{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T20:02:42Z","timestamp":1743883362423},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2012,8,21]],"date-time":"2012-08-21T00:00:00Z","timestamp":1345507200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Distrib Parallel Databases"],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1007\/s10619-012-7105-3","type":"journal-article","created":{"date-parts":[[2012,8,20]],"date-time":"2012-08-20T15:12:30Z","timestamp":1345475550000},"page":"307-324","source":"Crossref","is-referenced-by-count":14,"title":["Data-intensive architecture for scientific knowledge discovery"],"prefix":"10.1007","volume":"30","author":[{"given":"Malcolm","family":"Atkinson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee Sun","family":"Liew","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Galea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Martin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amrey","family":"Krause","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Mouat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Corcho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Snelling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,8,21]]},"reference":[{"key":"7105_CR1","volume-title":"The DATA Bonanza\u2014Improving Knowledge Discovery for Science, Engineering and Business","author":"M.P. Atkinson","year":"2012","unstructured":"Atkinson, M.P., Baxter, R., Besana, P., Galea, M., Parsons, M., Brezany, P., Corcho, O., van Hemert, J., Snelling, D.: The DATA Bonanza\u2014Improving Knowledge Discovery for Science, Engineering and Business. Wiley, New York (2012). To be published"},{"key":"7105_CR2","unstructured":"Atkinson, M.P., Galea, M., Liew, C.S., Martin, P.: Final report on the ADMIRE architecture, with an assessment and proposals for its development. Tech. rep., The ADMIRE Project (2011)"},{"key":"7105_CR3","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/eScience.2008.126","volume-title":"Proceedings of the 2008 Fourth IEEE International Conference on eScience, e-Science \u201908","author":"R. Barga","year":"2008","unstructured":"Barga, R., Jackson, J., Araujo, N., Guo, D., Gautam, N., Simmhan, Y.: The Trident scientific workflow workbench. In: Proceedings of the 2008 Fourth IEEE International Conference on eScience, e-Science \u201908, pp. 317\u2013318. IEEE Comput. Soc., Los Alamitos (2008)"},{"issue":"1","key":"7105_CR4","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.ecoinf.2009.08.008","volume":"5","author":"D. Barseghian","year":"2010","unstructured":"Barseghian, D., Altintas, I., Jones, M.B., Crawl, D., Potter, N., Gallagher, J., Cornillon, P., Schildhauer, M., Borer, E.T., Seabloom, E.W., Hosseini, P.R.: Workflows and extensions to the Kepler scientific workflow system to support environmental sensor data access and analysis. Ecol. Inform. 5(1), 42\u201350 (2010)","journal-title":"Ecol. Inform."},{"issue":"5919","key":"7105_CR5","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1126\/science.1170411","volume":"323","author":"G. Bell","year":"2009","unstructured":"Bell, G., Hey, T., Szalay, A.S.: Beyond the data deluge. Science 323(5919), 1297\u20131298 (2009)","journal-title":"Science"},{"issue":"12","key":"7105_CR6","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1145\/2043174.2043190","volume":"54","author":"G.B. Berriman","year":"2011","unstructured":"Berriman, G.B., Groom, S.L.: How will astronomy archives survive the data tsunami? Commun. ACM 54(12), 52\u201356 (2011)","journal-title":"Commun. ACM"},{"key":"7105_CR7","first-page":"1","volume-title":"Proceedings of the 8th Extended Semantic Web Conference on the Semanic Web: Research and Applications\u2014Volume Part II","author":"C. Buil-Aranda","year":"2011","unstructured":"Buil-Aranda, C., Arenas, M., Corcho, O.: Semantics and optimization of the SPARQL 1.1 federation extension. In: Proceedings of the 8th Extended Semantic Web Conference on the Semanic Web: Research and Applications\u2014Volume Part II, ESWC\u201911, pp. 1\u201315. Springer, Berlin (2011)"},{"key":"7105_CR8","first-page":"1","volume-title":"Cairo International Biomedical Engineering Conference","author":"V. Curcin","year":"2008","unstructured":"Curcin, V., Ghanem, M.: Scientific workflow systems\u2014can one size fit all? In: Cairo International Biomedical Engineering Conference, CIBEC \u201908, pp. 1\u20139 (2008)"},{"key":"7105_CR9","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1016\/j.future.2008.06.010","volume":"25","author":"D. Roure De","year":"2009","unstructured":"De Roure, D., Goble, C., Stevens, R.: The design and realisation of the myExperiment virtual research environment for social sharing of workflows. Future Gener. Comput. Syst. 25, 561\u2013567 (2009)","journal-title":"Future Gener. Comput. Syst."},{"issue":"5","key":"7105_CR10","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.future.2008.06.012","volume":"25","author":"E. Deelman","year":"2009","unstructured":"Deelman, E., Gannon, D., Shields, M., Taylor, I.: Workflows and e-Science: an overview of workflow system features and capabilities. Future Gener. Comput. Syst. 25(5), 528\u2013540 (2009)","journal-title":"Future Gener. Comput. Syst."},{"issue":"3","key":"7105_CR11","first-page":"219","volume":"13","author":"E. Deelman","year":"2005","unstructured":"Deelman, E., Singh, G., Su, M.H., Blythe, J., Gil, Y., Kesselman, C., Mehta, G., Vahi, K., Berriman, G.B., Good, J., Laity, A., Jacob, J.C., Katz, D.S.: Pegasus: a framework for mapping complex scientific workflows onto distributed systems. Sci. Program. 13(3), 219\u2013237 (2005)","journal-title":"Sci. Program."},{"issue":"1926","key":"7105_CR12","doi-asserted-by":"crossref","first-page":"4133","DOI":"10.1098\/rsta.2010.0166","volume":"368","author":"B. Dobrzelecki","year":"2010","unstructured":"Dobrzelecki, B., Krause, A., Hume, A., Grant, A., Antonioletti, M., Alemu, T., Atkinson, M.P., Jackson, M., Theocharopoulos, E.: Integrating distributed data sources with OGSA-DAI DQP and views. Philos. Trans. R. Soc. Lond. A 368(1926), 4133\u20134145 (2010)","journal-title":"Philos. Trans. R. Soc. Lond. A"},{"key":"7105_CR13","unstructured":"ebXML Business Process Technical Committee: ebXML business process specification schema technical specification (version 2.0.4). Tech. rep., OASIS (2006)"},{"key":"7105_CR14","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1145\/1376616.1376729","volume-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","author":"B. Gedik","year":"2008","unstructured":"Gedik, B., Andrade, H., Wu, K.L., Yu, P.S., Doo, M.: SPADE: the system S declarative stream processing engine. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD \u201908, pp. 1123\u20131134. ACM, New York (2008)"},{"issue":"4","key":"7105_CR15","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2008.122","volume":"41","author":"I. Gorton","year":"2008","unstructured":"Gorton, I., Greenfield, P., Szalay, A., Williams, R.: Data-intensive computing in the 21st century. Computer 41(4), 30\u201332 (2008)","journal-title":"Computer"},{"key":"7105_CR16","first-page":"xix","volume-title":"The Fourth Paradigm: Data-Intensive Scientific Discovery","author":"J. Gray","year":"2009","unstructured":"Gray, J.: Jim Gray on eScience: a transformed scientific method. In: Hey, T., Tansley, S., Tolle, K. (eds.) The Fourth Paradigm: Data-Intensive Scientific Discovery, pp. xix\u2013xxxiii. Microsoft Research, Washington (2009)"},{"key":"7105_CR17","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1145\/1107499.1107503","volume":"34","author":"J. Gray","year":"2005","unstructured":"Gray, J., Liu, D.T., Nieto-Santisteban, M., Szalay, A., DeWitt, D.J., Heber, G.: Scientific data management in the coming decade. SIGMOD Rec. 34, 34\u201341 (2005)","journal-title":"SIGMOD Rec."},{"key":"7105_CR18","unstructured":"Habala, O., Jarka, M., Laclavik, M., Simo, B., Tran, V.: Report on pilot applications deployment and platform evaluation. Tech. rep., The ADMIRE Project (2011)"},{"issue":"3","key":"7105_CR19","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.parco.2011.02.006","volume":"37","author":"L. Han","year":"2011","unstructured":"Han, L., Liew, C.S., van Hemert, J.I., Atkinson, M.P.: A generic parallel processing model for facilitating data mining and integration. Parallel Comput. 37(3), 157\u2013171 (2011)","journal-title":"Parallel Comput."},{"key":"7105_CR20","volume-title":"The Fourth Paradigm: Data-Intensive Scientific Discovery","year":"2009","unstructured":"Hey, T., Tansley, S., Tolle, K. (eds.): The Fourth Paradigm: Data-Intensive Scientific Discovery. Microsoft Research, Washington (2009)"},{"issue":"web\u2013server-issu","key":"7105_CR21","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1093\/nar\/gkl320","volume":"34","author":"D. Hull","year":"2006","unstructured":"Hull, D., Wolstencroft, K., Stevens, R., Goble, C.A., Pocock, M.R., Li, P., Oinn, T.: Taverna: a tool for building and running workflows of services. Nucleic Acids Res. 34(web\u2013server-issue), 729\u2013732 (2006)","journal-title":"Nucleic Acids Res."},{"key":"7105_CR22","first-page":"59","volume-title":"Proceedings of the 2nd ACM SIGOPS\/EuroSys European Conference on Computer Systems","author":"M. Isard","year":"2007","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: Proceedings of the 2nd ACM SIGOPS\/EuroSys European Conference on Computer Systems, EuroSys \u201907, pp. 59\u201372. ACM, New York (2007)"},{"key":"7105_CR23","unstructured":"Jordon, D., Evdemon, J.: Web services business process execution language, version 2.0, OASIS standard. Tech. rep., OASIS (2007)"},{"key":"7105_CR24","unstructured":"Language and Architecture Team, ADMIRE project: DISPEL: data-intensive systems process engineering language users\u2019 manual (version 1.0). Tech. rep., School of Informatics, University of Edinburgh (2011)"},{"key":"7105_CR25","unstructured":"Lee, E.A., Neuendorffer, S.: MoML\u2014a Modeling Markup Language in XML\u2013version 0.4. Tech. rep., University of California at Berkeley (2000)"},{"issue":"1949","key":"7105_CR26","doi-asserted-by":"crossref","first-page":"3268","DOI":"10.1098\/rsta.2011.0134","volume":"369","author":"C.S. Liew","year":"2011","unstructured":"Liew, C.S., Atkinson, M.P., Ostrowski, R., Cole, M., van Hemert, J.I., Han, L.: Performance database: capturing data for optimizing distributed streaming workflows. Philos. Trans. R. Soc. Lond. A 369(1949), 3268\u20133284 (2011)","journal-title":"Philos. Trans. R. Soc. Lond. A"},{"key":"7105_CR27","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1109\/eScience.2008.172","volume-title":"IEEE Fourth International Conference on eScience","author":"X. Llor\u00e1","year":"2008","unstructured":"Llor\u00e1, X., \u00c1cs, B., Auvil, L.S., Capitanu, B., Welge, M.E., Goldberg, D.E.: Meandre: semantic-driven data-intensive flows in the clouds. In: IEEE Fourth International Conference on eScience, pp. 238\u2013245. IEEE Press, New York (2008)"},{"issue":"10","key":"7105_CR28","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1002\/cpe.994","volume":"18","author":"B. Lud\u00e4scher","year":"2006","unstructured":"Lud\u00e4scher, B., Altintas, I., Berkley, C., Higgins, D., Jaeger, E., Jones, M., Lee, E.A., Tao, J., Zhao,\u00a0Y.: Scientific workflow management and the Kepler system. Concurr. Comput. 18(10), 1039\u20131065 (2006)","journal-title":"Concurr. Comput."},{"issue":"2","key":"7105_CR29","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1561\/0400000002","volume":"1","author":"S. Muthukrishnan","year":"2005","unstructured":"Muthukrishnan, S.: Data streams: algorithms and applications. Found. Trends Theor. Comput. Sci. 1(2), 117\u2013236 (2005)","journal-title":"Found. Trends Theor. Comput. Sci."},{"issue":"17","key":"7105_CR30","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1093\/bioinformatics\/bth361","volume":"20","author":"T. Oinn","year":"2004","unstructured":"Oinn, T., Addis, M., Ferris, J., Marvin, D., Senger, M., Greenwood, M., Carver, T., Glover, K., Pocock, M.R., Wipat, A., Li, P.: Taverna: a tool for the composition and enactment of bioinformatics workflows. Bioinformatics 20(17), 3045\u20133054 (2004)","journal-title":"Bioinformatics"},{"key":"7105_CR31","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1145\/1376616.1376726","volume-title":"Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data","author":"C. Olston","year":"2008","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig Latin: a not-so-foreign language for data processing. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD \u201908, pp. 1099\u20131110. ACM, New York (2008)"},{"key":"7105_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CLUSTR.2009.5289160","volume-title":"Proceedings of the IEEE International Conference on Cluster Computing and Workshops","author":"S. Pallickara","year":"2009","unstructured":"Pallickara, S., Ekanayake, J., Fox, G.: Granules: a lightweight, streaming runtime for cloud computing with support for map-reduce. In: Proceedings of the IEEE International Conference on Cluster Computing and Workshops, CLUSTER \u201909, pp. 1\u201310 (2009)"},{"issue":"4","key":"7105_CR33","first-page":"227","volume":"13","author":"R. Pike","year":"2005","unstructured":"Pike, R., Dorward, S., Griesemer, R., Quinlan, S.: Interpreting the data: parallel analysis with Sawzall. Sci. Program. 13(4), 227\u2013298 (2005)","journal-title":"Sci. Program."},{"key":"7105_CR34","volume-title":"Conference on Innovative Data Systems Research","author":"M. Stonebraker","year":"2009","unstructured":"Stonebraker, M., Becla, J., Dewitt, D., Lim, K.T., Maier, D., Ratzesberger, O., Zdonik, S.: Requirements for science data bases and SciDB. In: Conference on Innovative Data Systems Research (CIDR) (2009)"},{"key":"7105_CR35","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1007\/978-1-84628-757-2_20","volume-title":"Workflows for e-Science","author":"I. Taylor","year":"2007","unstructured":"Taylor, I., Shields, M., Wang, I., Harrison, A.: The Triana workflow environment: architecture and applications. In: Taylor, I., Deelman, E., Gannon, D., Shields, M. (eds.) Workflows for e-Science, pp.\u00a0320\u2013339. Springer, London (2007)"},{"key":"7105_CR36","series-title":"Lecture Notes in Computer Science","first-page":"49","volume-title":"Compiler Construction","author":"W. Thies","year":"2002","unstructured":"Thies, W., Karczmarek, M., Amarasinghe, S.: StreamIt: a language for streaming applications. In: Horspool, R. (ed.) Compiler Construction. Lecture Notes in Computer Science, vol. 2304, pp. 49\u201384. Springer, Berlin (2002)"},{"issue":"9","key":"7105_CR37","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1016\/j.parco.2011.05.005","volume":"37","author":"M. Wilde","year":"2011","unstructured":"Wilde, M., Hategan, M., Wozniak, J.M., Clifford, B., Katz, D.S., Foster, I.: Swift: a language for distributed parallel scripting. Parallel Comput. 37(9), 633\u2013652 (2011)","journal-title":"Parallel Comput."},{"issue":"1949","key":"7105_CR38","doi-asserted-by":"crossref","first-page":"3285","DOI":"10.1098\/rsta.2011.0135","volume":"369","author":"G. Yaikhom","year":"2011","unstructured":"Yaikhom, G., Atkinson, M.P., van Hemert, J.I., Corcho, O., Krause, A.: Validation and mismatch repair of workflows through typed data streams. Philos. Trans. R. Soc. Lond. A 369(1949), 3285\u20133299 (2011)","journal-title":"Philos. Trans. R. Soc. Lond. A"},{"key":"7105_CR39","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10723-005-9010-8","volume":"3","author":"J. Yu","year":"2005","unstructured":"Yu, J., Buyya, R.: A taxonomy of workflow management systems for grid computing. J. Grid Comput. 3, 171\u2013200 (2005)","journal-title":"J. Grid Comput."},{"key":"7105_CR40","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1109\/SERVICES.2007.63","volume-title":"Proceedings of the 2007 IEEE Congress on Services","author":"Y. Zhao","year":"2007","unstructured":"Zhao, Y., Hategan, M., Clifford, B., Foster, I., von Laszewski, G., Nefedova, V., Raicu, I., Stef-Praun,\u00a0T., Wilde, M.: Swift: fast, reliable, loosely coupled parallel computation. In: Proceedings of the 2007 IEEE Congress on Services, SERVICES \u201907, pp. 199\u2013206. IEEE Comput. Soc., Los Alamitos (2007)"}],"container-title":["Distributed and Parallel Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-012-7105-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10619-012-7105-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-012-7105-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T19:29:50Z","timestamp":1559244590000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10619-012-7105-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,8,21]]},"references-count":40,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2012,10]]}},"alternative-id":["7105"],"URL":"https:\/\/doi.org\/10.1007\/s10619-012-7105-3","relation":{},"ISSN":["0926-8782","1573-7578"],"issn-type":[{"value":"0926-8782","type":"print"},{"value":"1573-7578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,8,21]]}}}