{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T00:06:54Z","timestamp":1714781214445},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,12,22]],"date-time":"2012-12-22T00:00:00Z","timestamp":1356134400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s10115-012-0588-4","type":"journal-article","created":{"date-parts":[[2012,12,21]],"date-time":"2012-12-21T09:17:32Z","timestamp":1356081452000},"page":"331-364","source":"Crossref","is-referenced-by-count":0,"title":["Clustering semantically heterogeneous distributed aggregate databases"],"prefix":"10.1007","volume":"38","author":[{"given":"Shuai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sally I.","family":"McClean","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan W.","family":"Scotney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,12,22]]},"reference":[{"issue":"1","key":"588_CR1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s10115-011-0421-5","volume":"32","author":"A A\u00eftelhadj","year":"2011","unstructured":"A\u00eftelhadj A, Boughanem M, Mezghiche M, Souam F (2011) Using structural similarity for clustering XML documents. Knowl Inf Syst 32(1):109\u2013139","journal-title":"Knowl Inf Syst"},{"issue":"5","key":"588_CR2","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/scientificamerican0501-34","volume":"284","author":"T Berners-Lee","year":"2001","unstructured":"Berners-Lee T, Hendler J, Lassila O (2001) The semantic web. Sci. Am. 284(5):34\u201343","journal-title":"Sci. Am."},{"key":"588_CR3","volume-title":"A general probabilistic framework for clustering individuals (Technical report)","author":"I Cadez","year":"2000","unstructured":"Cadez I, Gaffney S, Smyth P (2000) A general probabilistic framework for clustering individuals (Technical report). Department of Information and Computer Science, University of California, Irvine"},{"key":"588_CR4","doi-asserted-by":"crossref","unstructured":"Caragea D, Bao J, Pathak J, Silvescu A, Andorf C, Dobbs D, Honavar V (2005) Information integration from semantically heterogeneous biological data sources. In: Proceedings of the international workshop on database and expert systems applications. Las Vegas, Nevada, pp 580\u2013584","DOI":"10.1109\/DEXA.2005.118"},{"key":"588_CR5","doi-asserted-by":"crossref","unstructured":"Caragea D, Pathak J, Honavar VG (2004) Learning classifiers from semantically heterogeneous data. In: Proceedings of the international conference on ontologies, databases, and applications of semantics for large scale information systems, Agia. Springer, Berlin, pp 963\u2013980","DOI":"10.1007\/978-3-540-30469-2_9"},{"issue":"3","key":"588_CR6","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1017\/S0269888904000025","volume":"18","author":"H Chen","year":"2003","unstructured":"Chen H, Finin T, Joshi A (2003) An ontology for context-aware pervasive computing environments. Knowl Eng Rev 18(3):197\u2013207","journal-title":"Knowl Eng Rev"},{"issue":"3","key":"588_CR7","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s10115-009-0274-3","volume":"24","author":"K Das","year":"2010","unstructured":"Das K, Bhaduri K, Kargupta H (2010) A local asynchronous distributed privacy preserving feature selection algorithm for large peer-to-peer networks. Knowl Inf Syst 24(3):341\u2013367","journal-title":"Knowl Inf Syst"},{"issue":"441","key":"588_CR8","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1080\/01621459.1998.10474110","volume":"93","author":"A Dasgupta","year":"1998","unstructured":"Dasgupta A, Raftery AE (1998) Detecting features is spatial point processes with clutter via model-based clustering. J Am Stat Assoc 93(441):294\u2013302","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"588_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood for incomplete data via the EM algorithm. J R Stat Soc 39(1):1\u201338","journal-title":"J R Stat Soc"},{"key":"588_CR10","doi-asserted-by":"crossref","unstructured":"Doan A, Domingos P, Halevy AY (2001) Reconciling schemas of disparate data sources: a machine-learning approach. In: Proceedings of the ACM SIGMOD Conference on Management of data, California, USA. ACM Press, New York, pp 509\u2013520","DOI":"10.1145\/375663.375731"},{"issue":"1","key":"588_CR11","first-page":"83","volume":"26","author":"A Doan","year":"2005","unstructured":"Doan A, Halevy AY (2005) Semantic integration research in the database community: a brief survey. AI Mag. 26(1):83\u201394","journal-title":"AI Mag."},{"issue":"4","key":"588_CR12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/1041410.1041413","volume":"33","author":"DW Embley","year":"2004","unstructured":"Embley DW, Xu L, Ding YH (2004) Automatic direct and indirect schema mapping: experiences and lessons learned. ACM SIGMOD Record 33(4):14\u201319","journal-title":"ACM SIGMOD Record"},{"key":"588_CR13","volume-title":"Tools for assembling modular ontologies in Ontolingua (Technical report)","author":"A Farquhar","year":"1997","unstructured":"Farquhar A, Fikes R, Rice J (1997) Tools for assembling modular ontologies in Ontolingua (Technical report). Knowledge Systems Laboratory Stanford University, Stanford"},{"issue":"2","key":"588_CR14","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1145\/380995.381010","volume":"2","author":"G Forman","year":"2000","unstructured":"Forman G, Zhang B (2000) Distributed data clustering can be efficient and exact. SIGKDD Explor 2(2):34\u201338","journal-title":"SIGKDD Explor"},{"key":"588_CR15","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1093\/comjnl\/41.8.578","volume":"41","author":"C Fraley","year":"1998","unstructured":"Fraley C, Raftery AE (1998) How many clusters? Which clustering methods? Answers via model-based cluster analysis. Comput J 41:578\u2013588","journal-title":"Comput J"},{"issue":"458","key":"588_CR16","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1198\/016214502760047131","volume":"97","author":"C Fraley","year":"2002","unstructured":"Fraley C, Raftery AE (2002) Model-based clustering, discriminant analysis, and density estimation. J Am Stat Assoc 97(458):611\u2013631","journal-title":"J Am Stat Assoc"},{"key":"588_CR17","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1023\/A:1008683107812","volume":"8","author":"H Garcia-molina","year":"1997","unstructured":"Garcia-molina H, Papakonstantinou Y, Quass D, Sagiv Y, Ullman J, Vassalos V, Widom J (1997) The TSIMMIS approach to mediation: data models and languages. J Intell Inf Syst 8:117\u2013132","journal-title":"J Intell Inf Syst"},{"issue":"2","key":"588_CR18","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1006\/knac.1993.1008","volume":"5","author":"TR Gruber","year":"1993","unstructured":"Gruber TR (1993) A translation approach to portable ontology specifications. Knowl Acquis 5(2):199\u2013220","journal-title":"Knowl Acquis"},{"key":"588_CR19","unstructured":"Gu T, Wang XH, Pung HK, Zhang DQ (2004) An ontology-based context model in intelligent environments. In: Proceedings of the communication networks and distributed systems modeling and simulation conference, San Diego, California. Society for Modeling and Simulation International, pp 270\u2013275"},{"issue":"3","key":"588_CR20","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1016\/j.patcog.2011.09.002","volume":"45","author":"Y-F Guo","year":"2012","unstructured":"Guo Y-F, Lin X, Teng Z, Xue X, Fan J (2012) A covariance-free iterative algorithm for distributed principal component analysis on vertically partitioned data. Pattern Recognit 45(3):1211\u20131219","journal-title":"Pattern Recognit"},{"key":"588_CR21","unstructured":"He J, Lan M, Tan C-L, Sung S-Y, Low H-B (2004) Initialization of cluster refinement algorithms: A review and comparative study. In: Proceedings of the IEEE international joint conference on neural networks, Budapest, Hungary. IEEE, pp 297\u2013302"},{"issue":"2","key":"588_CR22","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/TKDE.2009.69","volume":"22","author":"A Jaiswal","year":"2010","unstructured":"Jaiswal A, Miller DJ, Mitra P (2010) Uninterpreted schema matching with embedded value mapping under opaque column names and data values. IEEE Trans Knowl Data Eng 22(2):291\u2013304","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"588_CR23","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s10115-008-0153-3","volume":"18","author":"JJ Jung","year":"2009","unstructured":"Jung JJ (2009) Consensus-based evaluation framework for distributed information retrieval systems. Knowl Inf Syst 18(2):199\u2013211","journal-title":"Knowl Inf Syst"},{"key":"588_CR24","volume-title":"Advances in distributed and parallel knowledge discovery","author":"H Kargupta","year":"2000","unstructured":"Kargupta H, Chan P (2000) Advances in distributed and parallel knowledge discovery. AAAI Press \/MIT Press, Massachusetts"},{"issue":"4","key":"588_CR25","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1007\/PL00011677","volume":"3","author":"H Kargupta","year":"2001","unstructured":"Kargupta H, Huang W, Sivakumar K, Johnson E (2001) Distributed clustering using collective principal component analysis. Knowl Inf Syst 3(4):422\u2013448","journal-title":"Knowl Inf Syst"},{"key":"588_CR26","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1080\/01621459.1995.10476572","volume":"90","author":"RE Kass","year":"1995","unstructured":"Kass RE, Raftery AE (1995) Bayes factors. J Am Stat Assoc 90:773\u2013795","journal-title":"J Am Stat Assoc"},{"key":"588_CR27","unstructured":"Klyne G, Carroll JJ (2005) Resource Description Framework (RDF): Concepts and Abstract Syntax. W3C"},{"issue":"4","key":"588_CR28","first-page":"340","volume":"41","author":"S Kullback","year":"1987","unstructured":"Kullback S (1987) Letter to the editor: the Kullback-Leibler distance. Am Stat 41(4):340\u2013341","journal-title":"Am Stat"},{"issue":"3","key":"588_CR29","first-page":"12","volume":"13","author":"AY Levy","year":"1998","unstructured":"Levy AY (1998) The information manifold approach to data integration. IEEE Intell Syst 13(3):12\u201316","journal-title":"IEEE Intell Syst"},{"issue":"1","key":"588_CR30","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s101150050004","volume":"2","author":"W-S Li","year":"2000","unstructured":"Li W-S, Clifton C, Liu S-Y (2000) Database integration using neural network: implementation and experiences. Knowl Inf Syst 2(1):73\u201396","journal-title":"Knowl Inf Syst"},{"key":"588_CR31","unstructured":"Madhavan J, Bernstein PA, Rahm E (2001) Generic schema matching with cupid. In: Proceedings of the international conference on very large data bases, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc., Los Altos, pp 49\u201358"},{"key":"588_CR32","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H (2008) Introduction to information retrieval. Cambridge University Press, New York"},{"key":"588_CR33","unstructured":"Matlab\u00ae(August 2005) The language of technical computing (Service Pack 3). Version 7.1.0.246 (R14). The MathWorks, Inc., United States"},{"issue":"1\u20133","key":"588_CR34","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s10619-008-7031-6","volume":"24","author":"S McClean","year":"2008","unstructured":"McClean S, Scotney B, Morrow P, Greer K (2008) Integrating semantically heterogeneous aggregate views of distributed databases. Distrib Parallel Databases 24(1\u20133):73\u201394","journal-title":"Distrib Parallel Databases"},{"key":"588_CR35","doi-asserted-by":"crossref","unstructured":"McClean S, Scotney B, Rutjes H, Hartkamp J, Karali I, Hatzopoulos M, Lamb J, Defeng M (2004) MISSION: an agent-based system for semantic integration of heterogeneous distributed statistical information sources. In: Proceedings of the international conference on scientific and statistical database management Greece. IEEE, pp 337\u2013340","DOI":"10.1109\/SSDM.2004.1311226"},{"issue":"6","key":"588_CR36","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1109\/69.971186","volume":"13","author":"S McClean","year":"2001","unstructured":"McClean S, Scotney B, Shapcott M (2001) Aggregation of imprecise and uncertain information in databases. IEEE Trans Knowl Data Eng 13(6):902\u2013912","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"588_CR37","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1142\/S0218213002000782","volume":"11","author":"SI McClean","year":"2002","unstructured":"McClean SI, Karali I, Scotney BW, Greer K, Kapos G-D, P\u00e1irc\u00e9ir R, Hong J, Bell DA, Hatzopoulos M (2002) Agents for querying distributed statistical databases over the internet. Int J Artif Intell Tools 11(1):63\u201394","journal-title":"Int J Artif Intell Tools"},{"issue":"2","key":"588_CR38","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.datak.2004.12.001","volume":"54","author":"SI McClean","year":"2005","unstructured":"McClean SI, Scotney B, Morrow P, Greer K (2005) Knowledge discovery by probabilistic clustering of distributed databases. Data Knowl Eng 54(2):189\u2013210","journal-title":"Data Knowl Eng"},{"issue":"1","key":"588_CR39","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/TKDE.2003.1161592","volume":"15","author":"SI McClean","year":"2003","unstructured":"McClean SI, Scotney BW, Greer K (2003) A scalable approach to integrating heterogeneous aggregate views of distributed databases. IEEE Trans Knowl Data Eng 15(1):232\u2013235","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"588_CR40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v013.i02","volume":"13","author":"A Medrano-Soto","year":"2005","unstructured":"Medrano-Soto A, Christen JA, Collado-Vides J (2005) BClass: a Bayesian approach based on mixture models for clustering and classification of heterogeneous biological data. J Stat Softw 13(2):1\u201318","journal-title":"J Stat Softw"},{"key":"588_CR41","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1214\/09-SS053","volume":"4","author":"V Melnykov","year":"2010","unstructured":"Melnykov V, Maitra R (2010) Finite mixture models and model-based clustering. Stat Surv 4:80\u2013116","journal-title":"Stat Surv"},{"key":"588_CR42","doi-asserted-by":"crossref","unstructured":"Merugu S, Ghosh J (2005) A distributed learning framework for heterogeneous data sources. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery in data mining, Chicago, Illinois, USA. ACM, New York, pp 208\u2013217","DOI":"10.1145\/1081870.1081896"},{"key":"588_CR43","first-page":"341","volume-title":"Data mining handbook","author":"B-H Park","year":"2003","unstructured":"Park B-H, Kargupta H (2003) Distributed data mining: algorithms, systems, and applications. In: Ye N (ed) Data mining handbook. Lawrence Erlbaum Associates, Mahwah, pp 341\u2013358"},{"key":"588_CR44","volume-title":"Advances in distributed and parallel knowledge discovery. Distributed data mining: scaling up and beyond","author":"F Provost","year":"2000","unstructured":"Provost F (2000) Advances in distributed and parallel knowledge discovery. Distributed data mining: scaling up and beyond. AAAI Press\/ The MIT Press, Cambridge"},{"issue":"2","key":"588_CR45","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G Schwarz","year":"1978","unstructured":"Schwarz G (1978) Estimating the dimensions of a model. Ann Stat 6(2):461\u2013464","journal-title":"Ann Stat"},{"issue":"9","key":"588_CR46","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1016\/S0950-5849(99)00020-8","volume":"41","author":"B Scotney","year":"1999","unstructured":"Scotney B, McClean S (1999) Efficient knowledge discovery through the integration of heterogeneous data. Inf Softw Technol 41(9):569\u2013578","journal-title":"Inf Softw Technol"},{"key":"588_CR47","doi-asserted-by":"crossref","unstructured":"Scotney B, McClean S, Rodgers M (1999) Optimal and efficient integration of heterogeneous summary tables in a distributed database. Data Knowl Eng 29(3):337\u2013350","DOI":"10.1016\/S0169-023X(98)00039-1"},{"key":"588_CR48","doi-asserted-by":"crossref","unstructured":"Scotney B, McClean S, Zhang S (2006) Interoperability and integration of independent heterogeneous distributed databases over the internet. In: Proceedings of the BNCOD, Belfast, Northern Ireland. Springer, Berlin, pp 250\u2013253","DOI":"10.1007\/11788911_23"},{"key":"588_CR49","unstructured":"Taylor NE, Ives ZG (2006) Reconciling while tolerating disagreement in collaborative data sharing. In: Proceedings of the ACM SIGMOD international conference on management of data, Chicago, IL, USA. ACM, New York, pp 13\u201324"},{"key":"588_CR50","doi-asserted-by":"crossref","unstructured":"Tsoumakas G, Angelis L, Vlahavas I (2004) Clustering classifiers for knowledge discovery from physically distributed databases. Data Knowl Eng 49(3):223\u2013242","DOI":"10.1016\/j.datak.2003.09.002"},{"key":"588_CR51","unstructured":"U.S. CensusBureau (2003) 2000 census of population and housing, summary social, economic and housing characteristics. PHC-2-4, Arizona. U.S. Department of Commerce, Economics and Statistics Administration, Washington, DC"},{"key":"588_CR52","unstructured":"Wirth R, Borth M, Hipp J (2001) When distribution is part of the semantics: a new problem class for distributed knowledge discovery. In: Proceedings of the ECML and PKDD workshop on ubiquitous data mining for mobile and distributed environments, Freiburg, Germany, pp 56\u201364"},{"key":"588_CR53","doi-asserted-by":"crossref","unstructured":"Zhang J, Caragea D, Honavar V (2005) Learning Ontology-aware Classifiers. In: Proceedings of the 8th international conference discovery science, Singapore. Springer, Berlin, pp 294\u2013307","DOI":"10.1007\/11563983_26"},{"key":"588_CR54","unstructured":"Zhang S, McClean S, Scotney B (2006) Model-based clustering on semantically heterogeneous distributed databases on the internet. In: Proceedings of the AAAI fall symposium on semantic web for collaborative knowledge acquisition, Arlington, Virginia. AAAI, pp 78\u201385"},{"key":"588_CR55","doi-asserted-by":"crossref","unstructured":"Zhang S, McClean S, Scotney B (2007) Knowledge discovery from semantically heterogeneous aggregate databases using model-based clustering. In: Proceedings of the BNCOD, Glasgow, Scotland. Springer, Berlin, pp 190\u2013202","DOI":"10.1007\/978-3-540-73390-4_22"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-012-0588-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-012-0588-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-012-0588-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T22:01:38Z","timestamp":1714773698000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-012-0588-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12,22]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["588"],"URL":"https:\/\/doi.org\/10.1007\/s10115-012-0588-4","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,12,22]]}}}