Van Quoc Huynh, Josef Küng, Markus Jäger, Khanh Tran Dang,
"IFIN+: A Parallel Incremental Frequent Itemsets Mining in Shared-Memory Environment"
, in Tran Khanh Dang, Roland Wagner, Josef Küng, Nam Thoai, Makoto Takizawa, Erich Neuhold: Future Data and Security Engineering: 4th International Conference, FDSE 2017, Ho Chi Minh City, Vietnam, Nov 29 - Dez 01, 2017, Proceedings, Serie Future Data and Security Engineering: 4th International Conference, FDSE, Vol. 4, Springer International, Seite(n) 121-138, 11-2017, ISBN: 978-3-319-70003-8
Original Titel:
IFIN+: A Parallel Incremental Frequent Itemsets Mining in Shared-Memory Environment
Sprache des Titels:
Englisch
Original Buchtitel:
Future Data and Security Engineering: 4th International Conference, FDSE 2017, Ho Chi Minh City, Vietnam, Nov 29 - Dez 01, 2017, Proceedings
Original Kurzfassung:
In an effort to increase throughput for IFIN, a frequent itemsets mining algo-rithm, in this paper we introduce a solution, called IFIN+, for parallelizing the al-gorithm IFIN with shared-memory multithreads. The inspiration for our motiva-tion is that today commodity processors? computational power is enhanced with multi physical computational units; and therefore, exploiting full advantage of this is a potential solution for improving performance in single-machine environ-ments. Some portions in the serial version are changed in means which increase computational independence for convenience in designing parallel computation with Work-Pool model, be known as a good model for load balance. We con-ducted experiments to evaluate IFIN+ against its serial version IFIN, the well-known algorithm FP-Growth and other two state-of-the-art ones FIN and Pre-Post+. The experimental results show that the running time of IFIN+ is the most efficient, especially in the case of mining at different support thresholds in the same running session. Compare to its serial version, IFIN+ performance is im-proved significantly.
Sprache der Kurzfassung:
Englisch
Veröffentlicher:
Springer International
Serie:
Future Data and Security Engineering: 4th International Conference, FDSE
Forschungs-