{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:10:37Z","timestamp":1780355437701,"version":"3.54.1"},"reference-count":69,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/bigdata.2017.8258338","type":"proceedings-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T22:47:28Z","timestamp":1516056448000},"page":"3492-3498","source":"Crossref","is-referenced-by-count":76,"title":["Big data machine learning using apache spark MLlib"],"prefix":"10.1109","author":[{"given":"Mehdi","family":"Assefi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ehsun","family":"Behravesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangchi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad P.","family":"Tafti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27072-2_4"},{"key":"ref38","year":"0","journal-title":"Github-apache spark"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13021-7_9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806945"},{"key":"ref31","first-page":"1","article-title":"Mllib: Machine learning in apache spark","volume":"17","author":"meng","year":"2016","journal-title":"JMLR"},{"key":"ref30","article-title":"Mastering Apache Spark","author":"frampton","year":"2015","journal-title":"Packt Publishing Ltd"},{"key":"ref37","article-title":"Big data analysis: Apache spark perspective","volume":"15","author":"shoro","year":"2015","journal-title":"Global Journal of Computer Science and Technology"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2014.7004269"},{"key":"ref35","author":"sparks","year":"2015","journal-title":"Tupaq An efficient planner for large-scale predictive analytic queries"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824080"},{"key":"ref60","year":"0","journal-title":"Susy dataset"},{"key":"ref62","year":"0","journal-title":"Higgs dataset"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5308"},{"key":"ref63","year":"0","journal-title":"Heterogeneity activity recognition dataset"},{"key":"ref28","first-page":"95","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"zaharia","year":"2010","journal-title":"HotCloud"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809718"},{"key":"ref27","year":"0","journal-title":"Apache Spark MLLib"},{"key":"ref65","author":"han","year":"2011","journal-title":"Data Mining Concepts and Techniques"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref67","first-page":"363","article-title":"Ernest: Efficient performance prediction for large-scale advanced ana-lvtics","author":"venkataraman","year":"2016","journal-title":"NSDI"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ISKE.2015.7"},{"key":"ref69","year":"0","journal-title":"Spark standalone mode"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.162"},{"key":"ref1","volume":"66","author":"parashar","year":"2010","journal-title":"Advanced Computational Infrastructures for Parallel and Distributed Applications"},{"key":"ref20","article-title":"Scalable sde filtering and inference with apache spark","author":"bhat","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.86"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.158"},{"key":"ref24","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation USENIX Association"},{"key":"ref23","year":"0","journal-title":"Apache SPARK"},{"key":"ref26","year":"0","journal-title":"Apache hadoop releases"},{"key":"ref25","year":"0","journal-title":"Weka library"},{"key":"ref50","author":"fazli","year":"2017","journal-title":"Computational motility tracking of calcium dynamics in toxoplasma gondii"},{"key":"ref51","author":"allahyari","year":"2017","journal-title":"A brief survey of text mining Classification clustering and extraction techniques"},{"key":"ref59","author":"baldi","year":"2016","journal-title":"Parameterized machine learning for high-energy physics"},{"key":"ref58","year":"0","journal-title":"Hepmass dataset"},{"key":"ref57","year":"0","journal-title":"Us government's bureau of transportation research and innovative technology administration (rita)"},{"key":"ref56","year":"0","journal-title":"UCI Machine Learning Repository"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1097\/ACM.0000000000001234"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2650204"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1186\/2047-2501-2-3"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2014.10.007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1607582113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-016-0475-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ICACT.2017.7890112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu343"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv048"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2016.7558977"},{"key":"ref15","author":"syed","year":"2016","journal-title":"Using apache spark for scalable gene sequence analysis"},{"key":"ref16","first-page":"1","article-title":"Rapidminer for text analytic fundamentals","volume":"40","author":"ryan","year":"2016","journal-title":"Text mining and visualization case studies using open-source tools"},{"key":"ref17","first-page":"565","article-title":"Using mahout for clustering wikipedia's latest articles: a comparison between k-means and fuzzy c-means in the cloud","author":"rong","year":"2011","journal-title":"Cloud Computing Technology and Science (CloudCom) 2011 IEEE Third International Conference On IEEE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.9170"},{"key":"ref19","first-page":"714","article-title":"V3: Unsupervised aspect based sentiment analysis for semeval-2015 task 12","author":"garcia-pablos","year":"2015","journal-title":"SemEval-2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.17705\/1jais.00423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1951365.1951432"},{"key":"ref6","first-page":"17","article-title":"A spark-based workflow for probabilistic record linkage of healthcare data","author":"pita","year":"2015","journal-title":"EDBT\/ICDT Workshops"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30348-2_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_15"},{"key":"ref7","author":"how","year":"0","journal-title":"A case study Apache spark"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23525-7_8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2932707"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258394"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806945"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5120\/19788-0531"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.protcy.2015.10.085","article-title":"Apache spark a big data analytics platform for smart grid","volume":"21","author":"shyam","year":"2015","journal-title":"Procedia Technology"},{"key":"ref42","article-title":"Analyzing mobile phone usage using clustering in spark mllib and pig","volume":"8","author":"arora","year":"2017","journal-title":"International Journal"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0162721"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60438-1_46"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2759225"}],"event":{"name":"2017 IEEE International Conference on Big Data (Big Data)","location":"Boston, MA","start":{"date-parts":[[2017,12,11]]},"end":{"date-parts":[[2017,12,14]]}},"container-title":["2017 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8241556\/8257893\/08258338.pdf?arnumber=8258338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T11:07:11Z","timestamp":1570619231000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8258338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2017.8258338","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}