%0 Conference Paper %1 li:mining %A Li, Hua-Fu %A Lee, Suh-Yin %A Shan, Man-Kwan %B Proceedings of First International Workshop on Knowledge Discovery in Data Streams %D 2004 %K mining %T An Efficient Algorithm for Mining Frequent Itemsets over the Entire History of Data Streams %X A data stream is a continuous, huge, fast changing, rapid, infinite sequence of data elements. The nature of streaming data makes it essential to use online algorithms which require only one scan over the data for knowledge discovery. In this paper, we propose a new single-pass algorithm, called DSMFI (Data Stream Mining for Frequent Itemsets), to mine all frequent itemsets over the entire history of data streams. DSM-FI has three major features, namely single streaming data scan for counting itemsets’ frequency information, extended prefix-tree-based compact pattern representation, and top-down frequent itemset discovery scheme. Our performance study shows that DSM-FI outperforms the well-known algorithm Lossy Counting in the same streaming environment.

@inproceedings{li:mining, abstract = {A data stream is a continuous, huge, fast changing, rapid, infinite sequence of data elements. The nature of streaming data makes it essential to use online algorithms which require only one scan over the data for knowledge discovery. In this paper, we propose a new single-pass algorithm, called DSMFI (Data Stream Mining for Frequent Itemsets), to mine all frequent itemsets over the entire history of data streams. DSM-FI has three major features, namely single streaming data scan for counting itemsets’ frequency information, extended prefix-tree-based compact pattern representation, and top-down frequent itemset discovery scheme. Our performance study shows that DSM-FI outperforms the well-known algorithm Lossy Counting in the same streaming environment.}, added-at = {2006-06-02T10:59:17.000+0200}, author = {Li, Hua-Fu and Lee, Suh-Yin and Shan, Man-Kwan}, biburl = {https://www.bibsonomy.org/bibtex/22f8154f8875b9afb1bcf35ca44d15c62/wolfey}, booktitle = {Proceedings of First International Workshop on Knowledge Discovery in Data Streams}, interhash = {9d5282488214d7612a256a15f4e56615}, intrahash = {2f8154f8875b9afb1bcf35ca44d15c62}, keywords = {mining}, timestamp = {2006-06-02T10:59:17.000+0200}, title = {An Efficient Algorithm for Mining Frequent Itemsets over the Entire History of Data Streams}, year = 2004 }