{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T21:05:06Z","timestamp":1761599106019,"version":"3.38.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2011,11,20]],"date-time":"2011-11-20T00:00:00Z","timestamp":1321747200000},"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":[[2012,10]]},"DOI":"10.1007\/s10115-011-0447-8","type":"journal-article","created":{"date-parts":[[2011,11,19]],"date-time":"2011-11-19T06:55:57Z","timestamp":1321685757000},"page":"213-244","source":"Crossref","is-referenced-by-count":89,"title":["Facing the reality of data stream classification: coping with scarcity of labeled data"],"prefix":"10.1007","volume":"33","author":[{"given":"Mohammad M.","family":"Masud","sequence":"first","affiliation":[]},{"given":"Clay","family":"Woolam","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Latifur","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Jiawei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Kevin W.","family":"Hamlen","sequence":"additional","affiliation":[]},{"given":"Nikunj C.","family":"Oza","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,11,20]]},"reference":[{"key":"447_CR1","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10115-008-0174-y","volume":"20","author":"CC Aggarwal","year":"2009","unstructured":"Aggarwal CC (2009) On classification and segmentation of massive audio data streams. Knowl Inf Syst 20: 137\u2013156","journal-title":"Knowl Inf Syst"},{"issue":"5","key":"447_CR2","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1109\/TKDE.2006.69","volume":"18","author":"CC Aggarwal","year":"2006","unstructured":"Aggarwal CC, Han J, Wang J, Yu PS (2006) A framework for on-demand classification of evolving data streams. IEEE Trans Knowl Data Eng 18(5): 577\u2013589","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"447_CR3","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10115-009-0241-z","volume":"24","author":"CC Aggarwal","year":"2010","unstructured":"Aggarwal CC, Yu PS (2010) On clustering massive text and categorical data streams. Knowl Inf Syst 24: 171\u2013196","journal-title":"Knowl Inf Syst"},{"key":"447_CR4","unstructured":"Basu S, Banerjee A, Mooney RJ (2002) Semi-supervised clustering by seeding. In: Procedings of nineteenth international conference on machine learning (ICML), Sydney, Australia, pp 19\u201326"},{"key":"447_CR5","doi-asserted-by":"crossref","unstructured":"Basu S, Banerjee A, Mooney RJ (2004) Active semi-supervision for pairwise constrained clustering. In: Proceedings of SIAM international conference on data mining (SDM), Lake Buena Vista, FL, pp 333\u2013344","DOI":"10.1137\/1.9781611972740.31"},{"key":"447_CR6","doi-asserted-by":"crossref","unstructured":"Basu S, Bilenko M, Banerjee A, Mooney RJ (2006) Probabilistic semi-supervised clustering with constraints\u2019. In: Chapelle O, Schoelkopf B, Zien A (eds) Semi-supervised learning. pp 73\u2013102","DOI":"10.7551\/mitpress\/6173.003.0008"},{"key":"447_CR7","doi-asserted-by":"crossref","first-page":"193","DOI":"10.7551\/mitpress\/6173.003.0016","volume-title":"Semi-Supervised Learning","author":"Y Bengio","year":"2006","unstructured":"Bengio Y, Delalleau O, Le Roux N (2006) Label propagation and quadratic criterion. In: Chapelle O, Sch\u00f6lkopf B, Zien A (eds) Semi-Supervised Learning. MIT Press, Cambridge, pp 193\u2013216"},{"issue":"3","key":"447_CR8","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1111\/j.2517-6161.1986.tb01412.x","volume":"48","author":"J Besag","year":"1986","unstructured":"Besag J (1986) On the statistical analysis of dirty pictures. J R Stat Soc Ser B (Methodological) 48(3): 259\u2013302","journal-title":"J R Stat Soc Ser B (Methodological)"},{"key":"447_CR9","doi-asserted-by":"crossref","unstructured":"Bilenko M, Basu S, Mooney RJ (2004) Integrating constraints and metric learning in semi-supervised clustering. In: Proceedings of 21st international conference on machine learning (ICML), Banff, Canada, pp 81\u201388","DOI":"10.1145\/1015330.1015360"},{"key":"447_CR10","doi-asserted-by":"crossref","unstructured":"Chen S, Wang H, Zhou S, Yu P (2008) Stop chasing trends: discovering high order models in evolving data. In: Proceedings of ICDE, pp 923\u2013932","DOI":"10.1109\/ICDE.2008.4497501"},{"key":"447_CR11","unstructured":"Cohn D, Caruana R, McCallum A (2003) Semi-supervised clustering with user feedback. Technical report TR2003-1892, Cornell University"},{"key":"447_CR12","unstructured":"Demiriz A, Bennett KP, Embrechts MJ (1999) Semi-supervised clustering using genetic algorithms. In: Artificial neural networks in engineering (ANNIE-99). ASME Press, pp 809\u2013814"},{"key":"447_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the em algorithm. J R Stat Soc B 39: 1\u201338","journal-title":"J R Stat Soc B"},{"key":"447_CR14","doi-asserted-by":"crossref","unstructured":"Domingos P, Hulten G (2000) Mining high-speed data streams. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining KDD. ACM Press, Boston MA, USA, pp 71\u201380","DOI":"10.1145\/347090.347107"},{"key":"447_CR15","doi-asserted-by":"crossref","unstructured":"Fan W (2004) Systematic data selection to mine concept-drifting data streams. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining (KDD), Seattle, WA, USA, pp 128\u2013137","DOI":"10.1145\/1014052.1014069"},{"key":"447_CR16","doi-asserted-by":"crossref","unstructured":"Fan W, an Huang Y, Wang H, Yu PS (2004) Active mining of data streams. In: Proceedings of SDM \u201904\u2019. pp 457\u2013461","DOI":"10.1137\/1.9781611972740.46"},{"key":"447_CR17","doi-asserted-by":"crossref","unstructured":"Gao J, Fan W, Han J (2007) On appropriate assumptions to mine data streams. In: Proceedings of seventh IEEE international conference on data mining (ICDM), Omaha, NE, USA, pp 143\u2013152","DOI":"10.1109\/ICDM.2007.96"},{"key":"447_CR18","doi-asserted-by":"crossref","unstructured":"Grossi V, Turini F (2011) Stream mining: a novel architecture for ensemble-based classification in preprints. knowl Inf Syst","DOI":"10.1007\/s10115-011-0378-4"},{"key":"447_CR19","doi-asserted-by":"crossref","unstructured":"Halkidi M, Gunopulos D, Kumar N, Vazirgiannis M, Domeniconi C (2005) A framework for semi-supervised learning based on subjective and objective clustering criteria. In: Proceedings of fifth IEEE international conference on data mining (ICDM), Houston, Texas, USA, pp 637\u2013640","DOI":"10.1109\/ICDM.2005.4"},{"issue":"2","key":"447_CR20","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1287\/moor.10.2.180","volume":"10","author":"D Hochbaum","year":"1985","unstructured":"Hochbaum D, Shmoys D (1985) A best possible heuristic for the k-center problem. Math Oper Res 10(2): 180\u2013184","journal-title":"Math Oper Res"},{"key":"447_CR21","doi-asserted-by":"crossref","unstructured":"Hulten G, Spencer L, Domingos P (2001) Mining time-changing data streams. In: Proceedings of seventh ACM SIGKDD international conference on Knowledge discovery and data mining (KDD), San Francisco, CA, USA, pp 97\u2013106","DOI":"10.1145\/502512.502529"},{"key":"447_CR22","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/s10115-009-0206-2","volume":"22","author":"I Katakis","year":"2010","unstructured":"Katakis I, Tsoumakas G, Vlahavas I (2010) Tracking recurring contexts using ensemble classifiers: an application to email filtering. Knowl Inf Syst 22: 371\u2013391","journal-title":"Knowl Inf Syst"},{"key":"447_CR23","unstructured":"KDD Cup 1999 Intrusion Detection Dataset (n.d.) http:\/\/kdd.ics.uci.edu\/databases\/kddcup99\/kddcup99.html ."},{"key":"447_CR24","unstructured":"Klein D, Kamvar SD, Manning CD (2002) From instance-level constraints to space-level constraints: making the most of prior knowledge in data clustering. In: Proceedigs of 19th international conference on machine learning (ICML). Morgan Kaufmann Publishers Inc., Sydney, pp 307\u2013314"},{"key":"447_CR25","doi-asserted-by":"crossref","unstructured":"Kolter J, Maloof M (2005) Using additive expert ensembles to cope with concept drift. In: Proceedings of international conference on machine learning (ICML), Bonn, Germany, pp 449\u2013456","DOI":"10.1145\/1102351.1102408"},{"key":"447_CR26","first-page":"2755","volume":"8","author":"JZ Kolter","year":"2007","unstructured":"Kolter JZ, Maloof MA (2007) Dynamic weighted majority: an ensemble method for drifting concepts. J Mach Learn Res 8: 2755\u20132790","journal-title":"J Mach Learn Res"},{"key":"447_CR27","doi-asserted-by":"crossref","unstructured":"Kranen P, Assent I, Baldauf C, Seidl T (2010) The clustree: indexing micro-clusters for anytime stream mining. Knowl Inf Syst (In preprints)","DOI":"10.1007\/s10115-010-0342-8"},{"key":"447_CR28","doi-asserted-by":"crossref","unstructured":"Kuncheva LI, S\u00e1nchez JS (2008) Nearest neighbour classifiers for streaming data with delayed labelling. In: \u2018ICDM\u2019. pp 869\u2013874","DOI":"10.1109\/ICDM.2008.33"},{"key":"447_CR29","doi-asserted-by":"crossref","unstructured":"Li P, Wu X, Hu X (2010) Learning from concept drifting data streams with unlabeled data. In: \u2018AAAI\u2019. pp 1945\u20131946","DOI":"10.1609\/aaai.v24i1.7770"},{"key":"447_CR30","doi-asserted-by":"crossref","unstructured":"Li X, Yu PS, Liu B, Ng SK (2009) Positive unlabeled learning for data stream classification. In: \u2018SDM\u2019. pp 257\u2013268","DOI":"10.1137\/1.9781611972795.23"},{"key":"447_CR31","doi-asserted-by":"crossref","unstructured":"Masud MM, Gao J, Khan L, Han J, Thuraisingham B (2008) A practical approach to classify evolving data streams: training with limited amount of labeled data. In: Proceedings if international conference on data mining (ICDM), Pisa, Italy, pp 929\u2013934","DOI":"10.1109\/ICDM.2008.152"},{"key":"447_CR32","doi-asserted-by":"crossref","unstructured":"Masud MM, Gao J, Khan L, Han J, Thuraisingham BM (2009) Integrating novel class detection with classification for concept-drifting data streams. In: ECML PKDD \u201909, Vol. II. pp. 79\u201394","DOI":"10.1007\/978-3-642-04174-7_6"},{"key":"447_CR33","unstructured":"NASA Aviation Safety Reporting System (n.d.) http:\/\/akama.arc.nasa.gov\/ASRSDBOnline\/QueryWizard_Begin.aspx"},{"key":"447_CR34","unstructured":"Scholz M, Klinkenberg R (2005) An ensemble classifier for drifting concepts. In: Proceedings of second international workshop on knowledge discovery in data streams (IWKDDS), Porto, Portugal, pp 53\u201364"},{"issue":"304","key":"447_CR35","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1080\/095400996116839","volume":"8","author":"K Tumer","year":"1996","unstructured":"Tumer K, Ghosh J (1996) Error correlation and error reduction in ensemble classifiers. Connect Sci 8(304): 385\u2013403","journal-title":"Connect Sci"},{"key":"447_CR36","unstructured":"van Huyssteen GB, Puttkammer MJ, Pilon S, Groenewald HJ (2007) Using machine learning to annotate data for nlp tasks semi-automatically. In: Proceedings of computer-aided language processing (CALP\u201907)"},{"key":"447_CR37","unstructured":"Wagsta K, Cardie C, Schroedl S (2001) Constrained k-means clustering with background knowledge. In: Proceedings of 18th international conference on machine learning (ICML), Morgan Kaufmann, Williamstown, MA, USA, pp 577\u2013584"},{"key":"447_CR38","doi-asserted-by":"crossref","unstructured":"Wang H, Fan W, Yu PS, Han J (2003) Mining concept-drifting data streams using ensemble classifiers. In: Proceedings of ninth ACM SIGKDD international conference on knowledge discovery and data mining. ACM, Washington, DC, pp c226\u2013c235","DOI":"10.1145\/956750.956778"},{"key":"447_CR39","doi-asserted-by":"crossref","unstructured":"Woolam C, Masud MM, Khan L (2009) Lacking labels in the stream: classifying evolving stream data with few labels. In: Proceedings of international symposium on methodologies for intelligent systems (ISMIS), Prague, Czech Republic, pp 552\u2013562","DOI":"10.1007\/978-3-642-04125-9_58"},{"key":"447_CR40","unstructured":"Xing EP, Ng AY, Jordan MI, Russell S (2003) Distance metric learning, with application to clustering with side-information. In: Advances in neural information processing systems vol 15. MIT Press, pp 505\u2013512"},{"key":"447_CR41","doi-asserted-by":"crossref","unstructured":"Yang Y, Wu X, Zhu X (2005) Combining proactive and reactive predictions for data streams. In: Proceedigs of KDD. pp 710\u2013715","DOI":"10.1145\/1081870.1081961"},{"key":"447_CR42","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10115-007-0070-x","volume":"15","author":"A Zhou","year":"2008","unstructured":"Zhou A, Cao F, Qian W, Jin C (2008) Tracking clusters in evolving data streams over sliding windows. Knowl Inf Syst 15: 181\u2013214","journal-title":"Knowl Inf Syst"},{"key":"447_CR43","unstructured":"Zhou D, Bousquet O, Lal TN, Weston J, Olkopf BS (2004) Learning with local and global consistency. In: Advances in neural information processing systems, vol 16. MIT Press, pp 321\u2013328"},{"key":"447_CR44","unstructured":"Zhu X, Ding W, Yu P, Zhang C (2010) One-class learning and concept summarization for data streams. Knowl Inf Syst 1\u201331"},{"key":"447_CR45","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/s10115-005-0212-y","volume":"9","author":"X Zhu","year":"2006","unstructured":"Zhu X, Wu X, Yang Y (2006) Effective classification of noisy data streams with attribute-oriented dynamic classifier selection. Knowl Inf Syst 9: 339\u2013363","journal-title":"Knowl Inf Syst"},{"key":"447_CR46","doi-asserted-by":"crossref","unstructured":"Zhu X, Zhang P, Lin X, Shi Y (2007) Active learning from data streams. In: Proceedings of ICDM \u201907\u2019, pp 757\u2013762","DOI":"10.1109\/ICDM.2007.101"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0447-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-011-0447-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0447-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T06:58:53Z","timestamp":1741935533000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-011-0447-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,11,20]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,10]]}},"alternative-id":["447"],"URL":"https:\/\/doi.org\/10.1007\/s10115-011-0447-8","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2011,11,20]]}}}