{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:18:34Z","timestamp":1771024714735,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2009,2,28]],"date-time":"2009-02-28T00:00:00Z","timestamp":1235779200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1007\/s00778-009-0134-5","type":"journal-article","created":{"date-parts":[[2009,2,27]],"date-time":"2009-02-27T15:27:26Z","timestamp":1235748446000},"page":"1241-1260","source":"Crossref","is-referenced-by-count":23,"title":["HE-Tree: a framework for detecting changes in clustering structure for categorical data streams"],"prefix":"10.1007","volume":"18","author":[{"given":"Keke","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,2,28]]},"reference":[{"key":"134_CR1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/TKDE.2005.78","volume":"17","author":"C.C. Aggarwal","year":"2005","unstructured":"Aggarwal, C.C.: On change diagnosis in evolving data streams. IEEE Trans. Knowl. Data Eng. 17, 5 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"134_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Han, J., Wang, J., Yu, P.: A framework for projected clustering of high dimensional data streams. In: Proceedings of Very Large Databases Conference (VLDB) (2004)","DOI":"10.1016\/B978-012088469-8.50075-9"},{"key":"134_CR3","doi-asserted-by":"crossref","unstructured":"Andritsos, P., Tsaparas, P., Miller, R.J., Sevcik, K.C.: Limbo: scalable clustering of categorical data. In: Proceedings of Intternational Conference on Extending Database Technology (EDBT) (2004)","DOI":"10.1007\/978-3-540-24741-8_9"},{"key":"134_CR4","doi-asserted-by":"crossref","unstructured":"Babcock, B., Babu, S., Datar, M., Motwani, R., Widom, J.: Models and issues in data stream systems. In: Proceedings of ACM Conference on Principles of Database Systems (PODS) (2002)","DOI":"10.1145\/543613.543615"},{"key":"134_CR5","doi-asserted-by":"crossref","unstructured":"Barbara, D., Li, Y., Couto, J.: Coolcat: an entropy-based algorithm for categorical clustering. In: Proceedings of ACM Conference on Information and Knowledge Management (CIKM) (2002)","DOI":"10.1145\/584792.584888"},{"key":"134_CR6","unstructured":"Ben-David, S., Gehrke, J., Kifer, D.: Detecting change in data stream. In: Proceedings of Very Large Databases Conference (VLDB) (2004)"},{"key":"134_CR7","doi-asserted-by":"crossref","unstructured":"Bock, H.: Probabilistic aspects in cluster analysis. In: Conceptual and Numerical Analysis of Data. Springer, Berlin (1989)","DOI":"10.1007\/978-3-642-75040-3_2"},{"key":"134_CR8","unstructured":"Brand, M.: An entropic estimator for structure discovery. In: Proceedings Of Neural Information Processing Systems (NIPS), pp. 723\u2013729 (1998)"},{"key":"134_CR9","doi-asserted-by":"crossref","unstructured":"Celeux, G., Govaert, G.: Clustering criteria for discrete data and latent class models. J. Classif. (1991)","DOI":"10.1007\/BF02616237"},{"key":"134_CR10","unstructured":"Chakrabarti, A., Cormode, G., McGregor, A.: A near-optimal algorithm for computing the entropy of a stream. In: Annual ACM-SIAM Symposium on Discrete Algorithms (2007)"},{"key":"134_CR11","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Papadimitriou, S., Modha, D.S., Faloutsos, C.: Fully automatic cross-associations. In: Proceedings of ACM SIGKDD Conference (2004)","DOI":"10.21236\/ADA459025"},{"key":"134_CR12","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1057\/palgrave.ivs.9500076","volume":"4","author":"K. Chen","year":"2004","unstructured":"Chen K., Liu L.: VISTA: Validating and refining clusters via visualization. Inf. Vis. 3 4, 257\u2013270 (2004)","journal-title":"Inf. Vis. 3"},{"key":"134_CR13","unstructured":"Chen, K., Liu, L.: The \u201cbest k\u201d for entropy-based categorical clustering. In: Proceedings of International Conference on Scientific and Statistical Database Management (SSDBM), pp.253\u2013262 (2005)"},{"key":"134_CR14","doi-asserted-by":"crossref","unstructured":"Chen, K., Liu, L.: Detecting the change of clustering structure in categorical data streams. In: SIAM Data Mining Conference (2006)","DOI":"10.1137\/1.9781611972764.49"},{"key":"134_CR15","doi-asserted-by":"crossref","unstructured":"Chen, K., Liu, L.: iVIBRATE: Interactive visualization based framework for clustering large datasets. ACM Trans. Inf. Syst. 24, 2 (2006)","DOI":"10.1145\/1148020.1148024"},{"key":"134_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dong, G., Han, J., Wah, B.W., Wang, J.: Multidimensional regression analysis of time-series data streams. In : Proceedings of Very Large Databases Conference (VLDB) (2002)","DOI":"10.1016\/B978-155860869-6\/50036-6"},{"key":"134_CR17","doi-asserted-by":"crossref","unstructured":"Cheng, C.H., Fu, A. W.-C., Zhang, Y.: Entropy-based subspace clustering for mining numerical data. In: Proceedings of ACM SIGKDD Conference (1999)","DOI":"10.1145\/312129.312199"},{"key":"134_CR18","doi-asserted-by":"crossref","DOI":"10.1002\/0471200611","volume-title":"Elements of Information Theory","author":"T. Cover","year":"1991","unstructured":"Cover T., Thomas J.: Elements of Information Theory. Wiley, NY (1991)"},{"key":"134_CR19","doi-asserted-by":"crossref","unstructured":"Das, A., Gehrke, J., Riedewald, M.: Approximate join processing over data streams. In: Proceedings of ACM SIGMOD Conference (2003)","DOI":"10.1145\/872757.872765"},{"key":"134_CR20","doi-asserted-by":"crossref","unstructured":"Dhillon, I.S., Mellela, S., Modha, D.S.: Information-theoretic co-clustering. In: Proceedings of ACM SIGKDD Conference (2003)","DOI":"10.1145\/956750.956764"},{"key":"134_CR21","doi-asserted-by":"crossref","unstructured":"Domingos, P., Hulten, G.: Mining high-speed data streams. In: Proceedings of ACM SIGKDD Conference, pp. 71\u201380 (2000)","DOI":"10.1145\/347090.347107"},{"key":"134_CR22","doi-asserted-by":"crossref","unstructured":"Ganti, V., Gehrke, J., Ramakrishnan, R.: CACTUS-clustering categorical data using summaries. In: Proceedings of ACM SIGKDD Conference (1999)","DOI":"10.1145\/312129.312201"},{"key":"134_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/69.908980","volume":"13","author":"V. Ganti","year":"2001","unstructured":"Ganti V., Gehrke J., Ramakrishnan R.: Demon: Mining and monitoring evolving data. IEEE Trans. Knowl. Data Eng. 13, 1 (2001)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"134_CR24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1006\/jcss.2001.1808","volume":"64","author":"V. Ganti","year":"2002","unstructured":"Ganti V., Gehrke J., Ramakrishnan R., Loh W.: A framework for measuring differences in data characteristics. J. Comput. Syst. Sci. 64, 3 (2002)","journal-title":"J. Comput. Syst. Sci."},{"key":"134_CR25","doi-asserted-by":"crossref","unstructured":"Gehrke, J., Ganti, V., Ramakrishnan, R., Loh, W.-Y.: BOAT\u2014 optimistic decision tree construction. In: Proceedings of ACM SIGMOD Conference, pp. 169\u2013180 (1999)","DOI":"10.1145\/304181.304197"},{"key":"134_CR26","doi-asserted-by":"crossref","unstructured":"Gibson, D., Kleinberg, J., Raghavan, P.: Clustering categorical data: An approach based on dynamical systems. In: Proceedings of Very Large Databases Conference (VLDB), pp. 222\u2013236 (2000)","DOI":"10.1007\/s007780050005"},{"key":"134_CR27","doi-asserted-by":"crossref","unstructured":"Guha, S., Meyerson, A., Mishra, N., Motwani, R., O\u2019Callaghan, L.: Clustering data streams: Theory and practice. IEEE Trans. Knowl. Data Eng. 15 (2003)","DOI":"10.1109\/TKDE.2003.1198387"},{"key":"134_CR28","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","volume":"5","author":"S. Guha","year":"2000","unstructured":"Guha S., Rastogi R., Shim K.: ROCK: A robust clustering algorithm for categorical attributes. Inf. Syst. 25 5, 345\u2013366 (2000)","journal-title":"Inf. Syst. 25"},{"key":"134_CR29","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/565117.565124","volume":"2","author":"M. Halkidi","year":"2002","unstructured":"Halkidi M., Batistakis Y., Vazirgiannis M.: Cluster validity methods: Part I and II. SIGMOD Record 31 2, 40\u201345 (2002)","journal-title":"SIGMOD Record 31"},{"key":"134_CR30","unstructured":"Huang, Z.: A fast clustering algorithm to cluster very large categorical data sets in data mining. In: Workshop on Research Issues on Data Mining and Knowledge Discovery (1997)"},{"key":"134_CR31","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"A. Jain","year":"1999","unstructured":"Jain A., Murty M., , : Data clustering: A review. ACM Comput. Surv. 31, 264\u2013323 (1999)","journal-title":"ACM Comput. Surv."},{"key":"134_CR32","volume-title":"Algorithms for Clustering Data","author":"A.K. Jain","year":"1988","unstructured":"Jain A.K., Dubes R.C.: Algorithms for Clustering Data. Prentice hall, New York (1988)"},{"key":"134_CR33","doi-asserted-by":"crossref","unstructured":"Keogh, E., Lin, J., Truppel, W.: Clustering of time series subsequences is meaningless: Implications for previous and future research. In: Proceedings of International Conference on Data Mining (ICDM) (2003)","DOI":"10.1109\/ICDM.2003.1250910"},{"key":"134_CR34","doi-asserted-by":"crossref","unstructured":"Li, T., Ma, S., Ogihara, M.: Entropy-based criterion in categorical clustering. In: Proceedings of International Conference on Machine Learning (ICML) (2004)","DOI":"10.1145\/1015330.1015404"},{"key":"134_CR35","first-page":"397","volume":"2","author":"C. Meek","year":"2002","unstructured":"Meek C., Thiesson B., Heckerman D.: The learning-curve sampling method applied to model-based clustering. J. Mach. Learn. Res. 2, 397\u2013418 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"134_CR36","doi-asserted-by":"crossref","unstructured":"Singh, S., Mayfield, C., Prabhakar, S., Shah, R., Hambrusch, S.: Indexing uncertain categorical data. In: Proceedings of IEEE International Conference on Data Engineering (ICDE) (2007)","DOI":"10.1109\/ICDE.2007.367907"},{"key":"134_CR37","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedingd of the 37-th Annual Allerton Conference on Communication, Control and Computing (1999)"},{"key":"134_CR38","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1023\/A:1022699900025","volume":"4","author":"P.E. Utgoff","year":"1989","unstructured":"Utgoff P.E.: Incremental induction of decision trees. Mach. Learn. 4, 161\u2013186 (1989)","journal-title":"Mach. Learn."},{"key":"134_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Fan, W., Yu, P.S., Han, J.: Mining concept drifting data streams using ensemble classifiers. In: Proceedings of ACM SIGKDD Conference (2003)","DOI":"10.1145\/956750.956778"},{"key":"134_CR40","unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Fisher, D.H. (ed.) Proceedings of ICML-97, 14th International Conference on Machine Learning (Nashville, US, 1997), pp. 412\u2013420. Morgan Kaufmann, San Francisco (1997)"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-009-0134-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-009-0134-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-009-0134-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T15:05:05Z","timestamp":1559142305000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-009-0134-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,2,28]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2009,12]]}},"alternative-id":["134"],"URL":"https:\/\/doi.org\/10.1007\/s00778-009-0134-5","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,2,28]]}}}