{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T04:37:18Z","timestamp":1714192638681},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,4,11]],"date-time":"2013-04-11T00:00:00Z","timestamp":1365638400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1007\/s11227-013-0924-9","type":"journal-article","created":{"date-parts":[[2013,4,10]],"date-time":"2013-04-10T14:35:33Z","timestamp":1365604533000},"page":"539-555","source":"Crossref","is-referenced-by-count":28,"title":["An improved partitioning mechanism for optimizing massive data analysis using MapReduce"],"prefix":"10.1007","volume":"66","author":[{"given":"Kenn","family":"Slagter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Hsien","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeh-Ching","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,4,11]]},"reference":[{"issue":"1","key":"924_CR1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/MMUL.2010.70","volume":"18","author":"KS Candan","year":"2010","unstructured":"Candan KS, Kim JW, Nagarkar P, Nagendra M, Yu R (2010) RanKloud: scalable multimedia data processing in server clusters. IEEE MultiMed 18(1):64\u201377","journal-title":"IEEE MultiMed"},{"key":"924_CR2","first-page":"205","volume-title":"7th UENIX symposium on operating systems design and implementation","author":"F Chang","year":"2006","unstructured":"Chang F, Dean J, Ghemawat S, Hsieh WC, Wallach DA, Burrws M, Chandra T, Fikes A, Gruber RE (2006) Bigtable: a distributed storage system for structured data. In: 7th UENIX symposium on operating systems design and implementation, pp 205\u2013218"},{"key":"924_CR3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, GhemawatDean S (2008) MapReduce: simplified data processing on large clusters. Commun ACM 51:107\u2013113","journal-title":"Commun ACM"},{"key":"924_CR4","volume-title":"19th ACM symposium on operating systems principles (SOSP)","author":"S Ghemawat","year":"2003","unstructured":"Ghemawat S, Gobioff H, Leung S-T (2003) The Google file system. In: 19th ACM symposium on operating systems principles (SOSP)"},{"key":"924_CR5","first-page":"475","volume-title":"IEEE\/ACM international symposium on cluster, cloud and grid computing","author":"W Jiang","year":"2011","unstructured":"Jiang W, Agrawal G (2011) Ex-MATE data intensive computing with large reduction objects and its application to graph mining. In: IEEE\/ACM international symposium on cluster, cloud and grid computing, pp 475\u2013484"},{"key":"924_CR6","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/eScience.2008.78","volume-title":"IEEE fourth international conference on escience","author":"C Jin","year":"2008","unstructured":"Jin C, Vecchiola C, Buyya R (2008) MRPGA: an extension of MapReduce for parallelizing genetic algorithms. In: IEEE fourth international conference on escience, pp 214\u2013220"},{"key":"924_CR7","first-page":"94","volume-title":"IEEE\/ACM international conference on cluster, cloud and grid computing","author":"S Kavulya","year":"2010","unstructured":"Kavulya S, Tany J, Gandhi R, Narasimhan P (2010) An analysis of traces from a production MapReduce cluster. In: IEEE\/ACM international conference on cluster, cloud and grid computing, pp 94\u201395"},{"issue":"13","key":"924_CR8","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1002\/cpe.906","volume":"17","author":"A Krishnan","year":"2005","unstructured":"Krishnan A (2005) GridBLAST: a globus-based high-throughput implementation of BLAST in a grid computing framework. Concurr Comput 17(13):1607\u20131623","journal-title":"Concurr Comput"},{"key":"924_CR9","first-page":"464","volume-title":"IEEE\/ACM international symposium on cluster, cloud and grid computing","author":"H Liu","year":"2011","unstructured":"Liu H, Orban D (2011) Cloud MapReduce: a MapReduce implementation on top of a cloud operating system. In: IEEE\/ACM international symposium on cluster, cloud and grid computing, pp 464\u2013474"},{"issue":"3","key":"924_CR10","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1007\/s11227-010-0463-6","volume":"60","author":"C-H Hsu","year":"2012","unstructured":"Hsu C-H, Chen S-C (2012) Efficient selection strategies towards processor reordering techniques for improving data locality in heterogeneous clusters. J Supercomput 60(3):284\u2013300","journal-title":"J Supercomput"},{"key":"924_CR11","first-page":"489","volume-title":"IEEE fourth international conference on escience","author":"A Matsunaga","year":"2008","unstructured":"Matsunaga A, Tsugawa M, Fortes J (2008) Programming abstractions for data intensive computing on clouds and grids. In: IEEE fourth international conference on escience, pp 489\u2013493"},{"key":"924_CR12","first-page":"480","volume-title":"IEEE\/ACM international symposium on cluster computing and the grid","author":"C Miceli","year":"2009","unstructured":"Miceli C, Miceli M, Jha S, Kaiser H, Merzky A (2009) Programming abstractions for data intensive computing on clouds and grids. In: IEEE\/ACM international symposium on cluster computing and the grid, pp 480\u2013483"},{"key":"924_CR13","first-page":"452","volume-title":"International conference on data engineering","author":"B Panda","year":"2010","unstructured":"Panda B, Riedewald M, Fink D (2010) The model-summary problem and a solution for trees. In: International conference on data engineering, pp 452\u2013455"},{"key":"924_CR14","first-page":"519","volume-title":"IEEE international conference on data mining","author":"S Papadimitriou","year":"2008","unstructured":"Papadimitriou S, Sun J (2008) Distributed co-clustering with map-reduce. In: IEEE international conference on data mining, p 519"},{"issue":"4","key":"924_CR15","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1504\/IJAHUC.2010.035537","volume":"6","author":"C-H Hsu","year":"2010","unstructured":"Hsu C-H, Chen SC (2010) A two-level scheduling strategy for optimizing communications of data parallel programs in clusters. Int J Ad Hoc Ubiq Comput 6(4):263\u2013269","journal-title":"Int J Ad Hoc Ubiq Comput"},{"key":"924_CR16","first-page":"123","volume-title":"IEEE international symposium on performance analysis of system and software (ISPASS)","author":"J Shafer","year":"2010","unstructured":"Shafer J, Rixner S, Cox AL (2010) The hadoop distributed filesystem: balancing portability and performance. In: IEEE international symposium on performance analysis of system and software (ISPASS), p 123"},{"key":"924_CR17","volume-title":"IEEE international conference on e-science and grid computing","author":"H Stockinger","year":"2006","unstructured":"Stockinger H, Pagni M, Cerutti L, Falquet L (2006) Grid approach to embarrassingly parallel CPU-intensive bioinformatics problems. In: IEEE international conference on e-science and grid computing"},{"key":"924_CR18","volume-title":"USENIX workshop on hot topics in cloud computing (HotCloud)","author":"J Tan","year":"2009","unstructured":"Tan J, Pan X, Kavulya S, Gandhi R, Narasimhan P (2009) Mochi: visual log-analysis based tools for debugging hadoop. In: USENIX workshop on hot topics in cloud computing (HotCloud)"},{"issue":"3","key":"924_CR19","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s11227-008-0261-6","volume":"50","author":"C-H Hsu","year":"2009","unstructured":"Hsu C-H, Tsai B-R (2009) Scheduling for atomic broadcast operation in heterogeneous networks with one port model. J Supercomput 50(3):269\u2013288","journal-title":"J Supercomput"},{"key":"924_CR20","first-page":"110","volume-title":"IEEE world congress on services","author":"H Vashishtha","year":"2010","unstructured":"Vashishtha H, Smit M, Stroulia E (2010) Moving text analysis tools to the cloud. In: IEEE world congress on services, pp 110\u2013112"},{"key":"924_CR21","volume-title":"International conference on intelligent systems design and applications","author":"A Verma","year":"2009","unstructured":"Verma A, Llor\u2019a X, Goldberg DE, Campbell RH (2009) Scaling genetic algorithms using MapReduce. In: International conference on intelligent systems design and applications"},{"key":"924_CR22","volume-title":"Proceedings of the ACM SIGOPS 22nd symposium on operating systems principles (SOSP)","author":"W Xu","year":"2009","unstructured":"Xu W, Huang L, Fox A, Patterson D, Jordan M (2009) Detecting large-scale system problems by mining console logs. In: Proceedings of the ACM SIGOPS 22nd symposium on operating systems principles (SOSP)"},{"key":"924_CR23","first-page":"454","volume-title":"IEEE\/ACM international symposium on cluster, cloud and grid computing","author":"Z Fadika","year":"2011","unstructured":"Fadika Z, Govindaraju M (2011) DELMA: dynamic elastic MapReduce framework for CPU-intensive applications. In: IEEE\/ACM international symposium on cluster, cloud and grid computing, pp 454\u2013463"},{"key":"924_CR24","unstructured":"O\u2019Malley O (2008) TeraByte sort on Apache hadoop"},{"key":"924_CR25","unstructured":"Apache software foundation (2007) Hadoop. http:\/\/hadoop.apache.org\/core"},{"issue":"1","key":"924_CR26","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s11227-008-0211-3","volume":"45","author":"C-H Hsu","year":"2008","unstructured":"Hsu C-H, Chen T-L, Park J-H (2008) On improving resource utilization and system throughput of master slave jobs scheduling in heterogeneous systems. J Supercomput 45(1):129\u2013150","journal-title":"J Supercomput"},{"key":"924_CR27","unstructured":"HBase. http:\/\/hadoop.apache.org\/hbase\/"},{"key":"924_CR28","volume-title":"OSDI","author":"M Zaharia","year":"2008","unstructured":"Zaharia M, Konwinski A, Joseph AD, Katz R, Stoica I (2008) Improving MapReduce performance in heterogeneous environments. In: OSDI"},{"key":"924_CR29","first-page":"713","volume-title":"IEEE international conference on cloud computing technology and science","author":"S Lynden","year":"2011","unstructured":"Lynden S, Tanimura Y, Kojima I, Matono A (2011) Dynamic data redistribution for MapReduce joins. In: IEEE international conference on cloud computing technology and science, pp 713\u2013717"},{"key":"924_CR30","volume-title":"VLDB, PhD workshop","author":"S Groot","year":"2010","unstructured":"Groot S, Kitsuregawa M (2010) Jumbo: beyond MapReduce for workload balancing. In: VLDB, PhD workshop"},{"issue":"12","key":"924_CR31","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1145\/506309.506312","volume":"20","author":"S Heinz","year":"2002","unstructured":"Heinz S, Zobel J, Williams H (2002) Burst tries: a fast, efficient data structure for string keys. ACM Trans Inf Syst 20(12):192\u2013223","journal-title":"ACM Trans Inf Syst"},{"issue":"3","key":"924_CR32","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s11227-006-0024-1","volume":"40","author":"C-H Hsu","year":"2007","unstructured":"Hsu C-H, Chen S-C, Lan C-Y (2007) Scheduling contention-free irregular redistribution in parallelizing compilers. J Supercomput 40(3):229\u2013247","journal-title":"J Supercomput"},{"key":"924_CR33","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1002\/j.1538-7305.1951.tb01366.x","volume":"30","author":"CE Shannon","year":"1951","unstructured":"Shannon CE (1951) Prediction and entropy of printed English. Bell Syst Tech J 30:50\u201364","journal-title":"Bell Syst Tech J"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-0924-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-013-0924-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-0924-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T10:24:09Z","timestamp":1559384649000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-013-0924-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,11]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,10]]}},"alternative-id":["924"],"URL":"https:\/\/doi.org\/10.1007\/s11227-013-0924-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,11]]}}}