, to constrain the temporal gap between items. In this paper, we propose an e±cient algorithm for computing (temporally-)annotated sequential patterns, i.e., sequential patterns where each transition is annotated with a typical transition time derived from the source data. The algorithm adopts a prefix-projection approach to mine candidate sequences, and it is tightly integrated with a annotation mining process that associates sequences with temporal annotations. The pruning capabilities of the two steps sum together, yielding significant improvements in performances, as demonstrated by a set of experiments performed on synthetic datasets.
URL: http://www.siam.org/meetings/sdm06/proceedings/032giannottif.pdf
Subject Temporal Data Mining
Sequential Pattern
I.2.6 Learning

Icona documento 1) Download Document PDF

Icona documento Open access Icona documento Restricted Icona documento Private


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional