{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:38:46Z","timestamp":1772120326029,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/bigdata47090.2019.9006547","type":"proceedings-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T06:05:34Z","timestamp":1582610734000},"page":"3754-3763","source":"Crossref","is-referenced-by-count":19,"title":["Cluster-size optimization within a cloud-based ETL framework for Big Data"],"prefix":"10.1109","author":[{"given":"Eftim","family":"Zdravevski","sequence":"first","affiliation":[]},{"given":"Petre","family":"Lameski","sequence":"additional","affiliation":[]},{"given":"Ace","family":"Dimitrievski","sequence":"additional","affiliation":[]},{"given":"Marek","family":"Grzegorowski","sequence":"additional","affiliation":[]},{"given":"Cas","family":"Apanowicz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364082"},{"key":"ref32","article-title":"Overview of Amazon Web Services","author":"mathew","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2332453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2014.22"},{"key":"ref35","first-page":"387","article-title":"Scalable cloud-based etl for self-serving analytics","author":"zdravevski","year":"2019","journal-title":"Advances in Data Mining Applications and Theoretical Aspects 19th Industrial Conference ICDM 2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15439\/2015F90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.06.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2513190.2517828"},{"key":"ref12","first-page":"134","article-title":"Data consistency properties and the trade-offs in commercial cloud storage: the consumers’ perspective","volume":"11","author":"wada","year":"2011","journal-title":"CIDR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1978542.1978562"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1016\/j.protcy.2014.10.015","article-title":"Elta: New approach in designing business intelligence solutions in era of big data","volume":"16","author":"marin-ortega","year":"2014","journal-title":"Procedia Technology"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IACC.2017.0192"},{"key":"ref16","first-page":"1235","article-title":"Mllib: Machine learning in apache spark","volume":"17","author":"meng","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.580"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"181","DOI":"10.15439\/2015F89","article-title":"Parallel computation of information gain using hadoop and mapreduce","volume":"5","author":"zdravevski","year":"2015","journal-title":"Proceedings of the 2015 Federated Conference on Computer Science and Information Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2016.84"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2038916.2038934"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.jpdc.2014.08.003","article-title":"Big data computing and clouds: Trends and future directions","volume":"79","author":"assuncao","year":"2015","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2015.7279485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2014.07.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1516360.1516362"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14778\/2536222.2536225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.01.015"},{"key":"ref8","first-page":"112","article-title":"A framework for learning and embedding multisensor forecasting models into a decision support system","author":"slezak","year":"2018","journal-title":"A case study of methane concentration in coal mines Information Sciences"},{"key":"ref7","first-page":"375","article-title":"Data preparation for data mining, Applied Artificial Intelligence","volume":"17","author":"zhang","year":"2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/41703503"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258124"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-013-0272-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2014.7073177"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742795"},{"key":"ref21","author":"thusoo","year":"0","journal-title":"Hive-a petabyte scale data warehouse using hadoop (March 2010)"},{"key":"ref24","article-title":"A new approximate query engine based on intelligent capture and fast transformations of granulated data summaries","author":"slezak","year":"0","journal-title":"Journal of Intelligent Information Systems"},{"key":"ref23","first-page":"45","author":"farber","year":"2012","journal-title":"SAP HANA Database-Data Management for Modern Business Applications"},{"key":"ref26","article-title":"Asynchronous complex analytics in a distributed dataflow architecture","author":"gonzalez","year":"0","journal-title":"arXiv preprint arXiv 1510 07092"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742790"}],"event":{"name":"2019 IEEE International Conference on Big Data (Big Data)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2019,12,9]]},"end":{"date-parts":[[2019,12,12]]}},"container-title":["2019 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8986695\/9005444\/09006547.pdf?arnumber=9006547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:47:57Z","timestamp":1658094477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9006547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/bigdata47090.2019.9006547","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}