{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T21:38:21Z","timestamp":1773524301516,"version":"3.50.1"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319942940","type":"print"},{"value":"9783319942957","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-94295-7_24","type":"book-chapter","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T12:29:10Z","timestamp":1529324950000},"page":"347-364","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["A Two-Stage Data Processing Algorithm to Generate Random Sample Partitions for Big Data Analysis"],"prefix":"10.1007","author":[{"given":"Chenghao","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Salloum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamer Z.","family":"Emara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua Zhexue","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,19]]},"reference":[{"issue":"2","key":"24_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1093\/nsr\/nwt032","volume":"1","author":"J Fan","year":"2014","unstructured":"Fan, J., Fang, H., Han, L.: Challenges of big data analysis. Nat. Sci. Rev. 1(2), 293\u2013314 (2014)","journal-title":"Nat. Sci. Rev."},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, W., Liu, Y.: Improved K-means cluster algorithm in telecommunications enterprises customer segmentation. In: IEEE International Conference on Information Theory and Information Security, pp. 167\u2013169 (2010)","DOI":"10.1109\/ICITIS.2010.5688749"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Michael, B.: Uncovering online political communities of Belgian MPs through social network clustering analysis. In Proceedings of the ACM 2015 2nd International Conference on Electronic Governance and Open Society, pp. 150\u2013163 (2015)","DOI":"10.1145\/2846012.2846049"},{"issue":"86","key":"24_CR4","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1016\/j.neucom.2015.04.109","volume":"174","author":"A Ahmad","year":"2016","unstructured":"Ahmad, A., Paul, A., Rathore, M.M.: An efficient divide-and-conquer approach for big data analytics in machine-to-machine communication. Neurocomputing 174(86), 439\u2013453 (2016)","journal-title":"Neurocomputing"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In: IEEE 26th Symposium Mass Storage Systems and Technologies, pp. 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"issue":"1","key":"24_CR6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Elteir, M., Lin, H., Feng, W.C.: Enhancing mapreduce via asynchronous data processing. In: IEEE International Conference on Parallel and Distributed Systems, pp. 397\u2013405 (2010)","DOI":"10.1109\/ICPADS.2010.116"},{"key":"24_CR8","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: HotCloud 2010, p. 10 (2010)"},{"issue":"3\u20134","key":"24_CR9","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s41060-016-0027-9","volume":"1","author":"S Salloum","year":"2016","unstructured":"Salloum, S., Dautov, R., Chen, X., Peng, P.X., Huang, J.Z.: Big data analytics on apache spark. Int. J. Data Sci. Anal. 1(3\u20134), 145\u2013164 (2016)","journal-title":"Int. J. Data Sci. Anal."},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Salloum, S., Huang, J.Z., He, Y.L.: Empirical analysis of asymptotic ensemble learning for big data. In: Proceedings of the 2016 IEEE\/ACM International Conference on Big Data Computing, Applications and Technologies, pp. 8\u201317 (2016)","DOI":"10.1145\/3006299.3006306"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Cormode, G., Duffield, N.: Sampling for big data: a tutorial. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, p. 1975 (2014)","DOI":"10.1145\/2623330.2630811"},{"issue":"4","key":"24_CR12","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/S0020-0255(01)00123-2","volume":"138","author":"D Garcia","year":"2001","unstructured":"Garcia, D., Lubiano, M.A., Alonso, M.C.: Estimating the expected value of fuzzy random variables in the stratified random sampling from finite populations. Inf. Sci. 138(4), 165\u2013184 (2001)","journal-title":"Inf. Sci."},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Leo, S., Zanetti, G.: Pydoop: a python mapreduce and HDFS API for hadoop. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, pp. 819\u2013825 (2010)","DOI":"10.1145\/1851476.1851594"},{"issue":"3","key":"24_CR14","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1111\/j.2517-6161.1991.tb01857.x","volume":"53","author":"SJ Sheather","year":"1991","unstructured":"Sheather, S.J., Jones, M.C.: A reliable data-based bandwidth selection method for kernel density estimation. J. Roy. Stat. Soc. 53(3), 683\u2013690 (1991)","journal-title":"J. Roy. Stat. Soc."}],"container-title":["Lecture Notes in Computer Science","Cloud Computing \u2013 CLOUD 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-94295-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T05:00:06Z","timestamp":1751691606000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-94295-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319942940","9783319942957"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-94295-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLOUD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cloud Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cloud2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.thecloudcomputing.org\/2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"www.confhub.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}