{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T20:26:08Z","timestamp":1725999968501},"publisher-location":"Berlin, Heidelberg","reference-count":46,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662583838"},{"type":"electronic","value":"9783662583845"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-662-58384-5_5","type":"book-chapter","created":{"date-parts":[[2018,11,21]],"date-time":"2018-11-21T10:27:33Z","timestamp":1542796053000},"page":"119-145","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Query Processing Framework for Large-Scale Scientific Data Analysis"],"prefix":"10.1007","author":[{"given":"Leonidas","family":"Fegaras","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,22]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Armbrust, M., et al.: Spark SQL: relational data processing in spark. In: SIGMOD 2015 (2015)","DOI":"10.1145\/2723372.2742797"},{"key":"5_CR2","unstructured":"Apache Flink (2018). http:\/\/flink.apache.org\/"},{"key":"5_CR3","unstructured":"Apache Hadoop (2018). http:\/\/hadoop.apache.org\/"},{"key":"5_CR4","unstructured":"Apache Hama (2018). http:\/\/hama.apache.org\/"},{"key":"5_CR5","unstructured":"Apache Hive (2018). http:\/\/hive.apache.org\/"},{"key":"5_CR6","unstructured":"Apache Giraph (2018). http:\/\/giraph.apache.org\/"},{"key":"5_CR7","unstructured":"GraphX: Apache Spark\u2019s API for Graphs and Graph-Parallel Computation (2018). https:\/\/spark.apache.org\/graphx\/"},{"key":"5_CR8","unstructured":"Apache MRQL (incubating) (2018). http:\/\/mrql.incubator.apache.org\/"},{"key":"5_CR9","unstructured":"Apache Spark (2018). http:\/\/spark.apache.org\/"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Battre, D., Ewen, S., Hueske, F., Kao, O., Markl, V., Warneke, D.: Nephele\/PACTs: a programming model and execution framework for web-scale analytical processing. In: 1st ACM Symposium on Cloud computing (SOCC 2010), pp. 119\u2013130 (2010)","DOI":"10.1145\/1807128.1807148"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Buck, J., et al.: SciHadoop: array-based query processing in hadoop. In: International Conference for High Performance Computing, Networking, Storage and Analysis (SC) (2011)","DOI":"10.1145\/2063384.2063473"},{"issue":"2","key":"5_CR12","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.14778\/1454159.1454166","volume":"1","author":"R Chaiken","year":"2008","unstructured":"Chaiken, R., et al.: SCOPE: easy and efficient parallel processing of massive data sets. Proc. VLDB Endow. (PVLDB) 1(2), 1265\u20131276 (2008)","journal-title":"Proc. VLDB Endow. (PVLDB)"},{"key":"5_CR13","unstructured":"A. Das, F.N. Afrati, S. Salihoglu, and J.D. Ullman. Upper and lower bounds on the cost of a map-reduce computation. In VLDB 2013 (2013)"},{"key":"5_CR14","unstructured":"Dean, J., Ghemawat, S.: MapReduce: Simplified data processing on large clusters. In: OSDI 2004 (2004)"},{"key":"5_CR15","unstructured":"Fan, J., et al.: The case against specialized graph analytics engines. In: CIDR (2015)"},{"key":"5_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-44403-1_15","volume-title":"Database and Expert Systems Applications","author":"L Fegaras","year":"2016","unstructured":"Fegaras, L.: A query processing framework for array-based computations. In: Hartmann, S., Ma, H. (eds.) DEXA 2016, Part I. LNCS, vol. 9827, pp. 240\u2013254. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-44403-1_15"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Fegaras, L.: An Algebra for Distributed Big Data Analytics. Journal of Functional Programming, Special issue on Programming Languages for Big Data, Volume 27 (2017)","DOI":"10.1017\/S0956796817000193"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Fegaras, L., Li, C., Gupta, U.: An optimization framework for map-reduce queries. In: EDBT 2012 (2012)","DOI":"10.1145\/2247596.2247601"},{"key":"5_CR19","unstructured":"Fegaras, L., Li, C., Gupta, U., Philip, J.J.: XML query optimization in map-reduce. In: International Workshop on the Web and Databases (WebDB) (2011)"},{"issue":"2","key":"5_CR20","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1145\/568271.223789","volume":"24","author":"Leonidas Fegaras","year":"1995","unstructured":"Fegaras, L., Maier, D.: Towards an effective calculus for object query languages. In: International Conference on Management of Data (SIGMOD), pp. 47\u201358 (1995)","journal-title":"ACM SIGMOD Record"},{"issue":"4","key":"5_CR21","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1145\/377674.377676","volume":"25","author":"L Fegaras","year":"2000","unstructured":"Fegaras, L., Maier, D.: Optimizing object queries using an effective calculus. ACM Trans. Database Syst. (TODS) 25(4), 457\u2013516 (2000)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Folk, M., Heber, G., Koziol, Q., Pourmal, E., Robinson, D.: An overview of the HDF5 technology suite and its applications. In: EDBT\/ICDT Workshop on Array Databases (2011)","DOI":"10.1145\/1966895.1966900"},{"issue":"2","key":"5_CR23","doi-asserted-by":"publisher","first-page":"1414","DOI":"10.14778\/1687553.1687568","volume":"2","author":"AF Gates","year":"2009","unstructured":"Gates, A.F., et al.: Building a high-level dataflow system on top of map-reduce: the pig experience. Proc. VLDB Endow. (PVLDB) 2(2), 1414\u20131425 (2009)","journal-title":"Proc. VLDB Endow. (PVLDB)"},{"issue":"4","key":"5_CR24","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","volume":"9","author":"RA Geijn","year":"1997","unstructured":"Geijn, R.A., Watts, J.: SUMMA: scalable universal matrix multiplication algorithm. Concurr. Pract. Exp. 9(4), 255\u2013274 (1997)","journal-title":"Concurr. Pract. Exp."},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Geng, Y., Huang, X., Zhu, M., Ruan, H., Yang, G.: SciHive: array-based query processing with HiveQL. In: IEEE International Conference on Trust, Security and Privacy in Computing and Communications (Trustcom) (2013)","DOI":"10.1109\/TrustCom.2013.108"},{"issue":"13","key":"5_CR26","first-page":"1669","volume":"7","author":"A Jindal","year":"2014","unstructured":"Jindal, A., et al.: Vertexica: your relational friend for graph analytics!. PVLDB 7(13), 1669\u20131672 (2014)","journal-title":"PVLDB"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Ghoting, A., et al.: SystemML: declarative machine learning on mapreduce. In: IEEE International Conference on Data Engineering (ICDE) (2011)","DOI":"10.1109\/ICDE.2011.5767930"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Isard, M., Yu, Y.: Distributed data-parallel computing using a high-level programming language. In: ACM SIGMOD International Conference on Management of Data, pp. 987\u2013994 (2009)","DOI":"10.1145\/1559845.1559962"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. In: IEEE Computer, August 2009","DOI":"10.1109\/MC.2009.263"},{"key":"5_CR30","unstructured":"Kraska, T., Talwalkar, A., Duchi, J., Griffith, R., Franklin, M., Jordan, M.I.: MLbase: a distributed machine learning system. In: Conference on Innovative Data Systems Research (2013)"},{"key":"5_CR31","doi-asserted-by":"publisher","DOI":"10.2200\/S00274ED1V01Y201006HLT007","volume-title":"Data-Intensive Text Processing with MapReduce","author":"J Lin","year":"2010","unstructured":"Lin, J., Dyer, C.: Data-Intensive Text Processing with MapReduce. Morgan & Claypool Publishers, San Rafael (2010)"},{"issue":"8","key":"5_CR32","doi-asserted-by":"publisher","first-page":"716","DOI":"10.14778\/2212351.2212354","volume":"5","author":"Yucheng Low","year":"2012","unstructured":"Low, Y., Gonzalez, J., Kyrola, A., Bickson, D., Guestrin, C., Hellerstein, J.M.: Distributed GraphLab: a framework for machine learning and data mining in the cloud. In: VLDB 2012 (2012)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Malewicz, G., et al.: Pregel: a system for large-scale graph processing. In: ACM SIGMOD International Conference on Management of Data, pp. 135\u2013146 (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"5_CR34","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng, X., Bradley, J., Yavuz, B., et al.: MLlib: machine learning in apache spark. J. Mach. Learn. Res. 17, 1\u20137 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR35","unstructured":"NetCDF: Network Common Data Form. https:\/\/www.unidata.ucar.edu\/software\/netcdf\/"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig Latin: a not-so-Foreign language for data processing. In: ACM SIGMOD International Conference on Management of Data (2008)","DOI":"10.1145\/1376616.1376726"},{"issue":"4","key":"5_CR37","first-page":"349","volume":"10","author":"S Papadopoulos","year":"2016","unstructured":"Papadopoulos, S., Datta, K., Madden, S., Mattson, T.: The TileDB array data storage manager. PVLDB 10(4), 349\u2013360 (2016)","journal-title":"PVLDB"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Soroush, E., Balazinska, M., Wang, D.: ArrayStore: a storage manager for complex parallel array processing. In: ACM SIGMOD International Conference on Management of Data (2011)","DOI":"10.1145\/1989323.1989351"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Soroush, E., Balazinska, M., Krughoff, S., Connolly, A.: Efficient iterative processing in the SciDB parallel array engine. In: 27th International Conference on Scientific and Statistical Database Management (SSDBM) (2015)","DOI":"10.1145\/2791347.2791362"},{"issue":"12","key":"5_CR40","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.14778\/2367502.2367513","volume":"5","author":"Avraham Shinnar","year":"2012","unstructured":"Shinnar, A., Cunningham, D., Herta, B., Saraswat, B.: M3R: Increased performance for in-memory Hadoop jobs. In: VLDB 2012 (2012)","journal-title":"Proceedings of the VLDB Endowment"},{"key":"5_CR41","unstructured":"The SciDB Development Team. Overview of SciDB: large scale array storage, processing and analysis. In: ACM SIGMOD International Conference on Management of Data (2010)"},{"issue":"2","key":"5_CR42","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.14778\/1687553.1687609","volume":"2","author":"A Thusoo","year":"2009","unstructured":"Thusoo, A., et al.: Hive: a warehousing solution over a map-reduce framework. Proc. VLDB Endow. (PVLDB) 2(2), 1626\u20131629 (2009)","journal-title":"Proc. VLDB Endow. (PVLDB)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Thusoo, A., et al.: Hive: a petabyte scale data warehouse using hadoop. In: IEEE International Conference on Data Engineering (ICDE), pp. 996\u20131005 (2010)","DOI":"10.1109\/ICDE.2010.5447738"},{"issue":"8","key":"5_CR44","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant, L.G.: A bridging model for parallel computation. CACM 33(8), 103\u2013111 (1990)","journal-title":"CACM"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Jiang, W., Agrawal, G.: SciMATE: a novel MapReduce-like framework for multiple scientific data formats. In: IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) (2012)","DOI":"10.1109\/CCGrid.2012.32"},{"key":"5_CR46","unstructured":"Yu, Y., et al.: DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language. In: Symposium on Operating Systems Design and Implementation (OSDI) (2008)"}],"container-title":["Lecture Notes in Computer Science","Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXVIII"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-58384-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,5]],"date-time":"2019-11-05T20:36:58Z","timestamp":1572986218000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-58384-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783662583838","9783662583845"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-58384-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}