{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:28:50Z","timestamp":1706056130558},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,7,19]],"date-time":"2015-07-19T00:00:00Z","timestamp":1437264000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Journal of Big Data"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s40537-015-0021-4","type":"journal-article","created":{"date-parts":[[2015,7,18]],"date-time":"2015-07-18T01:23:00Z","timestamp":1437182580000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Meta-MapReduce for scalable data mining"],"prefix":"10.1186","volume":"2","author":[{"given":"Xuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stan","family":"Matwin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathalie","family":"Japkowicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,19]]},"reference":[{"issue":"1","key":"21_CR1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1002\/widm.1078","volume":"3","author":"J Bacardit","year":"2013","unstructured":"Bacardit J, Llor\u00e0 X (2013) Large-scale data mining using genetics-based machine learning. Wiley Interdiscip Rev Data Min Knowl Disc 3(1): 37\u201361.","journal-title":"Wiley Interdiscip Rev Data Min Knowl Disc"},{"key":"21_CR2","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1145\/1631272.1631451","volume-title":"Proceedings of the 17th ACM International Conference on Multimedia","author":"EY Chang","year":"2009","unstructured":"Chang EY, Bai H, Zhu K (2009) Parallel algorithms for mining large-scale rich-media data In: Proceedings of the 17th ACM International Conference on Multimedia, 917\u2013918.. ACM, New York, NY, USA."},{"issue":"1","key":"21_CR3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) Mapreduce: simplified data processing on large clusters. Commun ACM 51(1): 107\u2013113.","journal-title":"Commun ACM"},{"key":"21_CR4","volume-title":"Hadoop: The Definitive Guide","author":"T White","year":"2012","unstructured":"White T (2012) Hadoop: The Definitive Guide. \" O\u2019Reilly Media, Inc.\", California."},{"key":"21_CR5","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4302-1943-9","volume-title":"Pro Hadoop. vol. 1","author":"J Venner","year":"2009","unstructured":"Venner J, Cyrus S (2009) Pro Hadoop. vol. 1. Springer, New York."},{"key":"21_CR6","volume-title":"Hadoop in Action","author":"C Lam","year":"2010","unstructured":"Lam C (2010) Hadoop in Action. Manning Publications Co., New York."},{"key":"21_CR7","doi-asserted-by":"crossref","first-page":"281","DOI":"10.7551\/mitpress\/7503.003.0040","volume":"19","author":"C Chu","year":"2007","unstructured":"Chu C, Kim SK, Lin YA, Yu Y, Bradski G, Ng AY, Olukotun K (2007) Map-reduce for machine learning on multicore. Adv neural Info processing systems 19: 281.","journal-title":"Adv neural Info processing systems"},{"issue":"6","key":"21_CR8","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1145\/293347.293351","volume":"45","author":"M Kearns","year":"1998","unstructured":"Kearns M (1998) Efficient noise-tolerant learning from statistical queries. J ACM (JACM) 45(6): 983\u20131006.","journal-title":"J ACM (JACM)"},{"issue":"2","key":"21_CR9","doi-asserted-by":"crossref","first-page":"1426","DOI":"10.14778\/1687553.1687569","volume":"2","author":"B Panda","year":"2009","unstructured":"Panda B, Herbach JS, Basu S, Bayardo RJ (2009) Planet: massively parallel learning of tree ensembles with mapreduce. Proc. VLDB Endowment 2(2): 1426\u20131437.","journal-title":"Proc. VLDB Endowment"},{"issue":"10","key":"21_CR10","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TKDE.2011.208","volume":"24","author":"I Palit","year":"2012","unstructured":"Palit I, Reddy CK (2012) Scalable and parallel boosting with mapreduce. IEEE Trans Knowl Data Eng 24(10): 1904\u20131916.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Jin C, Vecchiola C, Buyya R (2008) Mrpga: an extension of mapreduce for parallelizing genetic algorithms In: eScience, 2008. eScience\u201908. IEEE Fourth International Conference On, 214\u2013221.. IEEE.","DOI":"10.1109\/eScience.2008.78"},{"key":"21_CR12","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1145\/1645953.1646301","volume-title":"Proceedings of the 18th ACM Conference on Information and Knowledge Management","author":"J Ye","year":"2009","unstructured":"Ye J, Chow JH, Chen J, Zheng Z (2009) Stochastic gradient boosted distributed decision trees In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, 2061\u20132064.. ACM, New York, NY, USA."},{"key":"21_CR13","unstructured":"Weimer M, Rao S, Zinkevich M (2010) A convenient framework for efficient parallel multipass algorithms In: LCCC: NIPS 2010 Workshop on Learning on Cores, Clusters and Clouds."},{"key":"21_CR14","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1145\/1807167.1807184","volume-title":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data","author":"G Malewicz","year":"2010","unstructured":"Malewicz G, Austern MH, Bik AJ, Dehnert JC, Horn I, Leiser N, Czajkowski G (2010) Pregel: a system for large-scale graph processing In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, 135\u2013146.. ACM, New York, NY, USA."},{"issue":"1-2","key":"21_CR15","doi-asserted-by":"crossref","first-page":"285","DOI":"10.14778\/1920841.1920881","volume":"3","author":"Y Bu","year":"2010","unstructured":"Bu Y, Howe B, Balazinska M, Ernst MD (2010) Haloop: Efficient iterative data processing on large clusters. Proc of the VLDB Endowment 3(1-2): 285\u2013296.","journal-title":"Proc of the VLDB Endowment"},{"key":"21_CR16","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1145\/1851476.1851593","volume-title":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","author":"J Ekanayake","year":"2010","unstructured":"Ekanayake J, Li H, Zhang B, Gunarathne T, Bae SH, Qiu J, Fox G (2010) Twister: a runtime for iterative mapreduce In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, 810\u2013818.. ACM, New York, NY, USA."},{"key":"21_CR17","first-page":"1111","volume":"15","author":"A Agarwal","year":"2014","unstructured":"Agarwal A, Chapelle O, Dud\u00edk M, Langford J (2014) A reliable effective terascale linear learning system. J Mach Learn Res 15: 1111\u20131133.","journal-title":"J Mach Learn Res"},{"key":"21_CR18","first-page":"2","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation","author":"M Zaharia","year":"2012","unstructured":"Zaharia M, Chowdhury M, Das T, Dave A, Ma J, McCauley M, Franklin MJ, Shenker S, Stoica I (2012) Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, 2\u20132.. USENIX Association, Berkeley, CA, USA."},{"key":"21_CR19","unstructured":"Rosen J, Polyzotis N, Borkar V, Bu Y, Carey MJ, Weimer M, Condie T, Ramakrishnan R (2013) Iterative mapreduce for large scale machine learning. arXiv preprint arXiv:1303.3517."},{"issue":"2","key":"21_CR20","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1019956318069","volume":"18","author":"R Vilalta","year":"2002","unstructured":"Vilalta R, Drissi Y (2002) A perspective view and survey of meta-learning. Artif Intell Rev 18(2): 77\u201395.","journal-title":"Artif Intell Rev"},{"key":"21_CR21","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1007\/978-3-642-38457-8_27","volume-title":"Advances in Artificial Intelligence","author":"X Liu","year":"2013","unstructured":"Liu X, Wang X, Japkowicz N, Matwin S (2013) An ensemble method based on adaboost and meta-learning In: Advances in Artificial Intelligence, 278\u2013285.. Springer, Springer Berlin Heidelberg."},{"key":"21_CR22","unstructured":"Page L, Brin S, Motwani R, Winograd T (1999) The pagerank citation ranking: Bringing order to the web. Technical Report. Stanford InfoLab, pp. 1999\u20131966. http:\/\/ilpubs.stanford.edu:8090\/422\/ ."},{"key":"21_CR23","volume-title":"An Amateur\u2019s Introduction to Recursive Query Processing Strategies. vol. 15","author":"F Bancilhon","year":"1986","unstructured":"Bancilhon F, Ramakrishnan R (1986) An Amateur\u2019s Introduction to Recursive Query Processing Strategies. vol. 15. ACM, New York, NY, USA."},{"key":"21_CR24","first-page":"10","volume-title":"Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing","author":"M Zaharia","year":"2010","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I (2010) Spark: cluster computing with working sets In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, 10\u201310.. USENIX Association, Berkeley, CA, USA."},{"key":"21_CR25","first-page":"59","volume-title":"ACM SIGOPS Operating Systems Review","author":"M Isard","year":"2007","unstructured":"Isard M, Budiu M, Yu Y, Birrell A, Fetterly D (2007) Dryad: distributed data-parallel programs from sequential building blocks In: ACM SIGOPS Operating Systems Review, 59\u201372.. ACM, New York, NY, USA."},{"key":"21_CR26","first-page":"26","volume-title":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics","author":"M Banko","year":"2001","unstructured":"Banko M, Brill E (2001) Scaling to very very large corpora for natural language disambiguation In: Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, 26\u201333.. Association for Computational Linguistics, Stroudsburg, PA, USA."},{"issue":"2","key":"21_CR27","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy A, Norvig P, Pereira F (2009) The unreasonable effectiveness of data. IEEE Intell Syst 24(2): 8\u201312.","journal-title":"IEEE Intell Syst"},{"key":"21_CR28","unstructured":"Amazon Elastic Compute Cloud:Amazon EC2. http:\/\/aws.amazon.com\/ec2\/ ."},{"key":"21_CR29","unstructured":"Cloudera. http:\/\/www.cloudera.com\/ ."},{"key":"21_CR30","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139058452","volume-title":"Mining of Massive Datasets","author":"A Rajaraman","year":"2011","unstructured":"Rajaraman A, Ullman JD (2011) Mining of Massive Datasets. Cambridge University Press, Cambridge."},{"key":"21_CR31","volume-title":"The Need for Biases in Learning Generalizations","author":"T Mitchell","year":"1980","unstructured":"Mitchell T (1980) The Need for Biases in Learning Generalizations. Department of Computer Science, Laboratory for Computer Science Research, Rutgers Univ., New Jersey."},{"issue":"1","key":"21_CR32","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1): 67\u201382.","journal-title":"IEEE Trans Evol Comput"},{"key":"21_CR33","first-page":"314","volume-title":"In Proc. Second Intl. Conference on Info. and Knowledge Mgmt","author":"P Chan","year":"1993","unstructured":"Chan P, Stolfo SJ (1993) Experiments on multistrategy learning by meta-learning In: In Proc. Second Intl. Conference on Info. and Knowledge Mgmt, 314\u2013323.. ACM, New York, NY, USA."},{"key":"21_CR34","volume-title":"Introduction to Parallel Computing","author":"A Grama","year":"2003","unstructured":"Grama A (2003) Introduction to Parallel Computing. Pearson Education, New Jersey."},{"key":"21_CR35","unstructured":"UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml\/ ."},{"issue":"1","key":"21_CR36","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The weka data mining software: an update. ACM SIGKDD explorations newsletter 11(1): 10\u201318.","journal-title":"ACM SIGKDD explorations newsletter"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0021-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-015-0021-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-015-0021-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,12]],"date-time":"2023-08-12T09:17:11Z","timestamp":1691831831000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.journalofbigdata.com\/content\/2\/1\/14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,19]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["21"],"URL":"https:\/\/doi.org\/10.1186\/s40537-015-0021-4","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,19]]},"article-number":"14"}}