{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T16:10:02Z","timestamp":1744906202439},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,2,9]],"date-time":"2013-02-09T00:00:00Z","timestamp":1360368000000},"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":[[2013,6]]},"DOI":"10.1007\/s10115-013-0612-3","type":"journal-article","created":{"date-parts":[[2013,2,9]],"date-time":"2013-02-09T02:05:32Z","timestamp":1360375532000},"page":"493-524","source":"Crossref","is-referenced-by-count":8,"title":["DEMass: a new density estimator for big data"],"prefix":"10.1007","volume":"35","author":[{"given":"Kai Ming","family":"Ting","sequence":"first","affiliation":[]},{"given":"Takashi","family":"Washio","sequence":"additional","affiliation":[]},{"given":"Jonathan R.","family":"Wells","sequence":"additional","affiliation":[]},{"given":"Fei Tony","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Sunil","family":"Aryal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,2,9]]},"reference":[{"key":"612_CR1","doi-asserted-by":"crossref","unstructured":"Achtert E, Kriegel H-P, Zimek A (2008) ELKI: a software system for evaluation of subspace clustering algorithms. In: Proceedings of the 20th international conference on scientific and statistical database management, pp 580\u2013585","DOI":"10.1007\/978-3-540-69497-7_41"},{"issue":"1","key":"612_CR2","doi-asserted-by":"crossref","first-page":"4:1","DOI":"10.1145\/1497577.1497581","volume":"3","author":"F Angiulli","year":"2009","unstructured":"Angiulli F, Fassetti F (2009) DOLPHIN: an efficient algorithm for mining distance-based outliers in very large datasets. ACM Trans Knowl Discov Data 3(1):4:1\u20134:57","journal-title":"ACM Trans Knowl Discov Data"},{"key":"612_CR3","unstructured":"Bay SD, Schwabacher M (2003) Mining distance-based outliers in near linear time with randomization and a simple pruning rule. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp. 29\u201338"},{"key":"612_CR4","doi-asserted-by":"crossref","unstructured":"Beyer KS, Goldstein J, Ramakrishnan R, Shaft U (1999) When is \u201cnearest neighbor\u201d meaningful? In: Proceedings of the 7th international conference on database theory, pp 217\u2013235","DOI":"10.1007\/3-540-49257-7_15"},{"key":"612_CR5","doi-asserted-by":"crossref","unstructured":"Beygelzimer A, Kakade S, Langford J (2006) Cover trees for nearest neighbor. In: Proceedings of the 23rd international conference on machine learning, pp 97\u2013104","DOI":"10.1145\/1143844.1143857"},{"key":"612_CR6","doi-asserted-by":"crossref","unstructured":"Breunig MM, Kriegel H-P, Ng RT, Sander J (2000) LOF: identifying density-based local outliers. In: Proceedings of ACM SIGMOD international conference on management of data, pp 93\u2013104","DOI":"10.1145\/335191.335388"},{"key":"612_CR7","doi-asserted-by":"crossref","unstructured":"Catlett J (1991) On changing continuous attributes into ordered discrete attributes. In: Proceedings of the European working session on learning, pp 164\u2013178","DOI":"10.1007\/BFb0017012"},{"key":"612_CR8","unstructured":"Ciaccia P, Patella M, Zezula P (1997) M-tree: an efficient access method for similarity search in metric spaces. In: Proceedings of the 23rd international conference on very large data, bases, pp 426\u2013435"},{"key":"612_CR9","unstructured":"Deegalla S, Bostrom H (2006) Reducing high-dimensional data by principal component analysis vs. random projection for nearest neighbor classification. In: Proceedings of the 5th international conference on machine learning and applications, IEEE Computer Society, Washington, pp 245\u2013250"},{"issue":"1","key":"612_CR10","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 Roy Stat Soc Ser B 39(1):1\u201338","journal-title":"J Roy Stat Soc Ser B"},{"key":"612_CR11","doi-asserted-by":"crossref","unstructured":"Dougherty J, Kohavi R, Sahami M (1995) Supervised and unsupervised discretization of continuous features. In: Proceedings of the 12th international conference on machine learning, Morgan Kaufmann, pp 194\u2013202","DOI":"10.1016\/B978-1-55860-377-6.50032-3"},{"key":"612_CR12","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 KDD, AAAI Press, pp 226\u2013231"},{"key":"612_CR13","unstructured":"Fayyad UM, Irani KB (1995) Multi-interval discretization of continuous valued attributes for classification learning. In: Proceedings of 14th international joint conference on artificial intelligence, pp 1034\u20131040"},{"key":"612_CR14","unstructured":"Frank A, Asuncion A (2010) UCI machine learning repository. University of California, Irvine, School of Information and Computer Sciences. URL: http:\/\/archive.ics.uci.edu\/ml"},{"key":"612_CR15","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Mach Learn 29:131\u2013163","journal-title":"Mach Learn"},{"key":"612_CR16","unstructured":"Hastie T, Tibshirani R, Friedman J (2001) Chapter 8.5 the EM algorithm. In The elements of statistical learning, pp 236\u2013243"},{"issue":"2","key":"612_CR17","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10115-010-0283-2","volume":"26","author":"S Hido","year":"2011","unstructured":"Hido S, Tsuboi Y, Kashima H, Sugiyama M, Kanamori T (2011) Statistical outlier detection using direct density ratio estimation. Knowl Inf Syst 26(2):309\u2013336","journal-title":"Knowl Inf Syst"},{"key":"612_CR18","unstructured":"Hinneburg A, Aggarwal CC, Keim DA (2000) What is the nearest neighbor in high dimensional spaces? In: Proceedings of the 26th international conference on very large data bases, pp 506\u2013515"},{"key":"612_CR19","unstructured":"Hinneburg A, Keim DA (1998) An efficient approach to clustering in large multimedia databases with noise. In: Proceedings of KDD, AAAI Press, pp 58\u201365"},{"key":"612_CR20","unstructured":"Johnson WB, Lindenstrauss J (1984) Extensions of Lipschitz mapping into Hilbert space. In: Proceedings of conference in modern analysis and probability, contemporary mathematics, vol 26. American Mathematical Society, pp 189\u2013206"},{"key":"612_CR21","unstructured":"Langley P, Iba W, Thompson K (1992) An analysis of Bayesian classifiers. In: Proceedings of the tenth national conference on artificial intelligence, pp 399\u2013406"},{"key":"612_CR22","unstructured":"Langley P, John GH (1995) Estimating continuous distribution in Bayesian classifiers. In: Proceedings of eleventh conference on uncertainty in artificial intelligence"},{"key":"612_CR23","doi-asserted-by":"crossref","unstructured":"Lazarevic A, Kumar V (2005) Feature bagging for outlier detection. In: Proceedings of the eleventh ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp 157\u2013166","DOI":"10.1145\/1081870.1081891"},{"key":"612_CR24","doi-asserted-by":"crossref","unstructured":"Liu FT, Ting KM, Zhou Z-H (2010) On detecting clustered anomalies using sciforest. In: Proceedings of ECML PKDD, pp 274\u2013290","DOI":"10.1007\/978-3-642-15883-4_18"},{"issue":"1","key":"612_CR25","first-page":"3:1","volume":"6","author":"FT Liu","year":"2012","unstructured":"Liu FT, Ting KM, Zhou Z-H (2012) Isolation-based anomaly detection. ACM Trans Knowl Discov Data 6(1):3:1\u20133:39","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"1","key":"612_CR26","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.datak.2005.03.003","volume":"57","author":"A Nanopoulos","year":"2006","unstructured":"Nanopoulos A, Theodoridis Y, Manolopoulos Y (2006) Indexed-based density biased sampling for clustering applications. IEEE Trans Data Knowl Eng 57(1):37\u201363","journal-title":"IEEE Trans Data Knowl Eng"},{"issue":"435","key":"612_CR27","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1080\/01621459.1996.10476975","volume":"91","author":"DM Rocke","year":"1996","unstructured":"Rocke DM, Woodruff DL (1996) Identification of outliers in multivariate data. J Am Stat Assoc 91(435):1047\u20131061","journal-title":"J Am Stat Assoc"},{"issue":"7","key":"612_CR28","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1162\/089976601750264965","volume":"13","author":"B Sch\u00f6lkopf","year":"2001","unstructured":"Sch\u00f6lkopf B, Platt JC, Shawe-Taylor JC, Smola AJ, Williamson RC (2001) Estimating the support of a high-dimensional distribution. Neural Comput 13(7):1443\u20131471","journal-title":"Neural Comput"},{"key":"612_CR29","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-3324-9","volume-title":"Density estimation for statistics and data analysis","author":"BW Silverman","year":"1986","unstructured":"Silverman BW (1986) Density estimation for statistics and data analysis. Chapmal & Hall, London"},{"key":"612_CR30","volume-title":"Introduction to data mining","author":"P-N Tan","year":"2006","unstructured":"Tan P-N, Steinbach M, Kumar V (2006) Introduction to data mining. Addison-Wesley, Reading"},{"key":"612_CR31","unstructured":"Tan SC, Ting KM, Liu FT (2011) Fast anomaly detection for streaming data. In: Proceedings of IJCAI, pp 1151\u20131156"},{"issue":"1","key":"612_CR32","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/B:MACH.0000008084.60811.49","volume":"54","author":"DMJ Tax","year":"2004","unstructured":"Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54(1):45\u201366","journal-title":"Mach Learn"},{"key":"612_CR33","doi-asserted-by":"crossref","unstructured":"Ting KM, Washio T, Wells JR, Liu FT (2011) Density estimation based on mass. In: Proceedings of the 2011 IEEE 11th international conference on data mining, IEEE Computer Society, pp 715\u2013724","DOI":"10.1109\/ICDM.2011.47"},{"key":"612_CR34","unstructured":"Ting KM, Wells JR (2010) Multi-dimensional mass estimation and mass-based clustering. In: Proceedings of IEEE international conference on data mining, pp 511\u2013520"},{"key":"612_CR35","doi-asserted-by":"crossref","unstructured":"Ting KM, Zhou G-T, Liu FT, Tan SC (2012) Mass estimation. Mach Learn, pp 1\u201334. doi: 10.1007\/s10994-012-5303-x","DOI":"10.1007\/s10994-012-5303-x"},{"key":"612_CR36","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3264-1","volume-title":"The nature of statistical learning theory","author":"VN Vapnik","year":"2000","unstructured":"Vapnik VN (2000) The nature of statistical learning theory, 2nd edn. Springer, Berlin","edition":"2"},{"key":"612_CR37","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10115-011-0430-4","volume":"32","author":"TD Vries","year":"2012","unstructured":"Vries TD, Chawla S, Houle M (2012) Density-preserving projections for large-scale local anomaly detection. Knowl Inf Syst 32:25\u201352","journal-title":"Knowl Inf Syst"},{"key":"612_CR38","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10994-005-4258-6","volume":"58","author":"GI Webb","year":"2005","unstructured":"Webb GI, Boughton JR, Wang Z (2005) Aggregating one-dependence estimators. Mach Learn 58:5\u201324","journal-title":"Mach Learn"},{"key":"612_CR39","volume-title":"Data mining: Practical machine learning tools and techniques","author":"IH Witten","year":"2011","unstructured":"Witten IH, Frank E, Hall MA (2011) Data mining: Practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann, San Francisco","edition":"3"},{"key":"612_CR40","doi-asserted-by":"crossref","unstructured":"Yamanishi K, Takeuchi J-I, Williams G, Milne P (2000) On-line unsupervised outlier detection using finite mixtures with discounting learning algorithms. In: Proceedings of ACM SIGKDD international conference on knowledge discovery and data mining, pp 320\u2013324","DOI":"10.1145\/347090.347160"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-013-0612-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-013-0612-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-013-0612-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T19:16:40Z","timestamp":1714936600000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-013-0612-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,9]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,6]]}},"alternative-id":["612"],"URL":"https:\/\/doi.org\/10.1007\/s10115-013-0612-3","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,2,9]]}}}