{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T23:59:12Z","timestamp":1726099152160},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602444"},{"type":"electronic","value":"9783030602451"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60245-1_31","type":"book-chapter","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T08:06:00Z","timestamp":1601453160000},"page":"448-464","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Distributed and Parallel Ensemble Classification for Big Data Based on Kullback-Leibler Random Sample Partition"],"prefix":"10.1007","author":[{"given":"Chenghao","family":"Wei","sequence":"first","affiliation":[]},{"given":"Jiyong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Timur","family":"Valiullin","sequence":"additional","affiliation":[]},{"given":"Weipeng","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Long","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.neucom.2015.08.052","volume":"174","author":"BW Chen","year":"2016","unstructured":"Chen, B.W., Wen, J., Seungmin, R.: Divide-and-conquer signal processing, feature extraction, and machine learning for big data. Neurocomputing 174, 383 (2016)","journal-title":"Neurocomputing"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In: IEEE 26th symposium on mass storage systems and technologies, pp. 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"issue":"1","key":"31_CR3","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. Communi of ACM. 51(1), 107\u201313 (2008)","journal-title":"Communi of ACM."},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Elteir M., Lin H., and 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":"31_CR5","unstructured":"Zaharia M., Chowdhury M., Franklin M.J., Shenker S., Stoica I.: Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX conference on hot topics in cloud computing, pp. 10 (2010)"},{"key":"31_CR6","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, 145\u2013164 (2016)","journal-title":"Int J Data Sci Anal"},{"key":"31_CR7","unstructured":"Lei G., Huan L.: Memory or time: performance evaluation for iterative operation on hadoop and spark. In: IEEE 10th international conference on high performance computing and communications. pp. 721\u2013727 (2013)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Wu X., Zhu X., Wu G.Q., Ding W., Data mining with big data, IEEE Trans. Knowl. Data Eng., 26(1), 97C107(2014)","DOI":"10.1109\/TKDE.2013.109"},{"issue":"11","key":"31_CR9","doi-asserted-by":"publisher","first-page":"5846","DOI":"10.1109\/TII.2019.2912723","volume":"15","author":"S Salloum","year":"2019","unstructured":"Salloum, S., Huang, J.Z., He, Y.L.: Random sample partition: a distributed data model for big data analysis. IEEE Trans on Indus Infor 15(11), 5846\u20135854 (2019)","journal-title":"IEEE Trans on Indus Infor"},{"issue":"2","key":"31_CR10","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","volume":"14","author":"X Dong","year":"2020","unstructured":"Dong, X., Yu, Z., Cao, W., Shi, Y.: Ma, Q: A survey on ensemble learning. Front Compu Sci 14(2), 241\u2013258 (2020)","journal-title":"Front Compu Sci"},{"key":"31_CR11","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1016\/j.knosys.2018.10.009","volume":"163","author":"A Galicia","year":"2018","unstructured":"Galicia, A., Talavera, L.R., Troncoso, A., Koprinska, I., Martnez, A.F.: Multi-step forecasting for big data time series based on ensemble learning. Know Base Sys 163, 830\u2013841 (2018)","journal-title":"Know Base Sys"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Tang Y., Wang Y., Cooper K.M.L., Li L.: Towards big data bayesian network learning - an ensemble learning based approach, In: IEEE international congress on big data, 2014, pp. 355\u2013357","DOI":"10.1109\/BigData.Congress.2014.58"},{"key":"31_CR13","unstructured":"Shadi K., Patrick M., Rebecca Y.,: Label-aware distributed ensemble learning: a simplified distributed classifier training model for big data, big data res, 15, pp. 1\u201311, (2019)"},{"key":"31_CR14","unstructured":"Diego M., Eduard A., Jose R. Herrero, Read J., Bifet A., Low-latency multi-threaded ensemble learning for dynamic big data streams. In: IEEE international conference on big data, pp. 223\u2013232 (2017)"},{"key":"31_CR15","doi-asserted-by":"publisher","first-page":"3675","DOI":"10.1109\/ACCESS.2018.2889355","volume":"7","author":"S Salman","year":"2019","unstructured":"Salman, S., Joshua, Z.X.H., He, Y.L., Chen, X.J.: An asymptotic ensemble learning framework for big data analysis. IEEE Acc 7, 3675\u20133693 (2019)","journal-title":"IEEE Acc"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Zhou Z.H., Wu J.X., Tang W.: Ensembling neural networks: many could be better than all, AI, 137(1C2),239\u2013263 (2002)","DOI":"10.1016\/S0004-3702(02)00190-X"},{"issue":"1","key":"31_CR17","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/S0167-8655(00)00096-9","volume":"22","author":"G Giancinto","year":"2001","unstructured":"Giancinto, G., Roli, F.: An approach to the automatic design of multiple classifier ensembles. Patt Recog Lett 22(1), 25\u201333 (2001)","journal-title":"Patt Recog Lett"},{"key":"31_CR18","unstructured":"Cheng X.Y., Guo H.L.: The technology of selective multiple classifiers ensemble based on kernel clustering. In: International symposium on intelligent information technology application. pp. 146\u2013150 (2008)"},{"issue":"1","key":"31_CR19","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.patrec.2006.06.018","volume":"28","author":"MG Martinez","year":"2007","unstructured":"Martinez, M.G., Suarez, A.: Using boosting to prune bagging ensembles. Patt Recog Lett 28(1), 156\u2013165 (2007)","journal-title":"Patt Recog Lett"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Martinez M.G., Suarez A. Pruning in ordered bagging ensembles. In: Prceedings of the 23rd international conference on machine learning, pp. 609\u2013368 (2006)","DOI":"10.1145\/1143844.1143921"},{"key":"31_CR21","volume-title":"Out-of-bag estimation","author":"L Breiman","year":"1996","unstructured":"Breiman, L.: Out-of-bag estimation. Statistics deparment in university of california, Technical Report (1996)"},{"issue":"1","key":"31_CR22","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.patcog.2010.07.021","volume":"44","author":"L Zhang","year":"2011","unstructured":"Zhang, L., Zhou, W.D.: Sparse ensembles using weighted combination methods based on linear programming. Patt Recog Lett 44(1), 97\u2013106 (2011)","journal-title":"Patt Recog Lett"},{"issue":"298","key":"31_CR23","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1080\/01621459.1962.10480667","volume":"57","author":"CT Fan","year":"1962","unstructured":"Fan, C.T., Muller, M.E., Rezucha, I.: Development of sampling plans by using sequential (item by item) selection techniques and digital computers. J Amer Stat Ass 57(298), 387\u2013402 (1962)","journal-title":"J Amer Stat Ass"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Haas, P.J.: Data-stream sampling: basic techniques and results. Data Stream Management. Springer, Berlin Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-540-28608-0_2","DOI":"10.1007\/978-3-540-28608-0_2"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Oliphant, T.E.: SciPy: open source scientific tools for Python. Comput Sci Eng, 9(3):10C20, (2007)","DOI":"10.1109\/MCSE.2007.58"},{"issue":"10","key":"31_CR26","first-page":"2825","volume":"12","author":"A Swami","year":"2013","unstructured":"Swami, A., Jain, R.: Scikit-learn: machine learning in Python. J Mach Lear Res 12(10), 2825\u20132830 (2013)","journal-title":"J Mach Lear Res"},{"issue":"5","key":"31_CR27","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1145\/167049.167076","volume":"18","author":"A Podgurski","year":"1993","unstructured":"Podgurski, A., Yang, C.: Partition testing, stratified sampling, and cluster analysis. ACM SIGSOFT Soft Eng Notes 18(5), 169\u2013181 (1993)","journal-title":"ACM SIGSOFT Soft Eng Notes"},{"key":"31_CR28","unstructured":"Kleiner A., Talwalkar A., Sarkar P., Jordan M.I.: The big data Bootstrap. In: Proceedings of the 29th international conference on machine learning. pp. 1787\u20131794, (2012)"},{"key":"31_CR29","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1214\/aoms\/1177728190","volume":"27","author":"M Rosenblatt","year":"1956","unstructured":"Rosenblatt, M.: Remarks on some nonparametric estimates of a density function. Ann Math Stat 27, 832\u2013837 (1956)","journal-title":"Ann Math Stat"},{"key":"31_CR30","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","volume":"33","author":"E Parzen","year":"1962","unstructured":"Parzen, E.: On the estimation of probability density functions and mode. Ann Math Stat 33, 1065\u20131076 (1962)","journal-title":"Ann Math Stat"},{"issue":"4","key":"31_CR31","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1109\/TSMCB.2004.828199","volume":"34","author":"S Chen","year":"2004","unstructured":"Chen, S., Hong, X., Harris, C.J.: Sparse kernel density construction using orthogonal forward regression with leave-one-out test score and local regularization. IEEE transactions on systems man and cybernetics part b cybernetics 34(4), 1708\u20131717 (2004)","journal-title":"IEEE transactions on systems man and cybernetics part b cybernetics"},{"issue":"3","key":"31_CR32","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1145\/355744.355745","volume":"3","author":"JH Friedman","year":"1977","unstructured":"Friedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Trans Math Soft 3(3), 209\u2013226 (1977)","journal-title":"ACM Trans Math Soft"},{"issue":"1","key":"31_CR33","first-page":"521","volume":"4","author":"AG Gray","year":"2001","unstructured":"Gray, A.G., Moore, A.W.: \u2018N-Body\u2019 problems in statistical learning. Adva in Neur Infor Proc Sys 4(1), 521\u2013527 (2001)","journal-title":"Adva in Neur Infor Proc Sys"},{"issue":"1","key":"31_CR34","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback, S., Leibler, R.A.: On information and sufficiency. Ann Math Stats 22(1), 79\u201386 (1951)","journal-title":"Ann Math Stats"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60245-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T04:59:32Z","timestamp":1723697972000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60245-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602444","9783030602451"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60245-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New York, NY","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cloud-conf.net\/ica3pp2020\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"495","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":"142","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":"5","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":"29% - 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":"305","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":"10","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)"}}]}}