{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:27:04Z","timestamp":1761611224006},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2008,5,17]],"date-time":"2008-05-17T00:00:00Z","timestamp":1210982400000},"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":[[2009,4]]},"DOI":"10.1007\/s10115-008-0142-6","type":"journal-article","created":{"date-parts":[[2008,5,16]],"date-time":"2008-05-16T12:23:25Z","timestamp":1210940605000},"page":"1-29","source":"Crossref","is-referenced-by-count":48,"title":["Data discretization unification"],"prefix":"10.1007","volume":"19","author":[{"given":"Ruoming","family":"Jin","sequence":"first","affiliation":[]},{"given":"Yuri","family":"Breitbart","sequence":"additional","affiliation":[]},{"given":"Chibuike","family":"Muoh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2008,5,17]]},"reference":[{"key":"142_CR1","volume-title":"Categorical data analysis","author":"A Agresti","year":"1990","unstructured":"Agresti A (1990) Categorical data analysis. Wiley, New York"},{"key":"142_CR2","doi-asserted-by":"crossref","unstructured":"Auer P, Holte R, Maass W (1995) Theory and applications of agnostic pac-learning with small decision trees. In: Machine learning: proceedings of the twelth international conference. Morgan Kaufmann","DOI":"10.1016\/B978-1-55860-377-6.50012-8"},{"issue":"4","key":"142_CR3","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1007\/PL00011680","volume":"3","author":"SD Bay","year":"2001","unstructured":"Bay SD (2001) Multivariate discretization for set mining. Knowl Inf Syst 3(4): 491\u2013512","journal-title":"Knowl Inf Syst"},{"key":"142_CR4","unstructured":"Breiman L, Friedman J, Olshen R, Stone C (1998) Classification and regression trees. CRC Press"},{"key":"142_CR5","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1023\/B:MACH.0000019804.29836.05","volume":"55","author":"M Boulle","year":"2004","unstructured":"Boulle M (2004) Khiops: a statistical discretization method of continuous attributes. Mach Learn 55: 53\u201369","journal-title":"Mach Learn"},{"issue":"1","key":"142_CR6","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s10994-006-8364-x","volume":"65","author":"M Boulle","year":"2006","unstructured":"Boulle M (2006) MODL: a Bayes optimal discretization method for continuous attributes. Mach Learn 65(1): 131\u2013165","journal-title":"Mach Learn"},{"key":"142_CR7","unstructured":"Casella G, Berger RL (2001) Statistical inference, 2nd edn. Duxbury Press"},{"key":"142_CR8","doi-asserted-by":"crossref","unstructured":"Catlett J (1991) On changing continuous attributes into ordered discrete attributes. In: Proceedings of European working session on learning, pp 164\u2013178","DOI":"10.1007\/BFb0017012"},{"issue":"7","key":"142_CR9","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1109\/34.391407","volume":"17","author":"JY Ching","year":"1995","unstructured":"Ching JY, Wong AKC, Chan KCC (1995) Class-dependent discretization for inductive learning from continuous and mixed-mode data. IEEE Trans Pattern Anal Mach Intell 17(7): 641\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"142_CR10","doi-asserted-by":"crossref","unstructured":"Chmielewski MR, Grzymala-Busse JW (1996) Global discretization of continuous attributes as preprocessing for machine learning. Int J Approx Reason 15","DOI":"10.1016\/S0888-613X(96)00074-6"},{"key":"142_CR11","volume-title":"Elements of information thoery","author":"TM Cover","year":"2006","unstructured":"Cover TM, Thomas JA (2006) Elements of information thoery, 2nd edn. Wiley, New York","edition":"2"},{"key":"142_CR12","unstructured":"Dougherty J, Kohavi R, Sahavi M (1995) Supervised and unsupervised discretization of continuous attributes. In: Proceedings of the 12th international conference on machine learning, pp 194\u2013202"},{"issue":"2","key":"142_CR13","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/s10115-003-0099-4","volume":"5","author":"T Elomaa","year":"2003","unstructured":"Elomaa T, Rousu J (2003) Necessary and sufficient pre-processing in numerical range discretization. Knowl Inf Syst 5(2): 162\u2013182","journal-title":"Knowl Inf Syst"},{"key":"142_CR14","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 elimination of partition candidates. Data Mining Knowl Discovery 8: 97\u2013126","journal-title":"Data Mining Knowl Discovery"},{"key":"142_CR15","unstructured":"Fayyad UM, Irani KB (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the 13th joint conference on artificial intelligence, pp 1022\u20131029"},{"issue":"2","key":"142_CR16","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1162\/neco.1995.7.2.219","volume":"7","author":"F Girosi","year":"1995","unstructured":"Girosi F, Jones M, Poggio T (1995) Regularization theory and neural networks architectures. Neural Comput 7(2): 219\u2013269","journal-title":"Neural Comput"},{"key":"142_CR17","doi-asserted-by":"crossref","unstructured":"Hand D, Mannila H, Smyth P (2001) Principles of data mining. MIT Press","DOI":"10.1002\/9780470057339.vad002"},{"key":"142_CR18","first-page":"454","volume":"96","author":"MH Hansen","year":"2001","unstructured":"Hansen MH, Yu B (2001) Model selection and the principle of minimum description length. J Am Statist Assci 96: 454","journal-title":"J Am Statist Assci"},{"key":"142_CR19","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The elements of statistical learning","author":"T Hastie","year":"2001","unstructured":"Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, Heidelberg"},{"key":"142_CR20","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/A:1022631118932","volume":"11","author":"RC Holte","year":"1993","unstructured":"Holte RC (1993) Very simple calssification rules perform well on most commonly used datasets. Mach Learn 11: 63\u201390","journal-title":"Mach Learn"},{"key":"142_CR21","volume-title":"Continuous univariate distributions","author":"N Johnson","year":"1994","unstructured":"Johnson N, Kotz S, Balakrishnan N (1994) Continuous univariate distributions, 2nd edn. Wiley, New York","edition":"2"},{"key":"142_CR22","doi-asserted-by":"crossref","unstructured":"Jin R, Breitbart Y (2007) Data discretization unification. Technical Report, Department of Computer Science, Kent State University. http:\/\/www.cs.kent.edu\/research\/techrpts.html","DOI":"10.1109\/ICDM.2007.35"},{"key":"142_CR23","unstructured":"Kerber R (1992) ChiMerge: discretization of numeric attributes. In: National conference on artificial intelligence"},{"issue":"2","key":"142_CR24","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/TKDE.2004.1269594","volume":"16","author":"LA Kurgan","year":"2004","unstructured":"Kurgan LA, Cios KJ (2004) CAIM discretization algorithm. IEEE Trans Knowl Data Eng 16(2): 145\u2013153","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"142_CR25","unstructured":"Kohavi R, Sahami M (1996) Error-based and entropy-based discretization of continuous features. In: Proceedings of the second international conference on knowledge discovery and data mining. Menlo Park. AAAI Press, pp 114\u2013119"},{"key":"142_CR26","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1023\/A:1016304305535","volume":"6","author":"H Liu","year":"2002","unstructured":"Liu H, Hussain F, Tan CL, Dash M (2002) Discretization: an enabling technique. Data Mining Knowl Discovery 6: 393\u2013423","journal-title":"Data Mining Knowl Discovery"},{"key":"142_CR27","unstructured":"Liu H, Setiono R (1995) Chi2: feature selection and discretization of numeric attributes. In: Proceedings of 7th IEEE int\u2019l conference on tools with artificial intelligence"},{"issue":"9","key":"142_CR28","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/TKDE.2005.135","volume":"17","author":"X Liu","year":"2005","unstructured":"Liu X, Wang H (2005) A discretization algorithm based on a heterogeneity criterion. IEEE Trans Knowl Data Eng 17(9): 1166\u20131173","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"7","key":"142_CR29","first-page":"1","volume":"4","author":"S Mussard","year":"2003","unstructured":"Mussard S, Seyte F, Terraza M (2003) Decomposition of Gini and the generalized entropy inequality measures. Econ Bull 4(7): 1\u20136","journal-title":"Econ Bull"},{"key":"142_CR30","unstructured":"Pfahringer B (1995) Supervised and unsupervised discretization of continuous features. In: Proceedings of 12th international conference on machine learning, pp 456\u2013463"},{"key":"142_CR31","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/0005-1098(78)90005-5","volume":"14","author":"J Rissanen","year":"1978","unstructured":"Rissanen J (1978) Modeling by shortest data description. Automatica 14: 465\u2013471","journal-title":"Automatica"},{"issue":"7","key":"142_CR32","doi-asserted-by":"crossref","first-page":"2138","DOI":"10.1109\/TIT.2002.1013159","volume":"48","author":"DA Simovici","year":"2002","unstructured":"Simovici DA, Jaroszewicz S (2002) An axiomatization of partition entropy. IEEE Trans Inf Theory 48(7): 2138\u20132142","journal-title":"IEEE Trans Inf Theory"},{"issue":"4","key":"142_CR33","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1214\/aoms\/1177706095","volume":"30","author":"DL Wallace","year":"1959","unstructured":"Wallace DL (1959) Bounds on normal approximations to Student\u2019s and the Chi-square distributions. Ann Mathe Stat 30(4): 1121\u20131130","journal-title":"Ann Mathe Stat"},{"issue":"3","key":"142_CR34","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1214\/aoms\/1177705813","volume":"31","author":"DL Wallace","year":"1960","unstructured":"Wallace DL (1960) Correction to \u201cBounds on Normal Approximations to Student\u2019s and the Chi-Square Distributions\u201d. Ann Math Statist 31(3): 810","journal-title":"Ann Math Statist"},{"issue":"6","key":"142_CR35","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TPAMI.1987.4767986","volume":"9","author":"AKC Wong","year":"1987","unstructured":"Wong AKC, Chiu DKY (1987) Synthesizing statistical knowledge from incomplete mixed-mode data. IEEE Trans Pattern Anal Mach Intell 9(6): 796\u2013805","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"142_CR36","doi-asserted-by":"crossref","unstructured":"Yang Y, Webb GI (2003) Weighted proportional k-interval discretization for naive\u2013Bayes classifiers. In: Advances in knowledge discovery and data mining: 7th Pacific-Asia Conference, PAKDD, pp 501\u2013512","DOI":"10.1007\/3-540-36175-8_50"},{"key":"142_CR37","unstructured":"UCI Machine Learning Repository (2007) http:\/\/www.ics.uci.edu\/mlearn\/ML.Repository.html"},{"key":"142_CR38","unstructured":"Weka 3 (2007) Data mining software in Java. http:\/\/www.cs.waikato.ac.nz\/ml\/weka"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-008-0142-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-008-0142-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-008-0142-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T11:20:08Z","timestamp":1684408808000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-008-0142-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,5,17]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2009,4]]}},"alternative-id":["142"],"URL":"https:\/\/doi.org\/10.1007\/s10115-008-0142-6","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,5,17]]}}}