{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T01:17:28Z","timestamp":1772587048995,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":34,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662661109","type":"print"},{"value":"9783662661116","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-662-66111-6_2","type":"book-chapter","created":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T07:05:19Z","timestamp":1665126319000},"page":"28-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Incremental Schema Generation for\u00a0Large and\u00a0Evolving RDF Sources"],"prefix":"10.1007","author":[{"given":"Redouane","family":"Bouhamoum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zoubida","family":"Kedad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Lopes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,8]]},"reference":[{"key":"2_CR1","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":"2_CR2","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":"2_CR3","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"},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s00778-018-0532-7","volume":"28","author":"MA Baazizi","year":"2019","unstructured":"Baazizi, M.A., Lahmar, H.B., Colazzo, D., Ghelli, G., Sartiani, C.: Parametric schema inference for massive JSON datasets. VLDB J. 28, 497\u2013521 (2019)","journal-title":"VLDB J."},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Bouhamoum, R., Kedad, Z., Lopes, S.: Scalable schema discovery for RDF data. Trans. Large Scale Data Knowl. Centered Syst. 46, 91\u2013120 (2020). https:\/\/doi.org\/10.1007\/978-3-662-62386-2_4","DOI":"10.1007\/978-3-662-62386-2_4"},{"key":"2_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-030-77385-4_12","volume-title":"The Semantic Web","author":"R Bouhamoum","year":"2021","unstructured":"Bouhamoum, R., Kedad, Z., Lopes, S.: Incremental schema discovery at scale for RDF data. In: Verborgh, R., et al. (eds.) ESWC 2021. LNCS, vol. 12731, pp. 195\u2013211. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77385-4_12"},{"key":"2_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":"2_CR8","doi-asserted-by":"publisher","unstructured":"Christodoulou, K., Paton, N.W., Fernandes, A.A.A.: Structure inference for linked data sources using clustering. Trans. Large Scale Data Knowl. Centered Syst. 19, 1\u201325 (2015). https:\/\/doi.org\/10.1007\/978-3-662-46562-2_1","DOI":"10.1007\/978-3-662-46562-2_1"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Cordova, I., Moh, T.: DBSCAN on resilient distributed datasets. In: 2015 International Conference on High Performance Computing & Simulation, HPCS 2015, Amsterdam, Netherlands, 20\u201324 July 2015, pp. 531\u2013540. IEEE (2015). https:\/\/doi.org\/10.1109\/HPCSim.2015.7237086","DOI":"10.1109\/HPCSim.2015.7237086"},{"key":"2_CR10","unstructured":"Ester, M., Kriegel, H., Sander, J., Wimmer, M., Xu, X.: Incremental clustering for mining in a data warehousing environment. In: Gupta, A., Shmueli, O., Widom, J. (eds.) VLDB 1998, Proceedings of 24rd International Conference on Very Large Data Bases, 24\u201327 August 1998, New York City, New York, USA, pp. 323\u2013333. Morgan Kaufmann (1998). http:\/\/www.vldb.org\/conf\/1998\/p323.pdf"},{"key":"2_CR11","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":"2_CR12","unstructured":"The Apache Software Foundation: Apache Hadoop (2018). https:\/\/hadoop.apache.org\/. Accessed 20 Oct 2018"},{"key":"2_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-319-93698-7_40","volume-title":"Computational Science \u2013 ICCS 2018","author":"Y Gong","year":"2018","unstructured":"Gong, Y., Sinnott, R.O., Rimba, P.: RT-DBSCAN: real-time parallel clustering of spatio-temporal data using spark-streaming. In: Shi, Y., et al. (eds.) ICCS 2018. LNCS, vol. 10860, pp. 524\u2013539. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93698-7_40"},{"key":"2_CR14","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. Theor. Comput. Sci. 718, 37\u201345 (2017)","journal-title":"Theor. Comput. Sci."},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Han, D., Agrawal, A., Liao, W., Choudhary, A.N.: A novel scalable DBSCAN algorithm with spark. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPS Workshops 2016, Chicago, IL, USA, 23\u201327 May 2016, pp. 1393\u20131402. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/IPDPSW.2016.57","DOI":"10.1109\/IPDPSW.2016.57"},{"issue":"1","key":"2_CR16","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. Comp. Sci. 8(1), 83\u201399 (2014). https:\/\/doi.org\/10.1007\/s11704-013-3158-3","journal-title":"Front. Comp. Sci."},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"He, Y., et al.: MR-DBSCAN: an efficient parallel density-based clustering algorithm using mapreduce. In: 17th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2011, Tainan, Taiwan, 7\u20139 December 2011, pp. 473\u2013480. IEEE Computer Society (2011). https:\/\/doi.org\/10.1109\/ICPADS.2011.83","DOI":"10.1109\/ICPADS.2011.83"},{"key":"2_CR18","unstructured":"IBM: IBM quest synthetic data generator (2015). https:\/\/sourceforge.net\/projects\/ibmquestdatagen\/. Accessed 01 Oct 2018"},{"issue":"2","key":"2_CR19","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 Phytol. 11(2), 37\u201350 (1912)","journal-title":"New Phytol."},{"key":"2_CR20","unstructured":"Jafari, O., Maurya, P., Nagarkar, P., Islam, K.M., Crushev, C.: A survey on locality sensitive hashing algorithms and their applications. CoRR abs\/2102.08942 (2021). https:\/\/arxiv.org\/abs\/2102.08942"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Kardoulakis, N., Kellou-Menouer, K., Troullinou, G., Kedad, Z., Plexousakis, D., Kondylakis, H.: Hint: hybrid and incremental type discovery for large RDF data sources. In: Zhu, Q., Zhu, X., Tu, Y., Xu, Z., Kumar, A. (eds.) SSDBM 2021: 33rd International Conference on Scientific and Statistical Database Management, Tampa, FL, USA, 6\u20137 July 2021, pp. 97\u2013108. ACM (2021). https:\/\/doi.org\/10.1145\/3468791.3468808","DOI":"10.1145\/3468791.3468808"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Kellou-Menouer, K., Kardoulakis, N., Troullinou, G., Kedad, Z., Plexousakis, D., Kondylakis, H.: A survey on semantic schema discovery. VLDB J. (2021). https:\/\/doi.org\/10.1145\/3468791.3468808","DOI":"10.1145\/3468791.3468808"},{"key":"2_CR23","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":"2_CR24","doi-asserted-by":"publisher","unstructured":"Kellou-Menouer, K., Kedad, Z.: A self-adaptive and incremental approach for data profiling in the semantic web. Trans. Large Scale Data Knowl. Centered Syst. 29, 108\u2013133 (2016). https:\/\/doi.org\/10.1007\/978-3-662-54037-4_4","DOI":"10.1007\/978-3-662-54037-4_4"},{"key":"2_CR25","doi-asserted-by":"publisher","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","DOI":"10.14778\/3021924.3021932"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Luo, G., Luo, X., Gooch, T.F., Tian, L., Qin, K.: A parallel DBSCAN algorithm based on spark. In: Cai, Z., et al. (eds.) 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (SocialCom), Sustainable Computing and Communications (SustainCom), BDCloud-SocialCom-SustainCom 2016, Atlanta, GA, USA, 8\u201310 October 2016, pp. 548\u2013553. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/BDCloud-SocialCom-SustainCom.2016.85","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.85"},{"key":"2_CR27","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1016\/j.aej.2015.08.009","volume":"54","author":"AM Bakr","year":"2015","unstructured":"Bakr, A.M., Ghanem, N.M., Ismail, M.A.: Efficient incremental density-based algorithm for clustering large datasets. Alex. Eng. J. 54, 1147\u20131154 (2015)","journal-title":"Alex. Eng. J."},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Patwary, M.M.A., Palsetia, D., Agrawal, A., Liao, W., Manne, F., Choudhary, A.N.: A new scalable parallel DBSCAN algorithm using the disjoint-set data structure. In: Hollingsworth, J.K. (ed.) SC Conference on High Performance Computing Networking, Storage and Analysis, SC 2012, Salt Lake City, UT, USA, 11\u201315 November 2012, p. 62. IEEE\/ACM (2012). https:\/\/doi.org\/10.1109\/SC.2012.9","DOI":"10.1109\/SC.2012.9"},{"key":"2_CR29","unstructured":"Pernelle, N., Sa\u00efs, F., Mercier, D., Thuraisamy, S.: RDF data evolution: efficient detection and semantic representation of changes. In: Proceedings of the Posters and Demos Track of the International Conference on Semantic Systems - SEMANTICS, vol. 12 (2016)"},{"key":"2_CR30","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":"2_CR31","doi-asserted-by":"publisher","unstructured":"Savvas, I.K., Tselios, D.C.: Parallelizing DBSCAN algorithm using MPI. In: Reddy, S., Gaaloul, W. (eds.) 25th IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2016, Paris, France, 13\u201315 June 2016, pp. 77\u201382. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/WETICE.2016.26","DOI":"10.1109\/WETICE.2016.26"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Song, H., Lee, J.: RP-DBSCAN: a superfast parallel DBSCAN algorithm based on random partitioning. In: Das, G., Jermaine, C.M., Bernstein, P.A. (eds.) Proceedings of the 2018 International Conference on Management of Data, SIGMOD Conference 2018, Houston, TX, USA, 10\u201315 June 2018, pp. 1173\u20131187. ACM (2018). https:\/\/doi.org\/10.1145\/3183713.3196887","DOI":"10.1145\/3183713.3196887"},{"key":"2_CR33","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":"2_CR34","unstructured":"The Apache Software Foundation: Apache Spark (2018). https:\/\/spark.apache.org. Accessed 20 Oct 2018"}],"container-title":["Lecture Notes in Computer Science","Transactions on Large-Scale Data- and Knowledge-Centered Systems LI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-66111-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T07:05:36Z","timestamp":1665126336000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-66111-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783662661109","9783662661116"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-66111-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"8 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}