{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:08:13Z","timestamp":1768295293126,"version":"3.49.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,3,11]],"date-time":"2014-03-11T00:00:00Z","timestamp":1394496000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s10586-014-0360-5","type":"journal-article","created":{"date-parts":[[2014,3,10]],"date-time":"2014-03-10T11:04:10Z","timestamp":1394449450000},"page":"1081-1100","source":"Crossref","is-referenced-by-count":14,"title":["Effective and efficient data sampling using bitmap indices"],"prefix":"10.1007","volume":"17","author":[{"given":"Yu","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gagan","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Woodring","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kary","family":"Myers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joanne","family":"Wendelberger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Ahrens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,3,11]]},"reference":[{"key":"360_CR1","doi-asserted-by":"crossref","unstructured":"Abramson, D., Kommineni, J.: A flexible IO scheme for grid workflows. In: Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS), April 2004.","DOI":"10.1109\/IPDPS.2004.1303039"},{"key":"360_CR2","volume-title":"The Visualization Handbook","author":"J Ahrens","year":"2005","unstructured":"Ahrens, J., Geveci, B., Law, C.: Paraview: an end user tool for large data visualization. In: Hansen, C.D., Johnson, C.R. (eds.) The Visualization Handbook. Elsevier, Burlington (2005)"},{"key":"360_CR3","unstructured":"Allcock, W.E., Foster, I., Madduri, R.: Reliable data transport: a critical service for the grid. In: Proceedings of the Workshop on Building Service Based Grids, 2004."},{"key":"360_CR4","doi-asserted-by":"crossref","unstructured":"Antoshenkov, G.: Byte-aligned bitmap compression. In: DCC\u201995: Proceedings of the Conference on Data Compression, p. 476. IEEE (1995)","DOI":"10.1109\/DCC.1995.515586"},{"key":"360_CR5","unstructured":"Baranovski, A., Beattie, K., Bharathi, S., Boverhof, J., Bresnahan, J., Chervenak, A., Foster, I., Freeman, T., Gunter, D., Keahey, K., Kesselman, C., Kettimuthu, R., Leroy, N., Link, M., Livny, M., Madduri, R., Oleynik, G., Pearlman, L., Schuler, R., Tierney, B.: Enabling petascale science: data management, troubleshooting, and scalable science services. J. Phys.: Conf. Ser. 125, (2008)"},{"issue":"3","key":"360_CR6","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/JPROC.2004.842745","volume":"93","author":"D Bernholdt","year":"2005","unstructured":"Bernholdt, D., Bharathi, S., Brown, D., Chanchio, K., Chen, M., Chervenak, A., Cinquini, L., Drach, B., Foster, I., Fox, P., et al.: The earth system grid: supporting the next generation of climate modeling research. Proc. IEEE 93(3), 485\u2013495 (2005)","journal-title":"Proc. IEEE"},{"key":"360_CR7","doi-asserted-by":"crossref","unstructured":"Cai, M., Chervenak, A., Frank, M.: A peer-to-peer replica location service based on a distributed hash table. In: Proceedings of SC 2004, Nov 2004","DOI":"10.1109\/SC.2004.7"},{"key":"360_CR8","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s007780100049","volume":"10","author":"K Chakrabarti","year":"2001","unstructured":"Chakrabarti, K., Garofalakis, M., Rastogi, R., Shim, K.: Approximate query processing using wavelets. VLDB J. 10, 199\u2013223 (2001)","journal-title":"VLDB J."},{"key":"360_CR9","first-page":"534","volume":"1999","author":"S Chaudhuri","year":"1999","unstructured":"Chaudhuri, S., Das, G., Datar, M., Motwani, R., Narasayya, V.: Overcoming limitations of sampling for aggregation queries. Proc. ICDE 1999, 534\u2013542 (1999)","journal-title":"Proc. ICDE"},{"key":"360_CR10","doi-asserted-by":"crossref","unstructured":"Chervenak, A.L., Palavalli, N., Bharathi, S., Kesselman, C., Schwartzkopf, R.: Performance and scalability of a replica location service. In: Proceedings of the Conference on High Performance Distributed Computing (HPDC), June 2004","DOI":"10.1109\/HPDC.2004.1323525"},{"key":"360_CR11","doi-asserted-by":"crossref","unstructured":"Chou, J., Wu, K., R\u00fcbel, O., Prabhat, M.H.J.Q., Austin, B., Bethel, E.W., Ryne, R.D., Shoshani, A.: Parallel index and query forlarge scale data analysis, In: SC (2011)","DOI":"10.1145\/2063384.2063424"},{"key":"360_CR12","volume-title":"Sampling Techniques","author":"WG Cochran","year":"2007","unstructured":"Cochran, W.G.: Sampling Techniques. Wiley-India, New Delhi (2007)"},{"key":"360_CR13","doi-asserted-by":"crossref","unstructured":"Deelman, E., Blythe, J., Gil, Y., Kesselman, C., Mehta, G., Vahi, K., Lazzarini, A., Arbree, A., Cavanaugh, R., Koranda, S.: Mapping abstract complex workflows onto grid environments. J. Grid Comput., 9\u201323 (2003)","DOI":"10.1007\/978-3-540-28642-4_2"},{"key":"360_CR14","unstructured":"Deelman, E., Singh, G., Atkinson, M.P., Chervenak, A., Chue Hong, N.P., Kesselman, C., Patil, S., Pearlman, L., Su, M.: Grid-based metadata services. In: Proceedings of the 16th International Conference on Scientific and Statistical Database Management (SSDBM04) (2004)"},{"key":"360_CR15","doi-asserted-by":"crossref","unstructured":"Ellsworth, D., Green, B., Moran, P.: Interactive terascale particle visualization. In: Proceedings of the conference on Visualization\u201904, pp. 353\u2013360. IEEE Computer Society (2004)","DOI":"10.1109\/VISUAL.2004.55"},{"key":"360_CR16","doi-asserted-by":"crossref","unstructured":"Foster, I., Voeckler, J., Wilde, M., Zhao, Y.: Chimera: a virtual data system for representing, querying and automating data derivation. In: Proceedings of the Conference on Scientific and Statistical Data Management, July 2002","DOI":"10.1109\/SSDM.2002.1029704"},{"key":"360_CR17","unstructured":"Grover, R., Carey, M.J.: Extending map-reduce for efficient predicate-based sampling. In: IEEE 28th International Conference on Data Engineering (ICDE), 2012, pp. 486\u2013497. IEEE (2012)"},{"key":"360_CR18","doi-asserted-by":"crossref","unstructured":"Hellerstein, J.M., Haas, P.J., Wang, H.J.: Online aggregation. In: Proceedings of SIGMOD 1997 (1997)","DOI":"10.1145\/253260.253291"},{"key":"360_CR19","unstructured":"Ioannidis, Y., Poosala, V.: Histogram-based approximation of set-valued query-answers. In: Proceedings of the International Conference on Very Large Data, Bases, pp. 174\u2013185. (1999)"},{"key":"360_CR20","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1145\/1247480.1247560","volume":"2007","author":"C Jermaine","year":"2007","unstructured":"Jermaine, C., Arumugam, S., Pol, A., Dobra, A.: Scalable approximate query processing with the dbo engine. Proc. SIGMOD 2007, 725\u2013736 (2007)","journal-title":"Proc. SIGMOD"},{"key":"360_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ravi, V.T., Agrawal, G.: A map-reduce system with an alternate API for multi-core environments. In: Proceedings of the 2010 10th IEEE\/ACM International Conference on Cluster, Cloud and Grid Computing, pp. 84\u201393. IEEE Computer Society (2010)","DOI":"10.1109\/CCGRID.2010.10"},{"issue":"5","key":"360_CR22","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/MCG.2003.1231171","volume":"23","author":"CR Johnson","year":"2003","unstructured":"Johnson, C.R., Sanderson, A.R.: A next step: visualizing errors and uncertainty. IEEE Comput. Graph. Appl. 23(5), 6\u201310 (2003)","journal-title":"IEEE Comput. Graph. Appl."},{"issue":"10","key":"360_CR23","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1002\/cpe.894","volume":"17","author":"PW Jones","year":"2005","unstructured":"Jones, P.W., Worley, P.H., Yoshida, Y., White III, J.B., Levesque, J.: Practical performance portability in the parallel ocean program (POP). Concurr. Comput.: Pract. Exp. 17(10), 1317\u20131327 (2005)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"360_CR24","doi-asserted-by":"crossref","unstructured":"Kettimuthu, R., Sim, A., Gunter, D., Allcock, B., Bremer, P.-T., Bresnahan, J., Cherry, A., Childers, L., Dart, E., Foster, I., Harms, K., Hick, J., Lee, J., Link, M., Long, J., Miller, K., Natarajan, V., Pascucci, V., Raffenetti, K., Ressman, D., Williams, D., Wilson, L., Winkler, L.: Lessons learned from moving earth system grid data sets over a 20 Gbps wide-area network. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing (HPDC 2010), June 2010","DOI":"10.1145\/1851476.1851519"},{"issue":"18","key":"360_CR25","doi-asserted-by":"crossref","first-page":"36173620","DOI":"10.1029\/2001GL013552","volume":"28","author":"MF Khairoutdinov","year":"2001","unstructured":"Khairoutdinov, M.F., Randall, D.A.: A cloud resolving model as a cloud parameterization in the ncar community climate system model: preliminary results. Geophys. Res. Lett. 28(18), 36173620 (2001)","journal-title":"Geophys. Res. Lett."},{"key":"360_CR26","doi-asserted-by":"crossref","unstructured":"Kissel, E., Martin Swany, D., Brown, A.: Improving GridFTP performance using the Phoebus session layer. In: Proceedings of SC, Nov 2009","DOI":"10.1145\/1654059.1654094"},{"key":"360_CR27","doi-asserted-by":"crossref","unstructured":"Kosar, T., Livny, M.: Stork: making data placement a first class citizen in the grid. In: Proceedings of International Conference on Distributed Computing Systems (ICDCS) (2004)","DOI":"10.1109\/ICDCS.2004.1281599"},{"key":"360_CR28","doi-asserted-by":"crossref","unstructured":"LaMar, E.C., Hamann, B., Joy, K.I.: Efficient error calculation for multiresolution texture-based volume visualization. In: Hierarchical and Geometrical Methods in Scientific Visualization. pp. 51\u201362. (2003)","DOI":"10.1007\/978-3-642-55787-3_4"},{"key":"360_CR29","doi-asserted-by":"crossref","unstructured":"LaMar, E., Hamann, B., Joy, K.I.: Multiresolution techniques for interactive texture-based volume visualization. In: Proceedings of the Conference on Visualization\u201999: Celebrating Ten Years, pp. 355\u2013361. IEEE Computer Society Press (1999)","DOI":"10.1109\/VISUAL.1999.809908"},{"issue":"10","key":"360_CR30","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.14778\/2336664.2336675","volume":"5","author":"N Laptev","year":"2012","unstructured":"Laptev, N., Zeng, K., Zaniolo, C.: Early accurate results for advanced analytics on mapreduce. Proc. VLDB Endow. 5(10), 1028\u20131039 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"360_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., Tieman, B., Kettimuthu, R., Foster, I.: A data transfer framework for large-scale science experiments. In: 3rd International Workshop on Data Intensive Distributed Computing (DIDC 2010) in conjunction with 19th International Symposium on High Performance Distributed Computing (HPDC) 2010 (2010)","DOI":"10.1145\/1851476.1851582"},{"key":"360_CR32","unstructured":"Lohr, S.L.: Sampling: design and analysis. Thomson (2009)"},{"key":"360_CR33","unstructured":"Lu, D., Qiao, Y., Dinda, P.A., Bustamante, F.E.: Modeling and taming parallel TCP on wide area networks. In: Proceedings of the 12th International Parallel and Distributed Processing Symposium (IPDPS), April 2005"},{"key":"360_CR34","doi-asserted-by":"crossref","unstructured":"O\u2019Neil, P., Quass, D.: Improved query performance with variant indexes. In ACM Sigmod Record, vol. 26, pp. 38\u201349. ACM (1997)","DOI":"10.1145\/253262.253268"},{"key":"360_CR35","doi-asserted-by":"crossref","unstructured":"Pascucci, V., Frank, R.J.: Global static indexing for real-time exploration of very large regular grids. In: Supercomputing, ACM\/IEEE 2001 Conference, pp. 45\u201345. IEEE (2001)","DOI":"10.1145\/582034.582036"},{"key":"360_CR36","doi-asserted-by":"crossref","unstructured":"Poosala, V., Ganti, V.: Fast approximate query answering using precomputed statistics. In: Proceedings of ICDE 1999, p. 252 (1999)","DOI":"10.1109\/ICDE.1999.754932"},{"key":"360_CR37","doi-asserted-by":"crossref","unstructured":"Poosala, V., Haas, P.J., Ioannidis, Y.E., Shekita, E.J.: Improved histograms for selectivity estimation of range predicates. ACM SIGMOD Record 25(2), 294\u2013305 (1996)","DOI":"10.1145\/235968.233342"},{"key":"360_CR38","doi-asserted-by":"crossref","unstructured":"Singh, G., Bharathi, S., Chervenak, A., Deelman, E., Kesselman, C., Mahohar, M., Pail, S., Pearlman L.: A metadata catalog service for data intensive applications. In: Proceedings of Supercomputing 2003 (SC2003), Nov 2003","DOI":"10.1145\/1048935.1050184"},{"key":"360_CR39","doi-asserted-by":"crossref","unstructured":"Singh, G., Bharathi, S., Chervenak, A., Deelman, E., Kesselman, E., Manohar, M., Patil, S., Pearlman, L.: A metadata catalog service for data intensive applications. In SC \u201903: Proceedings of the 2003 ACM\/IEEE Conference on Supercomputing, p. 33, Washington, DC, USA. IEEE Computer Society (2003)","DOI":"10.1145\/1048935.1050184"},{"key":"360_CR40","doi-asserted-by":"crossref","unstructured":"Su, Y., Agrawal, G.: Supporting user-defined subsetting and aggregation over parallel netcdf datasets. In: 2012 12th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 212\u2013219. IEEE (2012)","DOI":"10.1109\/CCGrid.2012.45"},{"key":"360_CR41","doi-asserted-by":"crossref","unstructured":"Su, Y., Agrawal, G., Woodring, J.: Indexing and parallel query processing support for visualizing climate datasets. In: 2012 41th IEEE\/ACM International Conference on Parallel Processing (ICPP), pp. 249\u2013258. IEEE (2012)","DOI":"10.1109\/ICPP.2012.33"},{"key":"360_CR42","doi-asserted-by":"crossref","unstructured":"Su, Y., Agrawal, G., Woodring, J., Myers, K., Wendelberger, J., Ahrens, J.: Taming massive distributed datasets: data sampling using bitmap indices. In: Proceedings of the 22nd international symposium on High-performance parallel and distributed computing, pp. 13\u201324. ACM (2013)","DOI":"10.1145\/2493123.2462906"},{"key":"360_CR43","unstructured":"Tuchinda, R., Thakkar, S., Gil, A., Deelman, E.: Artemis: integrating scientific data on the grid. In: Proceedings of the 16th Conference on Innovative Applications of Artificial Intelligence (IAAI), pp. 25\u201329 (2004)"},{"key":"360_CR44","doi-asserted-by":"crossref","unstructured":"Vazhkudai, S., Schopf, J.: Using disk throughput data in predictions of end-to-end grid transfers. In: Proceedings of the Third Workshop on Grid Computing (Grid 2002), Nov 2002","DOI":"10.1007\/3-540-36133-2_27"},{"issue":"1","key":"360_CR45","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/23002.23003","volume":"13","author":"JS Vitter","year":"1987","unstructured":"Vitter, J.S.: An efficient algorithm for sequential random sampling. ACM Trans. Math. Softw. (TOMS) 13(1), 58\u201367 (1987)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"issue":"1","key":"360_CR46","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TVCG.2007.15","volume":"13","author":"C Wang","year":"2007","unstructured":"Wang, C., Garcia, A., Shen, H.W.: Interactive level-of-detail selection using image-based quality metric for large volume visualization. IEEE Trans. Vis. Comput. Graph. 13(1), 122\u2013134 (2007)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"360_CR47","doi-asserted-by":"crossref","unstructured":"Woodring, J., Ahrens, J., Figg, J., Wendelberger, J., Habib, S., Heitmann, K.: In situ sampling of a large-scale particle simulation for interactive visualization and analysis. In: Computer Graphics Forum, vol. 30, pp. 1151\u20131160. Wiley Online Library (2011)","DOI":"10.1111\/j.1467-8659.2011.01964.x"},{"key":"360_CR48","unstructured":"Wu, K., Otoo, E.J., Shoshani, A.: Compressing bitmap indexes for faster search operations. In: Proceedings of the 14th International Conference on Scientific and Statistical Database Management, 2002, pp. 99\u2013108. IEEE (2002)"},{"key":"360_CR49","doi-asserted-by":"crossref","unstructured":"Wu, K., Stockinger, K., Shoshani, A.: Breaking the curse of cardinality on bitmap indexes. In: Scientific and Statistical Database Management, pp. 348\u2013365. Springer (2008)","DOI":"10.1007\/978-3-540-69497-7_23"},{"key":"360_CR50","unstructured":"Wu, K., Koegler, W., Chen, J., Shoshani, A.: Using bitmap index for interactive exploration of large datasets. In: 15th International Conference on Scientific and Statistical Database Management, 2003, pp. 65\u201374. IEEE, July 2003"},{"issue":"6","key":"360_CR51","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1109\/TVCG.2010.131","volume":"16","author":"L Xu","year":"2010","unstructured":"Xu, L., Lee, T.Y., Shen, H.W.: An information-theoretic framework for flow visualization. IEEE Trans. Vis. Comput. Graph. 16(6), 1216\u20131224 (2010)","journal-title":"IEEE Trans. Vis. Comput. Graph."}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-014-0360-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-014-0360-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-014-0360-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:57:31Z","timestamp":1746147451000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-014-0360-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3,11]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["360"],"URL":"https:\/\/doi.org\/10.1007\/s10586-014-0360-5","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3,11]]}}}