{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:38:32Z","timestamp":1761863912058,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","award":["745829"],"award-info":[{"award-number":["745829"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1007\/s00607-018-0683-9","type":"journal-article","created":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T16:35:37Z","timestamp":1543682137000},"page":"1687-1710","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A distributed, proactive intelligent scheme for securing quality in large scale data processing"],"prefix":"10.1007","volume":"101","author":[{"given":"Kostas","family":"Kolomvatsos","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,1]]},"reference":[{"key":"683_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2005.9","volume":"17","author":"E Acuna","year":"2005","unstructured":"Acuna E, Rodriguez C (2005) An empirical study of the effect of outliers on the misclassification error rate. Trans Knowl Data Eng 17:1\u201321","journal-title":"Trans Knowl Data Eng"},{"key":"683_CR2","unstructured":"Alferes J, Poirier P, Lamaire-Chad C, Sharma AK, Mikkelsen PS, Vanrolleghem PA (2013) Data quality assurance inmonitoring of wastewater quality: univariate on-line and off-linemethods. In: Proceedings of the 11th IWA conference on instrumentation control and automation. pp 18\u201320"},{"key":"683_CR3","first-page":"313","volume":"33","author":"J Alipour","year":"2017","unstructured":"Alipour J, Ahmadi M (2017) Dimensions and assessment methods of data quality in health information systems. Acta Med Mediterr 33:313\u2013320","journal-title":"Acta Med Mediterr"},{"key":"683_CR4","doi-asserted-by":"crossref","unstructured":"Arapoglou R, Kolomvatsos K, Hadjiefthymiades S (2010) Buyer agent decision process based on automatic fuzzy rules generation methods. In: Proceedings of the 2010 IEEE world congress on computational intelligence (WCCI 2010), FUZ-IEEE, July 18th\u201323rd, Barcelona. pp 856\u2013863","DOI":"10.1109\/FUZZY.2010.5584416"},{"issue":"1","key":"683_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.4018\/JDM.2015010103","volume":"26","author":"C Batini","year":"2015","unstructured":"Batini C, Rula A, Scannapieco M, Viscusi G (2015) From data quality to big data quality. J Database Manag 26(1):60\u201382","journal-title":"J Database Manag"},{"issue":"2","key":"683_CR6","first-page":"1","volume":"14","author":"L Cai","year":"2015","unstructured":"Cai L, Zhu Y (2015) The challenges of data quality and data quality assessment in the big data era. Data Sci J 14(2):1\u201310","journal-title":"Data Sci J"},{"key":"683_CR7","unstructured":"Cong G, Fan W, Geerts F, Jia X, Ma S (2007) Improving data quality: consistency and accuracy. In: Proceedings of the VLDB, Vienna, Austria. pp 1\u201312"},{"issue":"1","key":"683_CR8","first-page":"153","volume":"5","author":"TK Das","year":"2013","unstructured":"Das TK, Kumar PM (2013) Big data analytics: a framework for unstructured data analysis. Int J Eng Technol 5(1):153\u2013156","journal-title":"Int J Eng Technol"},{"issue":"8","key":"683_CR9","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1038\/nbt1406","volume":"26","author":"CB Do","year":"2008","unstructured":"Do CB, Batzoglou S (2008) What is the expectation maximization algorithm? Nat Biotechnol 26(8):897\u2013899","journal-title":"Nat Biotechnol"},{"key":"683_CR10","volume-title":"Handbook on data quality assessment methods and tools","author":"Eurostat","year":"2007","unstructured":"Eurostat (2007) Handbook on data quality assessment methods and tools. European Commission, Luxembourg"},{"key":"683_CR11","first-page":"1663","volume":"11","author":"P Forero","year":"2010","unstructured":"Forero P, Cano A, Giannakis G (2010) Consensus-based distributed support vector machines. JMLR 11:1663\u20131707","journal-title":"JMLR"},{"key":"683_CR12","doi-asserted-by":"publisher","unstructured":"Gao J, Xie C, Tao C (2016) Big data validation and quality assurance-issues, challenges and needs. In: Proceedings of the IEEE symposium on service-oriented system engineering (SOSE). \n                    https:\/\/doi.org\/10.1109\/SOSE.2016.63","DOI":"10.1109\/SOSE.2016.63"},{"key":"683_CR13","unstructured":"Guo H, Zhang J (2016) A distributed and scalable machine learning approach for big data. In: Proceedings of the 25th international joint conference of artificial intelligence, New York"},{"key":"683_CR14","volume-title":"Data mining, concepts and techniques","author":"J Han","year":"2012","unstructured":"Han J, Kamber M, Pei J (2012) Data mining, concepts and techniques, 3rd edn. Morgan Kaufmann Publishers, Burlington","edition":"3"},{"key":"683_CR15","unstructured":"Halkidi M, Varzigiannis M (2001) Clustering validity assessment: finding the optimal partitioning of a dataset. In: Proceedings of the IEEE international conference on data mining, San Jose, USA,"},{"key":"683_CR16","doi-asserted-by":"crossref","unstructured":"Hasani Z (2017) Robust anomaly detection algorithms for real-time bigdata: comparison of algorithms. In: Proceedings of the 6th Mediterranean conference on embedded computing (MECO)","DOI":"10.1109\/MECO.2017.7977130"},{"key":"683_CR17","doi-asserted-by":"publisher","first-page":"2028","DOI":"10.1109\/ACCESS.2015.2490723","volume":"3","author":"A Immonen","year":"2015","unstructured":"Immonen A, Paakkonen P, Ovaska E (2015) Evaluating the quality of social media data in big data architecture. IEEE Access 3:2028\u20132043","journal-title":"IEEE Access"},{"key":"683_CR18","unstructured":"Karjee J, Jamadagni HS (2011) Data accuracy model for distributed clustering algorithm based on spatial data correlation in wireless sensor networks. Networking and internet architecture. \n                    arXiv:1108.2644"},{"key":"683_CR19","unstructured":"Last M, Kandel A (2001) Automated detection of outliers in real-world data. In: Proceedings of the 2nd international conference on intelligent technologies"},{"key":"683_CR20","doi-asserted-by":"crossref","unstructured":"Loshin D (2011) Monitoring data quality performance using data quality metrics. Informatica, The Data Integration Company, white paper","DOI":"10.1016\/B978-0-12-373717-5.00003-8"},{"key":"683_CR21","unstructured":"Majewska J (2015) Identification of multivariate outliers-problems and challenges of visualization methods, Studia Ekonomiczne. Zeszyty Naukowe, Uniwersytetu Ekonomicznego w Katowicach, No 247"},{"key":"683_CR22","unstructured":"Management Group on Statistical Cooperation (2014) Report of the sixteenth meeting. European Commission, Eurostat, vol Doc., p MGSC\/2014\/14"},{"issue":"2","key":"683_CR23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MCI.2007.357235","volume":"2","author":"JM Mendel","year":"2007","unstructured":"Mendel JM (2007) Type-2 fuzzy sets and systems: an overview. IEEE Comput Intell Mag 2(2):20\u201329","journal-title":"IEEE Comput Intell Mag"},{"key":"683_CR24","volume-title":"Uncertain rule-based fuzzy logic systems: introduction and new directions","author":"JM Mendel","year":"2001","unstructured":"Mendel JM (2001) Uncertain rule-based fuzzy logic systems: introduction and new directions. Prentice-Hall, Upper Saddle River"},{"key":"683_CR25","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.future.2015.11.024","volume":"63","author":"J Merino","year":"2016","unstructured":"Merino J, Caballero I, Rivas B, Serrano M, Piattini M (2016) A Data quality in use model for big data. Future Gener Comput Syst 63:123\u2013130","journal-title":"Future Gener Comput Syst"},{"issue":"8","key":"683_CR26","first-page":"67","volume":"6","author":"S Mishra","year":"2016","unstructured":"Mishra S, Suman AC (2016) An efficient method of partitioning high volumes of multidimensional data for parallel clustering algorithms. Int J Eng Res Appl 6(8):67\u201371","journal-title":"Int J Eng Res Appl"},{"issue":"3","key":"683_CR27","doi-asserted-by":"publisher","first-page":"333","DOI":"10.14257\/ijdta.2015.8.3.29","volume":"8","author":"AO Mohammed","year":"2015","unstructured":"Mohammed AO, Talab SA (2015) Enhanced extraction clinical data technique to improve data quality in clinical data warehouse. Int J Database Theory Appl 8(3):333\u2013342","journal-title":"Int J Database Theory Appl"},{"key":"683_CR28","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1145\/1994.2209","volume":"9","author":"S Navathe","year":"1984","unstructured":"Navathe S, Ceri S, Wiederhold G, Dou J (1984) Vertical partitioning of algorithms for database design. ACM Trans Database Syst 9:680\u2013710","journal-title":"ACM Trans Database Syst"},{"issue":"4","key":"683_CR29","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1080\/07421222.2005.11045823","volume":"21","author":"RR Nelson","year":"2005","unstructured":"Nelson RR, Todd PA, Wixom BH (2005) Antecedents of information and system quality: an empirical examination within the context of data warehousing. J Manag Inf Syst 21(4):199\u2013235","journal-title":"J Manag Inf Syst"},{"issue":"1\/2","key":"683_CR30","doi-asserted-by":"publisher","first-page":"100","DOI":"10.2307\/2333009","volume":"41","author":"ES Page","year":"1954","unstructured":"Page ES (1954) Continuous inspection scheme. Biometrika 41(1\/2):100\u2013115","journal-title":"Biometrika"},{"issue":"4","key":"683_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1145\/505248.506010","volume":"45","author":"LL Pipino","year":"2002","unstructured":"Pipino LL, Lee YW, Wang RY (2002) Data quality assessment. Commun ACM 45(4):211\u2013218","journal-title":"Commun ACM"},{"key":"683_CR32","doi-asserted-by":"crossref","unstructured":"Rao D, Gudivada VN, Raghavan VV (2015) Data quality issues in bigdata. In: Proceedings of the IEEE international conference on bigdata, Santa Clara, CA, USA","DOI":"10.1109\/BigData.2015.7364065"},{"key":"683_CR33","doi-asserted-by":"crossref","unstructured":"Rosemary Tate A, Kalra D, Boggon R, Beloff N, Puri S, Williams T (2014) Data quality in European primary care research databases. Report of a workshop held in London September 2013. In: Proceedings of the IEEE-EMBS international conference on biomedical and health informatics (BHI), Valencia, Spain","DOI":"10.1109\/BHI.2014.6864310"},{"key":"683_CR34","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/3148.3161","volume":"10","author":"D Sacca","year":"1985","unstructured":"Sacca D, Wiederhold G (1985) Database partitioning in a cluster of processors. ACM Trans Database Syst 10:29\u201356","journal-title":"ACM Trans Database Syst"},{"key":"683_CR35","unstructured":"Salloum S, He Y, Huang JZ, Zhang X, Emara T (2018) A random sample partition data model for big data analysis. \n                    arXiv:1712.04146"},{"issue":"5","key":"683_CR36","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","volume":"3","author":"W Shi","year":"2016","unstructured":"Shi W, Cao J, Zhang Q, Li Y, Xu L (2016) Edge computing: vision and challenges. IEEE Internet Things 3(5):637\u2013646","journal-title":"IEEE Internet Things"},{"key":"683_CR37","doi-asserted-by":"crossref","unstructured":"Sidi F, Panahy PHS, Affendey LS, Jabar MA, Ibrahim H, Mustapha A (2012) Data quality: a survey of data quality dimensions. In: Proceedings of the international conference on information retrieval and knowledge management (CAMP), Kuala Lumpur, Malaysia, pp 300\u2013304","DOI":"10.1109\/InfRKM.2012.6204995"},{"issue":"1","key":"683_CR38","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.eswa.2014.07.026","volume":"42","author":"LH Son","year":"2015","unstructured":"Son LH (2015) DPFCM: a novel distributed picture fuzzy clustering method on picture fuzzy sets. Expert Syst Appl 42(1):51\u201366","journal-title":"Expert Syst Appl"},{"key":"683_CR39","doi-asserted-by":"crossref","unstructured":"Truong H, Karan M (2018) Analytics of performance and data quality for mobile edge cloud applications. In: Proceedings of the IEEE international conference on cloud computing, workshop: cloud and the edge San Francisco, USA","DOI":"10.1109\/CLOUD.2018.00091"},{"issue":"3","key":"683_CR40","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1023\/A:1010006529488","volume":"1","author":"A Umar","year":"1999","unstructured":"Umar A, Karabatis G, Ness L, Horowitz B, Elmagardmid A (1999) Enterprise data quality. Inf Syst Front 1(3):279\u2013301","journal-title":"Inf Syst Front"},{"key":"683_CR41","doi-asserted-by":"crossref","unstructured":"Urbano F, Basille M, Cagnacci F (2014) Data quality: detection and management of outliers, chapter. In: Spatial database for GPS wildlife tracking. Data: a practical guide to creating a data management system with Postgre SQL\/Post GIS and R. Springer","DOI":"10.1007\/978-3-319-03743-1_8"},{"key":"683_CR42","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.procs.2017.03.006","volume":"106","author":"S Berghe Van den","year":"2017","unstructured":"Van den Berghe S, Van Gaeveren K (2017) Data quality assessment and improvement: a Vrije Universiteit Brussel case study. Procedia Comput Sci 106:32\u201338","journal-title":"Procedia Comput Sci"},{"issue":"6","key":"683_CR43","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MC.2013.195","volume":"46","author":"MR Wigan","year":"2013","unstructured":"Wigan MR, Clarke R (2013) Big data\u2019s big unintended consequences. IEEE Comput 46(6):46\u201353","journal-title":"IEEE Comput"},{"issue":"5","key":"683_CR44","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/TFUZZ.2012.2186818","volume":"20","author":"D Wu","year":"2012","unstructured":"Wu D (2012) On the fundamental differences between interval type-2 and type-1 fuzzy logic controllers. IEEE Trans Fuzzy Syst 20(5):832\u2013848","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"683_CR45","doi-asserted-by":"crossref","unstructured":"Wanger C (2013) Juzzy\u2014a java based toolkit for type-2 fuzzy logic. In: Proceedings of the IEEE symposium on advances in type-2 fuzzy logic systems, Singapore","DOI":"10.1109\/T2FZZ.2013.6613298"},{"key":"683_CR46","unstructured":"Zhu K, Wang H, Bai H, Li J, Qiu Z, Cui H, Chang E (2008) Parallelizing support vector machines on distributed computers. In: Proceedings of NIPS 20"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-018-0683-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-018-0683-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-018-0683-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T07:53:36Z","timestamp":1575273216000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-018-0683-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,1]]},"references-count":46,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["683"],"URL":"https:\/\/doi.org\/10.1007\/s00607-018-0683-9","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"type":"print","value":"0010-485X"},{"type":"electronic","value":"1436-5057"}],"subject":[],"published":{"date-parts":[[2018,12,1]]},"assertion":[{"value":"15 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}