{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:53:01Z","timestamp":1774367581251,"version":"3.50.1"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2015,10,17]],"date-time":"2015-10-17T00:00:00Z","timestamp":1445040000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s10462-015-9446-6","type":"journal-article","created":{"date-parts":[[2015,10,19]],"date-time":"2015-10-19T00:19:51Z","timestamp":1445213991000},"page":"271-297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Facilitating data preprocessing by a generic framework: a proposal for clustering"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4638-0403","authenticated-orcid":false,"given":"Kathrin","family":"Kirchner","sequence":"first","affiliation":[]},{"given":"Jelena","family":"Zec","sequence":"additional","affiliation":[]},{"given":"Boris","family":"Deliba\u0161i\u0107","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,10,17]]},"reference":[{"key":"9446_CR1","doi-asserted-by":"crossref","unstructured":"Ankerst M, Breunig MM, Kriegel H-P (1999) OPTICS: ordering points to identify the clustering structure. In: ACM, Sigmod record, pp 49\u201360","DOI":"10.1145\/304182.304187"},{"key":"9446_CR2","first-page":"585","volume":"14","author":"M Belkin","year":"2002","unstructured":"Belkin M, Niyogi P (2002) Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Process Syst 14:585\u2013591","journal-title":"Adv Neural Inf Process Syst"},{"key":"9446_CR3","doi-asserted-by":"crossref","unstructured":"Berkhin P (2006) A survey of clustering data mining techniques. In: Grouping multidimensional data. Springer, Berlin, pp 25\u201371","DOI":"10.1007\/3-540-28349-8_2"},{"issue":"4","key":"9446_CR4","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1109\/TKDE.2005.67","volume":"17","author":"A Bernstein","year":"2005","unstructured":"Bernstein A, Provost F, Hill S (2005) Toward intelligent assistance for a data mining process: an ontology-based approach for cost-sensitive classification. IEEE Trans Knowl Data Eng 17(4):503\u2013518","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9446_CR5","doi-asserted-by":"crossref","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, K\u00f6tter T, Meinl T, Ohl P, Sieb C, Thiel K, Wiswedel B (2008) KNIME: the Konstanz information miner. In: Data analysis, machine learning and applications. Springer, Berlin, pp 319\u2013326","DOI":"10.1007\/978-3-540-78246-9_38"},{"key":"9446_CR6","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-0450-1","volume-title":"Pattern recognition with fuzzy objective function algorithms","author":"JC Bezdek","year":"1981","unstructured":"Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York"},{"key":"9446_CR7","unstructured":"Chakraborty S, Nagwani NK (2011) Analysis and study of incremental DBSCAN clustering algorithm. IJECBS 1(2). http:\/\/www.ijecbs.com\/July2011\/44.pdf"},{"key":"9446_CR8","doi-asserted-by":"crossref","unstructured":"Chan C, Batur C, Sirnivasan A (1991) Determination of quantization intervals in rule based model for dynamic. In: Proceedings of the IEEE conference on systems, pp 1719\u20131723","DOI":"10.1109\/ICSMC.1991.169942"},{"key":"9446_CR9","unstructured":"Chapman P, Clinton J, Kerber R, Khabaza T, Reinartz T, Shearer C, Wirth R (2000) CRISP-DM 1.0 Step-by-step data mining guide. SPSS Inc. ftp:\/\/ftp.software.ibm.com\/software\/analytics\/spss\/support\/Modeler\/Documentation\/14\/UserManual\/CRISP-DM.pdf"},{"key":"9446_CR10","doi-asserted-by":"crossref","unstructured":"Chickering D, Meek C, and Rounthwaite R (2001) Efficient determination of dynamic split points in a decision tree. In: Proceedings 2001 IEEE international conference on data mining, pp 91\u201398","DOI":"10.1109\/ICDM.2001.989505"},{"key":"9446_CR11","doi-asserted-by":"crossref","DOI":"10.1201\/9781420036121","volume-title":"Multidimensional scaling","author":"T Cox","year":"2000","unstructured":"Cox T, Cox M (2000) Multidimensional scaling. Chapman & Hall, London"},{"issue":"5","key":"9446_CR12","first-page":"327","volume":"15","author":"B Deliba\u0161i\u0107","year":"2011","unstructured":"Deliba\u0161i\u0107 B, Jovanovi\u0107 M, Vuki\u0107evi\u0107 M, Suknovi\u0107 M, Obradovi\u0107 Z (2011) Component-based decision trees for classification. Mach Learn 15(5):327\u2013334","journal-title":"Mach Learn"},{"key":"9446_CR13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-78246-9_39","volume-title":"A pattern based data mining approach","author":"B Deliba\u0161i\u0107","year":"2008","unstructured":"Deliba\u0161i\u0107 B, Kirchner K, Ruhland J (2008) A pattern based data mining approach. Springer, Berlin"},{"issue":"1\u20134","key":"9446_CR14","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s10462-009-9133-6","volume":"32","author":"B Deliba\u0161i\u0107","year":"2009","unstructured":"Deliba\u0161i\u0107 B, Kirchner K, Ruhland J, Jovanovi\u0107 M, Vuki\u0107evi\u0107 M (2009) Reusable components for partitioning clustering algorithms. Artif Intell Rev 32(1\u20134):59\u201375","journal-title":"Artif Intell Rev"},{"key":"9446_CR15","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.datak.2012.03.005","volume":"75","author":"B Deliba\u0161i\u0107","year":"2012","unstructured":"Deliba\u0161i\u0107 B, Vuki\u0107evi\u0107 M, Jovanovi\u0107 M, Kirchner K, Ruhland J, Suknovi\u0107 M (2012) An architecture for component-based design of representative-based clustering algorithms. Data Knowl Eng 75:78\u201398","journal-title":"Data Knowl Eng"},{"key":"9446_CR16","first-page":"580","volume":"5","author":"D Demers","year":"1993","unstructured":"Demers D, Cottrell G, Diego S, Jolla L (1993) Non linear dimensionality reduction. Adva Neural Inf Process Syst 5:580\u2013587","journal-title":"Adva Neural Inf Process Syst"},{"key":"9446_CR17","doi-asserted-by":"crossref","unstructured":"Dem\u0161ar J, Zupan B, Leban G, Curk T (2004) Orange: from experimental machine learning to interactive data mining. In: PKDD 2004. Knowledge discovery in databases. Springer, Berlin, pp 537\u2013539","DOI":"10.1007\/978-3-540-30116-5_58"},{"issue":"1","key":"9446_CR18","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"E Dijkstra","year":"1959","unstructured":"Dijkstra E (1959) A note on two problems in connexion with graphs. Numer Math 1(1):269\u2013271","journal-title":"Numer Math"},{"key":"9446_CR19","unstructured":"Donoho D, Grimes C (2005) New locally linear embedding techniques for high-dimensional data. In: Proceedings of the National Academy of Sciences, pp 7426\u20137431"},{"key":"9446_CR20","doi-asserted-by":"crossref","unstructured":"Dougherty J, Kohavi R, and Sahami M (1995) Supervised and unsupervised discretization of continuous features. ICML, pp 194\u2013202","DOI":"10.1016\/B978-1-55860-377-6.50032-3"},{"key":"9446_CR21","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1023\/B:DAMI.0000015868.85039.e6","volume":"8","author":"T Elomaa","year":"2004","unstructured":"Elomaa T, Rousu J (2004) Efficient multisplitting revisited: optima-preserving. Data Min Knowl Disc 8:97\u2013126","journal-title":"Data Min Knowl Disc"},{"key":"9446_CR22","volume-title":"Applied missing data analysis","author":"C Enders","year":"2010","unstructured":"Enders C (2010) Applied missing data analysis. Guilford Press, New York"},{"key":"9446_CR23","unstructured":"Engels R, Theusinger C (1998) Using a data metric for preprocessing advice for data mining applications. In: Machine learning, pp 430\u2013434"},{"key":"9446_CR24","unstructured":"Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd international conference on knowledge discovery and data mining, KDD, pp 226\u2013231"},{"key":"9446_CR25","unstructured":"Fayyad U, Piatetsky-Shapiro G, Smyth P, Uthurusamy R (1996) Advances in knowledge discovery and data mining. American Association for Artificial Intelligence"},{"key":"9446_CR26","doi-asserted-by":"crossref","unstructured":"Fodor I (2002) A survey of dimension reduction techniques. Technical report 1, U.S. Department of Energy","DOI":"10.2172\/15002155"},{"key":"9446_CR27","unstructured":"Fong M (2007) Dimension reduction on hyperspectral images. Technical report Figure 1, UCLA Department of Mathematics, Los Angeles"},{"key":"9446_CR28","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/3-540-47887-6_4","volume":"2336","author":"A Foss","year":"2002","unstructured":"Foss A, Lee C-H, Wang W (2002) On data clustering analysis: scalability, constraints and validation. Adv Knowl Discov Data Min 2336:28\u201339","journal-title":"Adv Knowl Discov Data Min"},{"key":"9446_CR29","doi-asserted-by":"crossref","unstructured":"Frank E, Hall M, Holmes G, Kirkby R, Pfahringer B, Witten IH, Trigg L (2005) Weka. In: Data mining and knowledge discovery handbook. Springer, US, pp 1305\u20131314","DOI":"10.1007\/0-387-25465-X_62"},{"key":"9446_CR30","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/978-3-319-10247-4_8","volume":"72","author":"S Garc\u00eda","year":"2015","unstructured":"Garc\u00eda S, Luengo J, Herrera F (2015) Instance selection. Data Preprocess Data Min 72:195\u2013243","journal-title":"Data Preprocess Data Min"},{"key":"9446_CR31","unstructured":"Grira N, Crucianu M, Boujemaa N, Rocquencourt I (2005) Unsupervised and semi-supervised clustering: a brief survey. Technical report, Report of the MUSCLE European Network of Excellence"},{"key":"9446_CR32","doi-asserted-by":"crossref","unstructured":"Guha S, Rastogi R, Shim K (1998) CURE: an efficient clustering algorithm for large databases. In: Proceedings of the international conference on management of data, (SIGMOD), pp 73\u201384, Seattle. ACM Press","DOI":"10.1145\/276304.276312"},{"key":"9446_CR33","doi-asserted-by":"crossref","unstructured":"Guha S, Rastogi R, Shim K (1999) ROCK: a robust clustering algorithm for categorical attributes. In: 15th international conference on data engineering (ICDE\u201999), pp 345\u2013366","DOI":"10.1109\/ICDE.1999.754967"},{"key":"9446_CR34","doi-asserted-by":"crossref","unstructured":"Gul N, Barki I, Akhtar N (2009) MFP: a mechanism for determining associated patterns of stock. Architecture, pp 1\u20137","DOI":"10.1145\/1838002.1838036"},{"key":"9446_CR35","volume-title":"Data mining: concepts and techniques","author":"J Han","year":"2011","unstructured":"Han J, Kamber M (2011) Data mining: concepts and techniques. Morgan Kaufmann, Los Altos"},{"key":"9446_CR36","unstructured":"IBM Director of Licensing, I. C. (2012) IBM SPSS 21 Information Center"},{"key":"9446_CR37","volume-title":"Algorithms for clustering data","author":"A Jain","year":"1988","unstructured":"Jain A, Dubes R (1988) Algorithms for clustering data. Prentice-Hall, Englewood Cliffs"},{"issue":"8","key":"9446_CR38","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","volume":"31","author":"AK Jain","year":"2010","unstructured":"Jain AK (2010) Data clustering: 50\u00a0years beyond K-means. Pattern Recognit Lett 31(8):651\u2013666","journal-title":"Pattern Recognit Lett"},{"issue":"1","key":"9446_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-008-0142-6","volume":"19","author":"R Jin","year":"2008","unstructured":"Jin R, Breitbart Y, Muoh C (2008) Data discretization unification. Knowl Inf Syst 19(1):1\u201329","journal-title":"Knowl Inf Syst"},{"key":"9446_CR40","doi-asserted-by":"crossref","unstructured":"Jin W, Tung AKH, Han J (2001) Mining top-n local outliers in large databases. In: Proceedings of the seventh ACM SIGKDD international conference on knowledge discovery and data mining\u2014KDD \u201901, pp 293\u2013298","DOI":"10.1145\/502512.502554"},{"key":"9446_CR41","first-page":"849","volume":"14","author":"A Jordan","year":"2001","unstructured":"Jordan A, Ng M, Weiss Y (2001) On spectral clustering: analysis and an algorithm. Adv Neural Inf Process Syst 14:849\u2013856","journal-title":"Adv Neural Inf Process Syst"},{"key":"9446_CR42","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3233\/IDA-130628","volume":"18","author":"M Jovanovi\u0107","year":"2014","unstructured":"Jovanovi\u0107 M, Deliba\u0161i\u0107 B, Vuki\u0107evi\u0107 M, Suknovi\u0107 M, Marti\u0107 M et al (2014) Evolutionary approach for automated component-based decision tree algorithm design. Intell Data Anal 18:25\u201342","journal-title":"Intell Data Anal"},{"issue":"7","key":"9446_CR43","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1162\/neco.1997.9.7.1493","volume":"9","author":"N Kambhatla","year":"1997","unstructured":"Kambhatla N, Leen TK (1997) Dimension reduction by local principal component analysis. Neural Comput 9(7):1493\u20131516","journal-title":"Neural Comput"},{"key":"9446_CR44","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029145","volume-title":"Data mining: concepts, models, methods, and algorithms","author":"M Kantardzic","year":"2011","unstructured":"Kantardzic M (2011) Data mining: concepts, models, methods, and algorithms, 2nd edn. Wiley, New York","edition":"2"},{"key":"9446_CR45","volume-title":"Clustering by means of medoids","author":"L Kaufman","year":"1987","unstructured":"Kaufman L, Rousseeuw P (1987) Clustering by means of medoids. North-Holland, Amsterdam"},{"key":"9446_CR46","doi-asserted-by":"crossref","unstructured":"Kaufman L, Rousseeuw PJ (1990) Clustering large applications (Program CLARA). In: Finding groups in data: an introduction to cluster analysis. Wiley, Hoboken","DOI":"10.1002\/9780470316801.ch3"},{"key":"9446_CR47","doi-asserted-by":"crossref","unstructured":"Khabaza T, Shearer C (1995) Data mining with Clementine. IEE colloquium on knowledge discovery in databases, IEE Digest No. 1995\/021(B), London","DOI":"10.1049\/ic:19950121"},{"key":"9446_CR48","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1177\/004912417700600206","volume":"6","author":"J Kim","year":"1977","unstructured":"Kim J, Curry J (1977) The treatment of missing data in multivariate analysis. Sociol Methods Res 6:215\u2013240","journal-title":"Sociol Methods Res"},{"key":"9446_CR49","first-page":"23","volume":"34","author":"K Kirchner","year":"2010","unstructured":"Kirchner K, Deliba\u0161i\u0107 B, Vuki\u0107evi\u0107 M (2010) Projektovanje procesa klasterovanja pomo\u0107u paterna (Designing the clustering process with reusable components). InfoM 34:23\u201329","journal-title":"InfoM"},{"issue":"01","key":"9446_CR50","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0269888906000737","volume":"21","author":"LA Kurgan","year":"2006","unstructured":"Kurgan LA, Musilek P (2006) A survey of Knowledge Discovery and Data Mining process models. Knowl Eng Rev 21(01):1","journal-title":"Knowl Eng Rev"},{"key":"9446_CR51","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/TPAMI.2006.56","volume":"28","author":"M Law","year":"2006","unstructured":"Law M, Jain A (2006) Incremental nonlinear dimensionality reduction by manifold learning. IEEE Trans Pattern Anal Mach Intell 28:377\u2013391","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9446_CR52","first-page":"6","volume":"1543","author":"K Leyton-Brown","year":"2003","unstructured":"Leyton-Brown K, Nudelman E, Andrew G, Mcfadden J, Shoham Y (2003) A portfolio approach to algorithm selection. IJCAI 1543:6\u20137","journal-title":"IJCAI"},{"key":"9446_CR53","doi-asserted-by":"crossref","unstructured":"Li D, Zhong C, Zhang L (2010) Fuzzy c-means clustering of partially missing data sets based on statistical representation. In: 2010 seventh international conference on fuzzy systems and knowledge discovery (FSKD 2010), pp 460\u2013464","DOI":"10.1109\/FSKD.2010.5569767"},{"key":"9446_CR54","unstructured":"Lichman M (2013) UCI machine learning repository. http:\/\/archive.ics.uci.edu\/ml . University of California, School of Information and Computer Science, Irvine, CA"},{"issue":"1","key":"9446_CR55","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TNN.2007.901277","volume":"19","author":"H Lu","year":"2008","unstructured":"Lu H, Plataniotis KNK, Venetsanopoulos AN (2008) MPCA: multilinear principal component analysis of tensor objects. IEEE Trans Neural Netw 19(1):18\u201339","journal-title":"IEEE Trans Neural Netw"},{"key":"9446_CR56","unstructured":"MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkeley symposium on mathematics, pp 281\u2013297"},{"key":"9446_CR57","doi-asserted-by":"crossref","unstructured":"Mierswa I, Wurst M, Klinkenberg R, Scholz M, Euler T (2006) YALE: rapid prototyping for complex data mining tasks. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1\u20136","DOI":"10.1145\/1150402.1150531"},{"key":"9446_CR58","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1177\/014662168701100401","volume":"11","author":"GW Milligan","year":"1987","unstructured":"Milligan GW, Martha C (1987) Methodology review: clustering methods. Appl Psychol Meas 11:329\u2013354","journal-title":"Appl Psychol Meas"},{"key":"9446_CR59","doi-asserted-by":"crossref","unstructured":"Othman Z, Bakar A, Hamdan A, Omar K, Shuib M, Liyana N (2007) Agent based preprocessing. In: Intelligent and advanced systems, pp 219\u2013223","DOI":"10.1109\/ICIAS.2007.4658378"},{"key":"9446_CR60","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/MIS.2007.7","volume":"22","author":"J Pan","year":"2007","unstructured":"Pan J, Yang Q, Yang Y, Li L, Li F, Li G (2007) Cost-sensitive-data preprocessing for mining customer relationship management databases. Intell Syst IEEE 22:46\u201351","journal-title":"Intell Syst IEEE"},{"key":"9446_CR61","unstructured":"Pelleg D, Moore AW (2000) X-means: extending k-means with efficient estimation of the number of clusters. In: ICML, pp 727\u2013734"},{"key":"9446_CR62","unstructured":"Rakotomalala R (2005) TANAGRA: a free software for research and academic purposes. In: Proceedings of EGC, vol 2. pp 697\u2013702"},{"key":"9446_CR63","unstructured":"Raymond TN, Han JW (1994) Efficient and effective clustering methods for spatial data mining. In: Proceedings of the 20th international conference on very large data bases, pp 144\u2013155"},{"key":"9446_CR64","unstructured":"R Development Core Team (2008) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. ISBN 3-900051-07-0. http:\/\/www.Rproject.org"},{"key":"9446_CR65","unstructured":"Rexer K (2013) 6th Rexer Analytics Data Miner Survey. Technical report, Rexer Analytics"},{"key":"9446_CR66","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0065-2458(08)60520-3","volume":"15","author":"J Rice","year":"1975","unstructured":"Rice J (1975) The algorithm selection problem. Adv Comput 15:65\u2013118","journal-title":"Adv Comput"},{"key":"9446_CR67","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"P Rousseeuw","year":"1987","unstructured":"Rousseeuw P (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365","journal-title":"J Comput Appl Math"},{"key":"9446_CR68","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-03345-6","volume-title":"Software engineering with reusable components","author":"J Sametinger","year":"1997","unstructured":"Sametinger J (1997) Software engineering with reusable components. Springer, Berlin"},{"key":"9446_CR69","unstructured":"SAS Institute (2008) SAS Enterprise Miner SEMMA"},{"key":"9446_CR70","volume-title":"Spectral methods for dimensionality reduction","author":"LK Saul","year":"2006","unstructured":"Saul LK, Weinberger KQ, Lee DD (2006) Spectral methods for dimensionality reduction. MIT Press, Cambridge"},{"issue":"2","key":"9446_CR71","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G Schwarz","year":"2008","unstructured":"Schwarz G (2008) Estimating the dimension of a model. Ann Stat 6(2):461\u2013464","journal-title":"Ann Stat"},{"key":"9446_CR72","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809682","volume-title":"Kernel methods for pattern analysis","author":"J Shawe-Taylor","year":"2004","unstructured":"Shawe-Taylor J, Christianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge"},{"issue":"1","key":"9446_CR73","first-page":"6","volume":"41","author":"KA Smith-Miles","year":"2008","unstructured":"Smith-Miles KA (2008) Cross-disciplinary perspectives on meta-learning for algorithm selection. ACM Comput Surv 41(1):6","journal-title":"ACM Comput Surv"},{"key":"9446_CR74","first-page":"2443","volume":"8","author":"S Sonnenburg","year":"2007","unstructured":"Sonnenburg S, Braun M, Ong CS, Bengio S, Bottou L, Holmes G, Lecun Y, M\u00fcller K-R, Raetsch G, Sch\u00f6lkopf B, Weston J, Williamson B (2007) The need for open source software in machine learning. J Mach Learn Res 8:2443\u20132466","journal-title":"J Mach Learn Res"},{"issue":"5500","key":"9446_CR75","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"JB Tenenbaum","year":"2000","unstructured":"Tenenbaum JB, Silva VD, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319\u20132323","journal-title":"Science"},{"key":"9446_CR76","doi-asserted-by":"crossref","unstructured":"Teng L, Li H, Fu X, Chen W, Shen I (2005) Dimension reduction of microarray data based on local tangent space alignment. In: Proceedings of the 4th IEEE international conference on cognitive informatics, pp 154\u2013159","DOI":"10.1109\/COGINF.2005.1532627"},{"key":"9446_CR77","first-page":"731","volume":"13","author":"P Valarmathie","year":"2009","unstructured":"Valarmathie P, Dinakaran K (2009) An increased performance of clustering high dimensional data through dimensionality. J Theor Appl Inf Technol 13:731\u2013733","journal-title":"J Theor Appl Inf Technol"},{"key":"9446_CR78","unstructured":"Van de Merckt T (1993) Decision trees in numerical attribute spaces. In: 13th international joint conference on artificial intelligence"},{"key":"9446_CR79","unstructured":"Van Der Maaten LJP, Postma EO, Herik HJVD (2008) Dimensionality reduction: a comparative review. J Mach Learn Res 10(January):66\u201371"},{"key":"9446_CR80","unstructured":"Vannucci M, Colla V (2004) Meaningful discretization of continuous features for association rules mining by means of a SOM. European Symposium on Artificial Neural Networks, Bruges"},{"key":"9446_CR81","first-page":"2837","volume":"11","author":"NX Vinh","year":"2009","unstructured":"Vinh NX, Bailey J (2009) Information theoretic measures for clusterings comparison: is a correction for chance necessary? J Mach Learn Res 11:2837\u20132854","journal-title":"J Mach Learn Res"},{"issue":"11","key":"9446_CR82","first-page":"111","volume":"35","author":"M Vuki\u0107evi\u0107","year":"2012","unstructured":"Vuki\u0107evi\u0107 M, Kirchner K, Deliba\u0161i\u0107 B, Jovanov\u0131\u2019c M, Ruhland J, Suknovi\u0107 M (2012) Finding best algorithmic components for clustering microarray data. Knowl Inf Syst 35(11):111\u2013130","journal-title":"Knowl Inf Syst"},{"key":"9446_CR83","doi-asserted-by":"crossref","unstructured":"Weiss Y (1999) Segmentation using eigenvectors: a unifying view. In: Proceedings of the IEEE international conference on computer vision. IEEE Computer Society Press, p 2","DOI":"10.1109\/ICCV.1999.790354"},{"key":"9446_CR84","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1214\/aoms\/1177732885","volume":"3","author":"S Wilks","year":"1932","unstructured":"Wilks S (1932) Moments and distributions of estimates of population parameters from fragmentary samples. Ann Math Stat 3:163\u2013195","journal-title":"Ann Math Stat"},{"key":"9446_CR85","unstructured":"Wirth R, Hipp J (2000) CRISP-DM: towards a standard process model for data mining. In: Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining, pp 29\u201339"},{"key":"9446_CR86","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TPAMI.1987.4767986","volume":"9","author":"A Wong","year":"1987","unstructured":"Wong A, Chiu D (1987) Synthesizing statistical knowledge from incomplete mixed-mode data. IEEE Trans Pattern Anal Mach Intell 9:796\u2013805","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"9446_CR87","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1109\/TPAMI.1979.4766942","volume":"1","author":"AK Wong","year":"1979","unstructured":"Wong AK, Wang DC (1979) DECA: a discrete-valued data clustering algorithm. IEEE Trans Pattern Anal Mach Intell 1(4):342\u2013349","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9446_CR88","doi-asserted-by":"crossref","unstructured":"Wu J, Song C-H, Kong JM, Lee WD (2007) Extended mean field annealing for clustering incomplete data. In: 2007 international symposium on information technology convergence (ISITC 2007). IEEE, pp 8\u201312","DOI":"10.1109\/ISITC.2007.30"},{"issue":"8","key":"9446_CR89","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/34.85677","volume":"13","author":"X Xie","year":"1991","unstructured":"Xie X, Beni G (1991) A validity measure for fuzzy clustering. IEEE Trans Pattern Anal Mach Intell 13(8):841\u2013847","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9446_CR90","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu R, Wunsch D (2005) Survey of clustering algorithms. IEEE Trans Neural Netw 16:645\u2013678","journal-title":"IEEE Trans Neural Netw"},{"key":"9446_CR91","doi-asserted-by":"crossref","unstructured":"Zhang T, Ramakrishnan R, Livny M (1996) BIRCH: an efficient data clustering method for very large databases. In: Proceedings of the international conference on management of data, (SIGMOD), pp 103\u2013114","DOI":"10.1145\/233269.233324"},{"key":"9446_CR92","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1137\/S1064827502419154","volume":"26","author":"Z Zhang","year":"2004","unstructured":"Zhang Z, Zha H (2004) Principal manifolds and nonlinear dimensionality reduction via local tangent space alignment. SIAM J Sci Comput 26:313\u2013338","journal-title":"SIAM J Sci Comput"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-015-9446-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-015-9446-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-015-9446-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T13:23:29Z","timestamp":1692105809000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-015-9446-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10,17]]},"references-count":92,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["9446"],"URL":"https:\/\/doi.org\/10.1007\/s10462-015-9446-6","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10,17]]}}}