{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:23:02Z","timestamp":1777695782271,"version":"3.51.4"},"reference-count":28,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2019,9,26]]},"DOI":"10.3233\/ida-184176","type":"journal-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T14:02:45Z","timestamp":1569938565000},"page":"759-778","source":"Crossref","is-referenced-by-count":2,"title":["Hephaistos: A fast and distributed outlier detection approach for big mixed attribute data"],"prefix":"10.1177","volume":"23","author":[{"given":"Haizhou","family":"Du","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai University of Electric Power, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai University of Electric Power, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Hangzhou Xiaoshan Power Supply Company, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"2","key":"10.3233\/IDA-184176_ref1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/376284.375668","article-title":"Outlier detection for high dimensional data","volume":"30","author":"Aggarwal","year":"2001","journal-title":"Acm Sigmod Record"},{"issue":"C","key":"10.3233\/IDA-184176_ref2","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.neucom.2015.05.135","article-title":"An efficient algorithm for distributed density-based outlier detection on big data","volume":"181","author":"Bai","year":"2016","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-184176_ref3","doi-asserted-by":"crossref","unstructured":"Bhaduri, Algorithms for speeding up distance-based outlier detection, in: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2011, pp. 859\u2013867.","DOI":"10.1145\/2020408.2020554"},{"key":"10.3233\/IDA-184176_ref4","doi-asserted-by":"crossref","unstructured":"Breunig, Lof: identifying density-based local outliers, Acm Sigmod Record 29(2) (2000), 93\u2013104.","DOI":"10.1145\/335191.335388"},{"key":"10.3233\/IDA-184176_ref5","unstructured":"K. Chen, The \u201cbest k\u201d for entropy-based categorical data clustering, in: International Conference on Scientific and Statistical Database Management, SSDBM 2005, 27\u201329 June 2005, University of California, Santa Barbara, Ca, Usa, Proceedings, 2005, pp. 253\u2013262."},{"key":"10.3233\/IDA-184176_ref7","doi-asserted-by":"crossref","unstructured":"H. Du, W. Fang, H. Huang and S. Zeng, Mmdbc: Density-based clustering algorithm for mixed attributes and multi-dimension data, in: IEEE International Conference on Big Data and Smart Computing, 2018, pp. 549\u2013552.","DOI":"10.1109\/BigComp.2018.00093"},{"issue":"2","key":"10.3233\/IDA-184176_ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10618-016-0471-0","article-title":"Comparison of local outlier detection techniques in spatial multivariate data","volume":"31","author":"Ernst","year":"2017","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.3233\/IDA-184176_ref10","doi-asserted-by":"crossref","unstructured":"Q. He, Parallel outlier detection using kd-tree based on mapreduce, in: IEEE Third International Conference on Cloud Computing Technology and Science, 2012, pp. 75\u201380.","DOI":"10.1109\/CloudCom.2011.20"},{"issue":"99","key":"10.3233\/IDA-184176_ref11","first-page":"1","article-title":"Subspace clustering of categorical and numerical data with an unknown number of clusters","volume":"PP","author":"Hong","year":"2017","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10.3233\/IDA-184176_ref13","doi-asserted-by":"crossref","unstructured":"R. Khade, Frequent set mining for streaming mixed and large data, in: IEEE International Conference on Machine Learning and Applications, 2015, pp. 1130\u20131135.","DOI":"10.1109\/ICMLA.2015.218"},{"issue":"2","key":"10.3233\/IDA-184176_ref14","first-page":"1605","article-title":"Clustering data of mixed categorical and numerical type with unsupervised feature learning","volume":"3","author":"Lam","year":"2017","journal-title":"IEEE Access"},{"key":"10.3233\/IDA-184176_ref15","doi-asserted-by":"crossref","unstructured":"S.T. Mai, Anydbc: An efficient anytime density-based clustering algorithm for very large complex datasets, in: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1025\u20131034.","DOI":"10.1145\/2939672.2939750"},{"key":"10.3233\/IDA-184176_ref16","doi-asserted-by":"crossref","unstructured":"H. Prasetyo, Comparison of distance and dissimilarity measures for clustering data with mix attribute types, in: International Conference on Information Technology, Computer and Electrical Engineering, 2015, pp. 276\u2013280.","DOI":"10.1109\/ICITACEE.2014.7065756"},{"key":"10.3233\/IDA-184176_ref17","doi-asserted-by":"crossref","unstructured":"Ramaswamy, Efficient algorithms for mining outliers from large datasets, in: ACM SIGMOD International Conference on Management of Data, 2000, pp. 427\u2013438.","DOI":"10.1145\/335191.335437"},{"issue":"4","key":"10.3233\/IDA-184176_ref18","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell System Technical Journal"},{"key":"10.3233\/IDA-184176_ref19","doi-asserted-by":"crossref","unstructured":"A. Sheth, Transforming big data into smart data: Deriving value via harnessing volume, variety, and velocity using semantic techniques and technologies, in: IEEE International Conference on Data Engineering, 2014, pp. 2\u20132.","DOI":"10.1109\/ICDE.2014.6816634"},{"issue":"6","key":"10.3233\/IDA-184176_ref20","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1007\/s11771-017-3535-4","article-title":"Outlier detection based on multi-dimensional clustering and local density","volume":"24","author":"Shou","year":"2017","journal-title":"Journal of Central South University"},{"key":"10.3233\/IDA-184176_ref21","doi-asserted-by":"crossref","unstructured":"G. Sreenivasulu, A proficient approach for clustering of large categorical data cataloguing, in: International Conference on Electrical, Electronics, and Optimization Techniques, 2016, pp. 2870\u20132875.","DOI":"10.1109\/ICEEOT.2016.7755222"},{"key":"10.3233\/IDA-184176_ref22","unstructured":"P. Tan, Hierarchical speaker verification: Kernel fisher discriminant plus mixed-pca classifier and fcm clustering, in: International Conference on Fuzzy Systems and Knowledge Discovery, 2016, pp. 1561\u20131565."},{"issue":"9-10","key":"10.3233\/IDA-184176_ref23","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.1007\/s10994-016-5624-2","article-title":"Vine copulas for mixed data: multi-view clustering for mixed data beyond meta-gaussian dependencies","volume":"106","author":"Tekumalla","year":"2017","journal-title":"Machine Learning"},{"issue":"6","key":"10.3233\/IDA-184176_ref24","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1007\/s10618-016-0453-2","article-title":"Discovering outlying aspects in large datasets","volume":"30","author":"Vinh","year":"2016","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"2","key":"10.3233\/IDA-184176_ref25","first-page":"1","article-title":"A distributed algorithm for the cluster-based outlier detection using unsupervised extreme learning machines","volume":"2017","author":"Wang","year":"2017","journal-title":"Mathematical Problems in Engineering"},{"issue":"10","key":"10.3233\/IDA-184176_ref26","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.14778\/2336664.2336674","article-title":"Efficient processing of k nearest neighbor joins using mapreduce","volume":"5","author":"Wei","year":"2012","journal-title":"Proceedings of The Vldb Endowment"},{"key":"10.3233\/IDA-184176_ref27","doi-asserted-by":"crossref","unstructured":"C. Xuan, An improved clustering algorithm for mixed attributes data based on k-prototypes algorithm, in: International Conference on Broadband and Wireless Computing, Communication and Applications, 2016, pp. 396\u2013399.","DOI":"10.1109\/BWCCA.2015.10"},{"key":"10.3233\/IDA-184176_ref28","doi-asserted-by":"crossref","unstructured":"Y. Yan, Distributed local outlier detection in big data, in: The ACM SIGKDD International Conference, 2017, pp. 1225\u20131234.","DOI":"10.1109\/BigData.2017.8257998"},{"key":"10.3233\/IDA-184176_ref31","doi-asserted-by":"crossref","unstructured":"H. Yu, A novel three-way clustering algorithm for mixed-type data, in: IEEE International Conference on Big Knowledge, 2017, pp. 119\u2013126.","DOI":"10.1109\/ICBK.2017.38"},{"key":"10.3233\/IDA-184176_ref32","doi-asserted-by":"crossref","first-page":"157","DOI":"10.3233\/IP-140322","article-title":"Review of big data: A revolution that will transform how we live, work and think, by kenneth cukier and viktor mayer-schonberger","volume":"19","author":"Zhang","year":"2014","journal-title":"Information Polity"},{"key":"10.3233\/IDA-184176_ref33","doi-asserted-by":"crossref","unstructured":"K. Zhang, From categorical to numerical: Multiple transitive distance learning and embedding, in: Siam International Conference on Data Mining, 2015.","DOI":"10.1137\/1.9781611974010.6"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-184176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:18:25Z","timestamp":1777454305000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-184176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,26]]},"references-count":28,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/ida-184176","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,26]]}}}