Clustering Data Streams: Theory and Practice Export

@article{citeulike:2206943, abstract = {The data stream model has recently attracted attention for its applicability to numerous types of data, including telephone records, Web documents, and clickstreams. For analysis of such data, the ability to process the data in a single pass, or a small number of passes, while using little memory, is crucial. We describe such a streaming algorithm that effectively clusters large data streams. We also provide empirical evidence of the algorithm's performance on synthetic and real data streams.}, address = {Los Alamitos, CA, USA}, author = {Guha, Sudipto and Meyerson, Adam and Mishra, Nina and Motwani, Rajeev and O'Callaghan, Liadan}, citeulike-article-id = {2206943}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=776752.776777}, citeulike-linkout-1 = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2003.1198387}, citeulike-linkout-2 = {http://dx.doi.org/10.1109/TKDE.2003.1198387}, citeulike-linkout-3 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1198387}, doi = {10.1109/TKDE.2003.1198387}, issn = {1041-4347}, journal = {IEEE Transactions on Knowledge and Data Engineering}, keywords = {clustering, data-processing, data-stream, dataflows, information-processing, signal-processing, streams}, month = {March}, number = {3}, pages = {515--528}, posted-at = {2009-07-15 17:48:10}, priority = {2}, publisher = {IEEE Computer Society}, title = {Clustering Data Streams: Theory and Practice}, url = {http://dx.doi.org/10.1109/TKDE.2003.1198387}, volume = {15}, year = {2003} }

TY - JOUR ID - citeulike:2206943 L3 - citeulike-article-id:2206943 N2 - The data stream model has recently attracted attention for its applicability to numerous types of data, including telephone records, Web documents, and clickstreams. For analysis of such data, the ability to process the data in a single pass, or a small number of passes, while using little memory, is crucial. We describe such a streaming algorithm that effectively clusters large data streams. We also provide empirical evidence of the algorithm's performance on synthetic and real data streams. IS - 3 JF - IEEE Transactions on Knowledge and Data Engineering SN - 1041-4347 AD - Los Alamitos, CA, USA EP - 528 TI - Clustering Data Streams: Theory and Practice PB - IEEE Computer Society VL - 15 SP - 515 KW - clustering KW - data-processing KW - data-stream KW - dataflows KW - information-processing KW - signal-processing KW - streams AU - Guha, Sudipto AU - Meyerson, Adam AU - Mishra, Nina AU - Motwani, Rajeev AU - O'Callaghan, Liadan PY - 2003/03// UR - http://dx.doi.org/10.1109/TKDE.2003.1198387 ER -