{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T23:16:07Z","timestamp":1775258167010,"version":"3.50.1"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030031916","type":"print"},{"value":"9783030031923","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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-03192-3_12","type":"book-chapter","created":{"date-parts":[[2018,10,25]],"date-time":"2018-10-25T23:06:48Z","timestamp":1540508808000},"page":"158-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Efficient Batch Similarity Processing with MapReduce"],"prefix":"10.1007","author":[{"given":"Trong Nhan","family":"Phan","sequence":"first","affiliation":[]},{"given":"Tran Khanh","family":"Dang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,27]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Alabduljalil, M.A., Tang, X., Yang, T.: Optimizing parallel algorithms for all pairs similarity search. In: Proceedings of the 6th ACM International Conference on Web Search and Data Mining, pp. 203\u2013212 (2013)","DOI":"10.1145\/2433396.2433422"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Dang, T.K., K\u00fcng, J., Wagner, R.: The SH-tree: a super hybrid index structure for multidimensional data. In: Proceedings of the 12th International Conference on Database and Expert Systems Applications, pp. 340\u2013349 (2001)","DOI":"10.1007\/3-540-44759-8_34"},{"issue":"1","key":"12_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. J. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"J. Commun. ACM"},{"issue":"3","key":"12_CR4","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1109\/TKDE.2016.2631599","volume":"29","author":"Y Gao","year":"2017","unstructured":"Gao, Y., Yang, K., Chen, L., Zheng, B., Chen, G., Chen, C.: Metric similarity joins using MapReduce. IEEE Trans. Knowl. Data Eng. 29(3), 656\u2013669 (2017)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"8","key":"12_CR5","doi-asserted-by":"publisher","first-page":"704","DOI":"10.14778\/2212351.2212353","volume":"5","author":"A Metwally","year":"2012","unstructured":"Metwally, A., Faloutsos, C.: V-SMART-join: a scalable mapreduce framework for all-pair similarity joins of multisets and vectors. Proc. VLDB Endow. 5(8), 704\u2013715 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Nguyen, D.T.-T., Yong, C.H., Pham, X.Q., Nguyen, H.Q., Loan, T.T.K., Huh, E.N.: An index scheme for similarity search on cloud computing using MapReduce over Docker container. In: Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication, pp. 60:1\u201360:6 (2016)","DOI":"10.1145\/2857546.2857607"},{"key":"12_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-662-49175-1_3","volume-title":"Transactions on Large-Scale Data- and Knowledge-Centered Systems XXIII","author":"TN Phan","year":"2016","unstructured":"Phan, T.N., K\u00fcng, J., Dang, T.K.: An adaptive similarity search in massive datasets. In: Hameurlain, A., K\u00fcng, J., Wagner, R., Dang, T.K., Thoai, N. (eds.) Transactions on Large-Scale Data- and Knowledge-Centered Systems XXIII. LNCS, vol. 9480, pp. 45\u201374. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-49175-1_3"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Phan, T.N., K\u00fcng, J., Dang, T.K.: eHSim: an efficient hybrid similarity search with MapReduce. In: Proceedings of the 30th IEEE International Conference on Advanced Information Networking and Applications, pp. 422\u2013429. IEEE Computer Society (2016)","DOI":"10.1109\/AINA.2016.37"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Rajaraman, A., Ullman, J.D.: Finding similar items (Chap. 3). In: Mining of Massive Datasets, pp. 71\u2013127. Cambridge University Press, Cambridge (2011)","DOI":"10.1017\/CBO9781139058452"},{"issue":"10","key":"12_CR10","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/TKDE.2012.195","volume":"25","author":"C Rong","year":"2013","unstructured":"Rong, C., Lu, W., Wang, X., Du, X., Chen, Y., Tung, A.K.H.: Efficient and scalable processing of string similarity join. IEEE Trans. Knowl. Data Eng. 25(10), 2217\u20132230 (2013)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"5","key":"12_CR11","doi-asserted-by":"publisher","first-page":"430","DOI":"10.14778\/2140436.2140440","volume":"5","author":"V Satuluri","year":"2012","unstructured":"Satuluri, V., Parthasarathy, S.: Bayesian locality sensitive hashing for fast similarity search. Proc. VLDB Endow. 5(5), 430\u2013441 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR12","unstructured":"Tang, M., Yu, Y., Aref, W.G., Malluhi, Q.M., Ouzzani, M.: Efficient processing of Hamming-distance-based similarity-search queries over MapReduce. In: Proceedings of 18th International Conference on Extending Database Technology, pp. 361\u2013372 (2015)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, G., Deng, D., Zhang, Y., Feng, J.: Two birds with one stone: an efficient hierarchical framework for top-k and threshold-based string similarity search. In: 31st IEEE International Conference on Data Engineering, pp. 519\u2013530 (2015)","DOI":"10.1109\/ICDE.2015.7113311"},{"issue":"3","key":"12_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2000824.2000825","volume":"36","author":"Chuan Xiao","year":"2011","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X., Wang, G.: Efficient similarity joins for near-duplicate detection. ACM Trans. Syst. 6(3), 15:1\u201315:41 (2011)","journal-title":"ACM Transactions on Database Systems"},{"issue":"1","key":"12_CR15","first-page":"1605","volume":"14","author":"RB Zadeh","year":"2013","unstructured":"Zadeh, R.B., Goel, A.: Dimension independent similarity computation. J. Mach. Learn. Res. 14(1), 1605\u20131626 (2013)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR16","series-title":"Advances in Database Systems","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/0-387-29151-2","volume-title":"Similarity Search - The Metric Space Approach","author":"P Zezula","year":"2006","unstructured":"Zezula, P., Amato, G., Dohnal, V., Batko, M.: Similarity Search - The Metric Space Approach. Advances in Database Systems, vol. 32, XVIII, pp. 1\u2013220. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/0-387-29151-2. ISBN 0-387-29146-6"}],"container-title":["Lecture Notes in Computer Science","Future Data and Security Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03192-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:53:08Z","timestamp":1775253188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03192-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030031916","9783030031923"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03192-3_12","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":"27 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FDSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Future Data and Security Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"28 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"fdse2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cse.hcmut.edu.vn\/fdse2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}