{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:10:40Z","timestamp":1742962240037,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662623855"},{"type":"electronic","value":"9783662623862"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-662-62386-2_4","type":"book-chapter","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T00:30:00Z","timestamp":1605832200000},"page":"91-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Scalable Schema Discovery for RDF Data"],"prefix":"10.1007","author":[{"given":"Redouane","family":"Bouhamoum","sequence":"first","affiliation":[]},{"given":"Zoubida","family":"Kedad","sequence":"additional","affiliation":[]},{"given":"St\u00e9phane","family":"Lopes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"issue":"1","key":"4_CR1","first-page":"1","volume":"7","author":"S Abiteboul","year":"2018","unstructured":"Abiteboul, S., et al.: Research directions for principles of data management (Dagstuhl perspectives workshop 16151). Dagstuhl Manifestos 7(1), 1\u201329 (2018)","journal-title":"Dagstuhl Manifestos"},{"key":"4_CR2","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/978-3-319-91473-2_46","volume-title":"Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations","author":"C Alcalde","year":"2018","unstructured":"Alcalde, C., Burusco, A.: Study of the relevance of objects and attributes of L-fuzzy contexts using overlap indexes. In: Medina, J., et al. (eds.) IPMU 2018. CCIS, vol. 853, pp. 537\u2013548. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-91473-2_46"},{"key":"4_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","volume-title":"The Semantic Web","author":"S Auer","year":"2007","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC\/ISWC -2007. LNCS, vol. 4825, pp. 722\u2013735. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-76298-0_52"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Baazizi, M.A., Lahmar, H.B., Colazzo, D., Ghelli, G., Sartiani, C.: Schema inference for massive JSON datasets. In: Proceeding of the 20th International Conference on Extending Database Technology (EDBT), pp. 222\u2013233 (2017)","DOI":"10.1145\/3122831.3122837"},{"issue":"4","key":"4_CR5","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s00778-018-0532-7","volume":"28","author":"M-A Baazizi","year":"2019","unstructured":"Baazizi, M.-A., Colazzo, D., Ghelli, G., Sartiani, C.: Parametric schema inference for massive JSON datasets. VLDB J. 28(4), 497\u2013521 (2019). https:\/\/doi.org\/10.1007\/s00778-018-0532-7","journal-title":"VLDB J."},{"key":"4_CR6","unstructured":"Bouhamoum, R., Kedad, Z., Lopes, S.: Schema discovery in large web data sources. In: proceeding of the 1st International Conference on Big Data and Cybersecurity Intelligence (BDCSIntell) (2018)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Bouhamoum, R., Kellou-Menouer, K.K., Lopes, S., Kedad, Z.: Scaling up schema discovery approaches. In: Proceeding of the 34th International Conference on Data Engineering Workshops (ICDEW), pp. 84\u201389. IEEE (2018)","DOI":"10.1109\/ICDEW.2018.00021"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Campina, S., Perry, T.E., Ceccarelli, D., Delbru, R., Tummarello, G.: Introducing RDF graph summary with application to assisted SPARQL formulation. In: Proceeding of the 23rd International Workshop on Database and Expert Systems Applications (DEXA), pp. 261\u2013266. IEEE (2012)","DOI":"10.1109\/DEXA.2012.38"},{"key":"4_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-662-46562-2_1","volume-title":"Transactions on Large-Scale Data- and Knowledge-Centered Systems XIX","author":"K Christodoulou","year":"2015","unstructured":"Christodoulou, K., Paton, N.W., Fernandes, A.A.A.: Structure inference for linked data sources using clustering. In: Hameurlain, A., K\u00fcng, J., Wagner, R., Bianchini, D., De Antonellis, V., De Virgilio, R. (eds.) Transactions on Large-Scale Data- and Knowledge-Centered Systems XIX. LNCS, vol. 8990, pp. 1\u201325. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-46562-2_1"},{"key":"4_CR10","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceeding of the Second International Conference on Knowledge Discovery and Data Mining (KDD), pp. 226\u2013231. AAAI Press (1996)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Fuchs, H., Kedem, Z.M., Naylor, B.F.: On visible surface generation by a priori tree structures. In: Proceedings of the 7th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) pp. 124\u2013133. ACM Press (1980)","DOI":"10.1145\/965105.807481"},{"key":"4_CR12","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.tcs.2017.01.004","volume":"718","author":"A Gragera Aguaza","year":"2017","unstructured":"Gragera Aguaza, A., Suppakitpaisarn, V.: Relaxed triangle inequality ratio of the S\u00f8rensen-dice and Tversky indexes. Theoret. Comput. Sci. 718, 37\u201345 (2017)","journal-title":"Theoret. Comput. Sci."},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Han, D., Agrawal, A., Liao, W., Choudhary, A.: A novel scalable DBSCAN algorithm with spark. In: Proceeding of the 29th International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1393\u20131402. IEEE (2016)","DOI":"10.1109\/IPDPSW.2016.57"},{"issue":"1","key":"4_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s11704-013-3158-3","volume":"8","author":"Y He","year":"2014","unstructured":"He, Y., Tan, H., Luo, W., Feng, S., Fan, J.: MR-DBSCAN: a scalable MapReduce-based DBSCAN algorithm for heavily skewed data. Front. Comput. Sci. 8(1), 83\u201399 (2014). https:\/\/doi.org\/10.1007\/s11704-013-3158-3. Proceeding of the 27th International Parallel and Distributed Processing Symposium Workshops (IPDPS). Springer, Berlin, Heidelberg","journal-title":"Front. Comput. Sci."},{"key":"4_CR15","unstructured":"IBM: IBM quest synthetic data generator. https:\/\/sourceforge.net\/projects\/ibmquestdatagen\/ (2015). Accessed 1 Oct 2018"},{"issue":"2","key":"4_CR16","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","volume":"11","author":"P Jaccard","year":"1912","unstructured":"Jaccard, P.: The distribution of flora in the Alpine zone. New Phytologist 11(2), 37\u201350 (1912)","journal-title":"New Phytologist"},{"key":"4_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1007\/978-3-319-25264-3_36","volume-title":"Conceptual Modeling","author":"K Kellou-Menouer","year":"2015","unstructured":"Kellou-Menouer, K., Kedad, Z.: Schema discovery in RDF data sources. In: Johannesson, P., Lee, M.L., Liddle, S.W., Opdahl, A.L., L\u00f3pez, \u00d3.P. (eds.) ER 2015. LNCS, vol. 9381, pp. 481\u2013495. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-25264-3_36"},{"key":"4_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-662-54037-4_4","volume-title":"Transactions on Large-Scale Data- and Knowledge-Centered Systems XXIX","author":"K Kellou-Menouer","year":"2016","unstructured":"Kellou-Menouer, K., Kedad, Z.: A self-adaptive and incremental approach for data profiling in the semantic web. In: Hameurlain, A., K\u00fcng, J., Wagner, R. (eds.) Transactions on Large-Scale Data- and Knowledge-Centered Systems XXIX. LNCS, vol. 10120, pp. 108\u2013133. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-54037-4_4"},{"issue":"3","key":"4_CR19","doi-asserted-by":"publisher","first-page":"157","DOI":"10.14778\/3021924.3021932","volume":"10","author":"A Lulli","year":"2016","unstructured":"Lulli, A., Dell\u2019Amico, M., Michiardi, P., Ricci, L.: NG-DBSCAN: scalable density-based clustering for arbitrary data. Proc. VLDB Endow. 10(3), 157\u2013168 (2016). https:\/\/doi.org\/10.14778\/3021924.3021932","journal-title":"Proc. VLDB Endow."},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Luo, G., Luo, X., Gooch, T.F.: A parallel DBSCAN algorithm based on spark. In: Proceeding of the 6th International Conference on Big Data and Cloud Computing (BDCloud), pp. 548\u2013553. IEEE (2016)","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.85"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Suchanek, F.M., Kasneci, G., Weikum, G.: YAGO: a core of semantic knowledge. In: Proceedings of the 16th International Conference on World Wide Web (WWW), pp. 697\u2013706. ACM Press (2007)","DOI":"10.1145\/1242572.1242667"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Patwary, M.M.A., Palsetia, D., Agrawal, A., Liao, W.K., Manne, F., Choudhary, A.: A new scalable parallel DBSCAN algorithm using the disjoint-set data structure. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201311. IEEE (2012)","DOI":"10.1109\/SC.2012.9"},{"key":"4_CR23","unstructured":"Patwary, M.M.A., Palsetia, D., Agrawal, A., Liao, W.K., Manne, F., Choudhary, A.: DBSCAN on resilient distributed datasets. In: Proceedings of the International Conference on High Performance Computing and Simulation (HPCS), pp. 531\u2013540. IEEE (2015)"},{"key":"4_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-25264-3_35","volume-title":"Conceptual Modeling","author":"D Sevilla Ruiz","year":"2015","unstructured":"Sevilla Ruiz, D., Morales, S.F., Garc\u00eda Molina, J.: Inferring versioned schemas from NoSQL databases and its applications. In: Johannesson, P., Lee, M.L., Liddle, S.W., Opdahl, A.L., L\u00f3pez, \u00d3.P. (eds.) ER 2015. LNCS, vol. 9381, pp. 467\u2013480. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-25264-3_35"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Savvas, I.K., Tselios, D.: Parallelizing DBSCAN algorithm using MPI. In: Proceeding of the 25th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE), pp. 77\u201382. IEEE (2016)","DOI":"10.1109\/WETICE.2016.26"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Song, H., Lee, J.G.: RP-DBSCAN: A superfast parallel DBSCAN algorithm based on random partitioning. In: Proceedings of the International Conference on Management of Data (SIGMOD), pp. 1173\u20131187. ACM (2018)","DOI":"10.1145\/3183713.3196887"},{"key":"4_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-030-21290-2_20","volume-title":"Advanced Information Systems Engineering","author":"S Issa","year":"2019","unstructured":"Issa, S., Paris, P.-H., Hamdi, F., Si-Said Cherfi, S.: Revealing the conceptual schemas of RDF datasets. In: Giorgini, P., Weber, B. (eds.) CAiSE 2019. LNCS, vol. 11483, pp. 312\u2013327. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21290-2_20"},{"key":"4_CR28","unstructured":"The Apache Software Foundation: Apache Hadoop. https:\/\/hadoop.apache.org\/ (2018). Accessed 20 Oct 2018"},{"key":"4_CR29","unstructured":"The Apache Software Foundation: Apache Spark. https:\/\/spark.apache.org (2018). Accessed 20 Oct 2018"},{"key":"4_CR30","unstructured":"W3C: SPARQL query language for RDF. https:\/\/www.w3.org\/TR\/rdf-sparql-query\/ (2013). Accessed 01 Aug 2020"}],"container-title":["Lecture Notes in Computer Science","Transactions on Large-Scale Data- and Knowledge-Centered Systems XLVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-62386-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T21:51:56Z","timestamp":1618437116000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-62386-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783662623855","9783662623862"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-62386-2_4","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":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}