{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:32:12Z","timestamp":1771612332703,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T00:00:00Z","timestamp":1647388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T00:00:00Z","timestamp":1647388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 105-2410-H-008-043-MY3"],"award-info":[{"award-number":["MOST 105-2410-H-008-043-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10115-022-01661-0","type":"journal-article","created":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T14:04:03Z","timestamp":1647439443000},"page":"1047-1075","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Empirical comparison of supervised learning techniques for missing value imputation"],"prefix":"10.1007","volume":"64","author":[{"given":"Chih-Fong","family":"Tsai","sequence":"first","affiliation":[]},{"given":"Ya-Han","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,16]]},"reference":[{"key":"1661_CR1","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1007\/978-3-642-17103-1_60","volume-title":"Classification, clustering and data mining applications","author":"E Acuna","year":"2004","unstructured":"Acuna E, Rodriguez C (2004) The treatment of missing values and its effect in the classifier accuracy. In: Banks D et al (eds) Classification, clustering and data mining applications. Springer-Verlag, Berlin, pp 639\u2013648"},{"key":"1661_CR2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1214\/09-SS054","volume":"4","author":"S Arlot","year":"2010","unstructured":"Arlot S (2010) A survey of cross-validation procedures for model selection. Stat Surv 4:40\u201379","journal-title":"Stat Surv"},{"key":"1661_CR3","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1080\/713827181","volume":"17","author":"G Batista","year":"2003","unstructured":"Batista G, Monard M (2003) An analysis of four missing data treatment methods for supervised learning. Appl Artif Intell 17:519\u2013533","journal-title":"Appl Artif Intell"},{"issue":"3","key":"1661_CR4","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1142\/S0218001403002460","volume":"17","author":"H Byun","year":"2003","unstructured":"Byun H, Lee S-W (2003) A survey on pattern recognition applications of support vector machines. Int J Pattern Recognit Artif Intell 17(3):459\u2013486","journal-title":"Int J Pattern Recognit Artif Intell"},{"key":"1661_CR5","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.neucom.2019.10.118","volume":"408","author":"J Cervantes","year":"2020","unstructured":"Cervantes J, Garcia-Lamont F, Rodriguez-Mazahua L, Lopez A (2020) A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408:189\u2013215","journal-title":"Neurocomputing"},{"issue":"3","key":"1661_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","journal-title":"ACM Trans Intell Syst Technol"},{"key":"1661_CR7","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1023\/A:1010395805406","volume":"35","author":"E De Leeuw","year":"2001","unstructured":"De Leeuw E (2001) Reducing missing data in surveys: an overview of methods. Qual Quant 35:147\u2013160","journal-title":"Qual Quant"},{"key":"1661_CR8","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"1661_CR9","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TSMC.1979.4310090","volume":"10","author":"JK Dixon","year":"1979","unstructured":"Dixon JK (1979) Pattern recognition with partly missing data. IEEE Trans Syst Man Cybern 10:617\u2013621","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1661_CR10","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.neucom.2013.07.050","volume":"131","author":"E Eirola","year":"2014","unstructured":"Eirola E, Lendasse A, Vandewalle V, Biernacki C (2014) Mixture of Gaussians for distance estimation with missing data. Neurocomputing 131:32\u201342","journal-title":"Neurocomputing"},{"key":"1661_CR11","volume-title":"Applied missing data analysis","author":"CK Enders","year":"2010","unstructured":"Enders CK (2010) Applied missing data analysis. Guilford Press, USA"},{"key":"1661_CR12","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.1016\/j.patcog.2008.05.019","volume":"41","author":"A Farhangfar","year":"2008","unstructured":"Farhangfar A, Kurgan L, Dy J (2008) Impact of imputation of missing values on classification error for discrete data. Pattern Recogn 41:3692\u20133705","journal-title":"Pattern Recogn"},{"key":"1661_CR13","doi-asserted-by":"crossref","unstructured":"Garcia AJT, Hruschka ER (2005) Na\u00efve Bayes as an imputation tool for classification problems. In: International conference on hybrid intelligent systems, pp 497\u2013499","DOI":"10.1109\/ICHIS.2005.78"},{"key":"1661_CR14","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","volume":"19","author":"PJ Garcia-Laencina","year":"2010","unstructured":"Garcia-Laencina PJ, Sancho-Gomez J-L, Figueiras-Vidal AR (2010) Pattern classification with missing data: a review. Neural Comput Appl 19:263\u2013282","journal-title":"Neural Comput Appl"},{"key":"1661_CR15","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/0-387-25465-X_3","volume-title":"Data mining and knowledge discovery handbook","author":"JW Grzymala-Busse","year":"2005","unstructured":"Grzymala-Busse JW, Grzymala-Busse WJ (2005) Handling missing attribute values. In: Maimon O, Rokach L (eds) Data mining and knowledge discovery handbook. Springer-Verlag, pp 37\u201357"},{"key":"1661_CR16","volume-title":"Neural networks: a comprehensive foundation","author":"S Haykin","year":"1999","unstructured":"Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, USA","edition":"2"},{"key":"1661_CR17","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s10844-006-0016-x","volume":"29","author":"ER Hruschka Jr","year":"2007","unstructured":"Hruschka ER Jr, Hruschka ER, Ebecken NFF (2007) Bayesian networks for imputation in classification problems. J Intell Inf Syst 29:231\u2013252","journal-title":"J Intell Inf Syst"},{"key":"1661_CR18","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.jss.2017.07.012","volume":"132","author":"J Huang","year":"2017","unstructured":"Huang J, Keung JW, Sarro F, Li YF, Yu YT, Chan WK, Sun H (2017) Cross-validation based K nearest neighbor imputation for software quality datasets: an empirical study. J Syst Softw 132:226\u2013252","journal-title":"J Syst Softw"},{"key":"1661_CR19","doi-asserted-by":"crossref","unstructured":"Jonsson P, Wohlin C (2004) An evaluation of k-nearest neighbor imputation using likert data. In: IEEE international symposium on software metrics, pp 108\u2013118","DOI":"10.1109\/METRIC.2004.1357895"},{"issue":"1","key":"1661_CR20","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/10485252.2017.1404598","volume":"30","author":"Y Jung","year":"2018","unstructured":"Jung Y (2018) Multiple predicting k-fold cross-validation for model selection. J Nonparametric Stat 30(1):197\u2013215","journal-title":"J Nonparametric Stat"},{"key":"1661_CR21","unstructured":"Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: International joint conference on artificial intelligence, pp 1137\u20131143"},{"issue":"3","key":"1661_CR22","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1008334909089","volume":"11","author":"K Lakshminarayan","year":"1999","unstructured":"Lakshminarayan K, Harp SA, Samad T (1999) Imputation of missing data in industrial databases. Appl Intell 11(3):259\u2013275","journal-title":"Appl Intell"},{"key":"1661_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09709-4","author":"W-C Lin","year":"2019","unstructured":"Lin W-C, Tsai C-F (2019) Missing value imputation: a review and analysis of the literature (2016\u20132017). Artif Intell Rev. https:\/\/doi.org\/10.1007\/s10462-019-09709-4","journal-title":"Artif Intell Rev"},{"key":"1661_CR24","doi-asserted-by":"crossref","DOI":"10.1002\/9781119013563","volume-title":"Statistical analysis with missing data","author":"RJA Little","year":"2002","unstructured":"Little RJA, Rubin DB (2002) Statistical analysis with missing data, 2nd edn. John Wiley and Sons, USA","edition":"2"},{"key":"1661_CR25","doi-asserted-by":"crossref","first-page":"169","DOI":"10.14257\/ijdta.2015.8.1.18","volume":"8","author":"J Nayak","year":"2015","unstructured":"Nayak J, Naik B, Behera H (2015) A comprehensive survey on support vector machine in data mining tasks: applications & challenges. Int J Database Theory Appl 8:169\u2013186","journal-title":"Int J Database Theory Appl"},{"key":"1661_CR26","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.neucom.2016.08.044","volume":"218","author":"KJ Nishanth","year":"2016","unstructured":"Nishanth KJ, Ravi V (2016) Probabilistic neural network based categorical data imputation. Neurocomputing 218:17\u201325","journal-title":"Neurocomputing"},{"key":"1661_CR27","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1007\/s10489-015-0666-x","volume":"43","author":"R Pan","year":"2015","unstructured":"Pan R, Yang T, Cao J, Lu K, Zhang Z (2015) Missing data imputation by K nearest neighbours based on grey relational structure and mutual information. Appl Intell 43:614\u2013632","journal-title":"Appl Intell"},{"issue":"3","key":"1661_CR28","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/s10115-017-1025-5","volume":"52","author":"SK Pati","year":"2017","unstructured":"Pati SK, Das AK (2017) Missing value estimation for microarray data through cluster analysis. Knowl Inf Syst 52(3):709\u2013750","journal-title":"Knowl Inf Syst"},{"key":"1661_CR29","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1016\/j.neunet.2005.06.025","volume":"18","author":"K Pelckmans","year":"2005","unstructured":"Pelckmans K, De Brabanter J, Suykens JAK, De Moor B (2005) Handling missing values in support vector machine classifiers. Neural Netw 18:684\u2013692","journal-title":"Neural Netw"},{"issue":"2","key":"1661_CR30","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1080\/08839514.2018.1448143","volume":"32","author":"J Poulos","year":"2018","unstructured":"Poulos J, Valle R (2018) Missing data imputation for supervised learning. Appl Artif Intell 32(2):186\u2013196","journal-title":"Appl Artif Intell"},{"issue":"1","key":"1661_CR31","first-page":"81","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81\u2013106","journal-title":"Mach Learn"},{"key":"1661_CR32","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1177\/0013164487471002","volume":"47","author":"M Raymond","year":"1987","unstructured":"Raymond M, Roberts D (1987) A comparison of methods for treating incomplete data in selection research. Educ Psychol Meas 47:13\u201326","journal-title":"Educ Psychol Meas"},{"issue":"3","key":"1661_CR33","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2009.187","volume":"32","author":"JD Rodriguez","year":"2010","unstructured":"Rodriguez JD, Perez A, Lozano JA (2010) Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell 32(3):569\u2013575","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"1661_CR34","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1002\/widm.1125","volume":"4","author":"S Salcedo-Sanz","year":"2014","unstructured":"Salcedo-Sanz S, Rojo-Alvarez JL, Martinez-Ramon M, Camps-Valls G (2014) Support vector machines in engineering: an overview. Wiley Interdiscip Rev Data Min Knowl Dis 4(3):234\u2013267","journal-title":"Wiley Interdiscip Rev Data Min Knowl Dis"},{"key":"1661_CR35","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.asoc.2014.09.052","volume":"29","author":"E-L Silva-Ramirez","year":"2015","unstructured":"Silva-Ramirez E-L, Pino-ejias R, Lopez-Coello M (2015) Single imputation with multilayer perceptron and multiple imputation combining multilayer perceptron and k-nearest neighbors for monotone patterns. Appl Soft Comput 29:65\u201374","journal-title":"Appl Soft Comput"},{"issue":"4","key":"1661_CR36","first-page":"29","volume":"1","author":"TR Sivapriya","year":"2012","unstructured":"Sivapriya TR, Kamal ARNB, Thavavel V (2012) Imputation and classification of missing data using least square support vector machines\u2014a new approach in dementia diagnosis. Int J Adv Res Artif Intell 1(4):29\u201334","journal-title":"Int J Adv Res Artif Intell"},{"issue":"10","key":"1661_CR37","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1109\/32.962560","volume":"27","author":"K Strike","year":"2001","unstructured":"Strike K, Emam KE, Madhavji N (2001) Software cost estimation with incomplete data. IEEE Trans Softw Eng 27(10):890\u2013908","journal-title":"IEEE Trans Softw Eng"},{"key":"1661_CR38","doi-asserted-by":"crossref","unstructured":"Su X, Khoshgoftaar TM, Zhu X, Greiner R (2008) Imputation-boosted collaborative filtering using machine learning classifiers. In: ACM symposium on applied computing, pp 949\u2013950","DOI":"10.1145\/1363686.1363903"},{"key":"1661_CR39","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.jss.2016.08.093","volume":"122","author":"C-F Tsai","year":"2016","unstructured":"Tsai C-F, Chang F-Y (2016) Combining instance selection for better missing value imputation. J Syst Softw 122:63\u201371","journal-title":"J Syst Softw"},{"key":"1661_CR40","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.ins.2015.03.018","volume":"311","author":"HC Valdiviezo","year":"2015","unstructured":"Valdiviezo HC, van Aelst S (2015) Tree-based prediction on incomplete data using imputation or surrogate decision. Inf Sci 311:163\u2013181","journal-title":"Inf Sci"},{"key":"1661_CR41","volume-title":"Statistical learning theory","author":"V Vapnik","year":"1998","unstructured":"Vapnik V (1998) Statistical learning theory. John Wiley, USA"},{"issue":"1","key":"1661_CR42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.346","volume":"6","author":"DR Wilson","year":"1997","unstructured":"Wilson DR, Martinez TR (1997) Improved heterogeneous distance functions. J Artif Intell Res 6(1):1\u201334","journal-title":"J Artif Intell Res"},{"key":"1661_CR43","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 JR, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Yu PS, Zhou Z-H, Steinbach M, Hand DJ, Steinberg D (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14:1\u201337","journal-title":"Knowl Inf Syst"},{"key":"1661_CR44","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.patcog.2017.04.005","volume":"69","author":"J Xia","year":"2017","unstructured":"Xia J, Zhang S, Cai G, Li L, Pan Q, Yan J, Ning G (2017) Adjusted weight voting algorithm for random forests in handling missing values. Pattern Recogn 69:52\u201360","journal-title":"Pattern Recogn"},{"key":"1661_CR45","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/s10044-014-0376-8","volume":"18","author":"L Zhang","year":"2015","unstructured":"Zhang L, Bing Z, Zhang L (2015) A hybrid clustering algorithm based on missing attribute interval estimation for incomplete data. Pattern Anal Appl 18:377\u2013384","journal-title":"Pattern Anal Appl"},{"issue":"1","key":"1661_CR46","first-page":"32","volume":"9","author":"S Zhang","year":"2008","unstructured":"Zhang S (2008) Parimputation: from imputation and null-imputation to partially imputation. IEEE Intell Inf Bull 9(1):32\u201338","journal-title":"IEEE Intell Inf Bull"},{"issue":"5","key":"1661_CR47","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1109\/LSP.2009.2016451","volume":"16","author":"Y Zhang","year":"2009","unstructured":"Zhang Y, Liu Y (2009) Data imputation using least squares support vector machines in urban arterial streets. IEEE Signal Process Lett 16(5):414\u2013417","journal-title":"IEEE Signal Process Lett"},{"issue":"2","key":"1661_CR48","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1198\/tast.2010.09109","volume":"64","author":"X Zhou","year":"2010","unstructured":"Zhou X, Reiter JP (2010) A note n Bayesian inference after multiple imputation. Am Stat 64(2):159\u2013163","journal-title":"Am Stat"},{"issue":"1","key":"1661_CR49","doi-asserted-by":"crossref","first-page":"69869","DOI":"10.1109\/ACCESS.2018.2877847","volume":"6","author":"Y Zhou","year":"2018","unstructured":"Zhou Y, De S, Wang W, Wang R, Moessner K (2018) Missing data estimation in mobile sensing environments. IEEE Access 6(1):69869\u201369882","journal-title":"IEEE Access"},{"issue":"1","key":"1661_CR50","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/TKDE.2010.99","volume":"23","author":"X Zhu","year":"2011","unstructured":"Zhu X, Zhang S, Jin Z, Zhang Z, Xu Z (2011) Missing value estimation for mixed-attribute data sets. IEEE Trans Knowl Data Eng 23(1):110\u2013121","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01661-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-022-01661-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01661-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T08:32:36Z","timestamp":1674981156000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-022-01661-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,16]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["1661"],"URL":"https:\/\/doi.org\/10.1007\/s10115-022-01661-0","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,16]]},"assertion":[{"value":"18 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}