{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T05:33:33Z","timestamp":1725860013987},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319415604"},{"type":"electronic","value":"9783319415611"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-41561-1_32","type":"book-chapter","created":{"date-parts":[[2016,6,27]],"date-time":"2016-06-27T01:11:44Z","timestamp":1466989904000},"page":"428-437","source":"Crossref","is-referenced-by-count":0,"title":["Data Quality Visualization for Preprocessing"],"prefix":"10.1007","author":[{"given":"Markus","family":"Vattulainen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,6,28]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","first-page":"305","DOI":"10.3233\/IDA-2012-0525","volume":"16","author":"S Abdul-Rahmana","year":"2012","unstructured":"Abdul-Rahmana, S., Abu Bakara, A., Hussein, B., Zeti, A.: An intelligent data pre-processing of complex datasets. Intell. Data Anal. 16, 305\u2013325 (2012)","journal-title":"Intell. Data Anal."},{"key":"32_CR2","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Rand Corporation, Princeton University Press (1957)"},{"key":"32_CR3","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84882-260-3","volume-title":"Guide to Intelligent Data Analysis \u2013 How to Intelligently Make Sense of Real Data","author":"MR Berthold","year":"2010","unstructured":"Berthold, M.R., Borgelt, C., H\u00f6ppner, F., Klawonn, F.: Guide to Intelligent Data Analysis \u2013 How to Intelligently Make Sense of Real Data. Springer, London (2010)"},{"key":"32_CR4","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H-P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the ACM SIGMOD 2000 International Conference on Management of Data, pp. 93\u2013104 (2000)","DOI":"10.1145\/342009.335388"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Caruana, R., Niculescu-Mizil, A., Crew, G., Ksikes, A.: Ensemble selection for libraries of models. In: Proceedings of ICML, p. 18 (2004)","DOI":"10.1145\/1015330.1015432"},{"key":"32_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-75936-4","volume-title":"Software for Data Analysis","author":"J Chambers","year":"2008","unstructured":"Chambers, J.: Software for Data Analysis. Springer, New York (2008)"},{"issue":"3","key":"32_CR8","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3), 15 (2009)","journal-title":"ACM Comput. Surv."},{"key":"32_CR9","unstructured":"Chapman, P., Clinton, J., Kerber, R., Khabaza T., Reinartz T., Shearer, C., Wirth R.: Crisp-Dm 1.0 step by step data mining guide, Crisp-DM Consortium (2000)"},{"issue":"3","key":"32_CR10","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1016\/j.ejor.2005.07.023","volume":"173","author":"SF Crone","year":"2005","unstructured":"Crone, S.F., Lessmann, S., Stahlbock, R.: The impact of preprocessing on data mining: an evaluation of classifier sensitivity in direct marketing. Eur. J. Oper. Res. 173(3), 781\u2013800 (2005)","journal-title":"Eur. J. Oper. Res."},{"key":"32_CR11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.trac.2013.04.015","volume":"50","author":"J Engel","year":"2013","unstructured":"Engel, J., Gerretzen, J., Szymanka, E., Jansen, J.J., Downey, G., Blanchet, L., Buydens, L.: Breaking with trends in preprocessing. TrAC Trends Anal. Chem. 50, 96\u2013106 (2013)","journal-title":"TrAC Trends Anal. Chem."},{"issue":"11","key":"32_CR12","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/240455.240464","volume":"39","author":"U Fayyad","year":"1996","unstructured":"Fayyad, U., Piatetsky-Shapiro, G., Smyth, P.: The KDD process for extracting useful knowledge from volumes of data. Commun. ACM 39(11), 27\u201334 (1996)","journal-title":"Commun. ACM"},{"issue":"3","key":"32_CR13","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1016\/j.csda.2007.05.018","volume":"52","author":"P Filzmoser","year":"2008","unstructured":"Filzmoser, P., Maronna, R., Werner, M.: Outlier identification in high dimensions. Comput. Stat. Data Anal. 52(3), 1694\u20131711 (2008)","journal-title":"Comput. Stat. Data Anal."},{"issue":"8","key":"32_CR14","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1108\/01443570710763778","volume":"27","author":"M Franco-Santos","year":"2007","unstructured":"Franco-Santos, M., Kennerley, M., Micheli, P., Martinez, V., Mason, S., Marr, B., Gray, D., Neely, A.: Towards a definition of a business performance measurement system. Int. J. Oper. Prod. Manage. 27(8), 784\u2013801 (2007)","journal-title":"Int. J. Oper. Prod. Manage."},{"issue":"1","key":"32_CR15","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1995","unstructured":"Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119\u2013139 (1995)","journal-title":"J. Comput. Syst. Sci."},{"key":"32_CR16","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157\u20131182 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"32_CR17","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2012","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques. Morgan Kaufmann, San Francisco (2012)"},{"key":"32_CR18","volume-title":"A Practical Guide to Support Vector Classification","author":"C-W Hsu","year":"2010","unstructured":"Hsu, C.-W., Chang, C.-C., Lin, C.-J.: A Practical Guide to Support Vector Classification. Taiwan National University, Taipei (2010)"},{"issue":"2","key":"32_CR19","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1023\/B:AIRE.0000045502.10941.a9","volume":"22","author":"VJ Hodge","year":"2004","unstructured":"Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85\u2013126 (2004)","journal-title":"Artif. Intell. Rev."},{"key":"32_CR20","unstructured":"Hu, M-X., Salvucci, S.: A Study of Imputation Algorithms, Institute of Education Science, NCES, U.S. Department of Education (1991)"},{"issue":"2","key":"32_CR21","doi-asserted-by":"crossref","first-page":"137","DOI":"10.3233\/ICA-2011-0385","volume":"19","author":"M Juhola","year":"2012","unstructured":"Juhola, M., Siermala, M.: A scatter method for data and variable importance evaluation. Integr. Comput. Aided Eng. 19(2), 137\u2013149 (2012)","journal-title":"Integr. Comput. Aided Eng."},{"key":"32_CR22","volume-title":"On Research Methods","author":"P J\u00e4rvinen","year":"2012","unstructured":"J\u00e4rvinen, P.: On Research Methods. Opinpajan kirja, Tampere (2012)"},{"issue":"1","key":"32_CR23","first-page":"71","volume":"71","author":"RS Kaplan","year":"1992","unstructured":"Kaplan, R.S., Norton, D.P.: The balanced scorecard \u2013 measures that drive performance. Harvard Bus. Rev. 71(1), 71\u201379 (1992)","journal-title":"Harvard Bus. Rev."},{"issue":"1","key":"32_CR24","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/s10618-007-0067-9","volume":"15","author":"H-P Kriegel","year":"2007","unstructured":"Kriegel, H.-P., Borgwardt, K.M., Kr\u00f6ger, P., Pryakhin, A., Schubert, M., Zimek, A.: Future trends in data mining. Data Min. Knowl. Disc. 15(1), 87\u201397 (2007)","journal-title":"Data Min. Knowl. Disc."},{"key":"32_CR25","unstructured":"Kriegel, H-P., Kr\u00f6ger P., Zimek, A.: Outlier detection techniques. In: 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC (2010)"},{"key":"32_CR26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied Predictive Modeling","author":"M Kuhn","year":"2013","unstructured":"Kuhn, M., Johnson, K.: Applied Predictive Modeling. Springer, New York (2013)"},{"key":"32_CR27","doi-asserted-by":"publisher","unstructured":"Kochanski, A., Perzyk, M., Klebczyk, M.: Knowledge in imperfect data in advances in knowledge representation. In: Ramirez, C. (ed.) (2012). DOI: 10.5772\/37714 . http:\/\/www.intechopen.com\/books\/advances-inknowledge-representation\/knowledge-in-imperfect-data","DOI":"10.5772\/37714"},{"key":"32_CR28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","volume":"97","author":"R Kohavi","year":"1997","unstructured":"Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97, 273\u2013324 (1997)","journal-title":"Artif. Intell."},{"key":"32_CR29","first-page":"111","volume":"2","author":"SB Kotsiantis","year":"2006","unstructured":"Kotsiantis, S.B., Kanellopoulos, D., Pintelas, P.E.: Data preprocessing for supervised learning. Int. J. Comput. Sci. 2, 111\u2013117 (2006)","journal-title":"Int. J. Comput. Sci."},{"key":"32_CR30","doi-asserted-by":"crossref","DOI":"10.1002\/0471660264","volume-title":"Combining Pattern Classifiers: Methods and Algorithms","author":"L Kuncheva","year":"2004","unstructured":"Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, Hoboken (2004)"},{"key":"32_CR31","unstructured":"Longadge, R., Dongre, S.S., Malik, L.: Class imbalance problem in data mining: review. Int. J. Comput. Sci. Netw. 2(1) (2013)"},{"issue":"1","key":"32_CR32","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1021\/ci00065a010","volume":"30","author":"RG Lawson","year":"1990","unstructured":"Lawson, R.G., Jurs, P.C.: New index for clustering tendency and its application to chemical problems. J. Chem. Inf. Comput. Sci. 30(1), 36\u201341 (1990)","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"4","key":"32_CR33","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0167-9236(94)00041-2","volume":"15","author":"S March","year":"1995","unstructured":"March, S., Smith, G.: Design and natural science research on information technology. J. Decis. Support Syst. 15(4), 251\u2013266 (1995)","journal-title":"J. Decis. Support Syst."},{"issue":"1","key":"32_CR34","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1006\/mare.1999.0121","volume":"11","author":"H N\u00f8rreklit","year":"2000","unstructured":"N\u00f8rreklit, H.: The balance on the balanced scorecard\u2014a critical analysis of some of its assumptions. Manage. Account. Res. 11(1), 65\u201388 (2000)","journal-title":"Manage. Account. Res."},{"key":"32_CR35","volume-title":"Data Preparation for Data Mining","author":"D Pyle","year":"2003","unstructured":"Pyle, D.: Data Preparation for Data Mining. Morgan Kauffman, San Francisco (2003)"},{"key":"32_CR36","volume-title":"C4.5: Programs for Machine Learning","author":"JR Quinlan","year":"1993","unstructured":"Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)"},{"key":"32_CR37","unstructured":"R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2008)"},{"key":"32_CR38","unstructured":"Sadig, S., Yeganeh, N.K., Induska, M.: 20 years of data quality research: themes, trends and synergies. In: ADC 2011 Proceedings of the Twenty-Second Australasian Database Conference, vol. 115, pp. 153\u2013162 (2011)"},{"key":"32_CR39","volume-title":"Software Engineering","author":"I Somerville","year":"2015","unstructured":"Somerville, I.: Software Engineering. Pearson, Boston (2015)"},{"key":"32_CR40","unstructured":"Sondhi, P.: Feature Construction Methods: A Survey, Jan 2016. sifaka.cs.uiuc.edu"},{"key":"32_CR41","doi-asserted-by":"crossref","DOI":"10.1201\/b10328","volume-title":"Data Mining with R: Learning with Case Studies","author":"L Torgo","year":"2010","unstructured":"Torgo, L.: Data Mining with R: Learning with Case Studies. CRC Press, Boca Raton (2010)"},{"key":"32_CR42","unstructured":"Vattulainen, M.: A method to improve the predictive power of a business performance measurement system by data preprocessing combinations: two cases in predictive classification of service sales volume from balanced data. In: Ghazawneh, A., N\u00f8rbjerg, J., Pries-Heje, J. (eds.) Proceedings of the 37th Information Systems Research Seminar in Scandinavia (IRIS 37), Ringsted, Denmark, 10\u201313 August 2014"},{"key":"32_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-20910-4_1","volume-title":"Advances in Data Mining: Applications and Theoretical Aspects","author":"M Vattulainen","year":"2015","unstructured":"Vattulainen, M.: Improving the predictive power of business performance measurement systems by constructed data quality features - five cases. In: Perner, P. (ed.) ICDM 2015. LNCS, vol. 9165, pp. 3\u201316. Springer, Heidelberg (2015)"},{"key":"32_CR44","unstructured":"Vattulainen, M.: Preproviz: Tools for Visualization of Interdependent Data Quality Issues (2016). https:\/\/cran.r-project.org\/web\/packages\/preproviz"},{"issue":"1","key":"32_CR45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-007-0114-2","volume":"14","author":"X Wu","year":"2008","unstructured":"Wu, X., Kumar, V., Quinlan, J.R., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G., Ng, A., Liu, B., Yu, P.S., Zhou, Z.H., Steinbach, M., Hand, D.J., Steinberg, D.: Top 10 algorithms in data mining. Knowl. Inf. Syst. 14(1), 1\u201337 (2008)","journal-title":"Knowl. Inf. Syst."},{"issue":"11","key":"32_CR46","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/240455.240479","volume":"39","author":"Y Wand","year":"1996","unstructured":"Wand, Y., Wang, R.: Anchoring data quality dimensions in ontological foundations. Commun. ACM 39(11), 86\u201395 (1996)","journal-title":"Commun. ACM"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"Wickham, H.: Advanced R. Chapman (2014)","DOI":"10.1201\/b17487"},{"issue":"1","key":"32_CR48","first-page":"97","volume":"26","author":"X Wu","year":"2013","unstructured":"Wu, X., Zhu, X., Wu, G.-Q., Ding, W.: Data mining with big data. IEEE Trans. Knowl. Discov. Data Eng. 26(1), 97\u2013107 (2013)","journal-title":"IEEE Trans. Knowl. Discov. Data Eng."},{"issue":"4","key":"32_CR49","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1142\/S0219622006002258","volume":"5","author":"Q Yang","year":"2006","unstructured":"Yang, Q., Wu, X.: 10 Challenging problems in data mining research. Int. J. Inf. Technol. Decis. Making 5(4), 597\u2013604 (2006)","journal-title":"Int. J. Inf. Technol. Decis. Making"},{"issue":"2","key":"32_CR50","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.is.2003.11.001","volume":"30","author":"H Zhao","year":"2005","unstructured":"Zhao, H., Sudra, R.: Entity identification for heterogenous database integration \u2014a multiple classifier system approach and empirical evaluation. Inf. Syst. 30(2), 119\u2013132 (2005)","journal-title":"Inf. Syst."}],"container-title":["Lecture Notes in Computer Science","Advances in Data Mining. Applications and Theoretical Aspects"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-41561-1_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T07:00:14Z","timestamp":1568098814000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41561-1_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319415604","9783319415611"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41561-1_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}