{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T09:10:02Z","timestamp":1746177002496,"version":"3.40.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2014,4,8]],"date-time":"2014-04-08T00:00:00Z","timestamp":1396915200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1007\/s11042-014-1914-5","type":"journal-article","created":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T05:58:57Z","timestamp":1396850337000},"page":"3489-3505","source":"Crossref","is-referenced-by-count":4,"title":["How to measure similarity for multiple categorical data sets?"],"prefix":"10.1007","volume":"74","author":[{"given":"Simon Soon-Hyoung","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin JongSu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James Jung-Hoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wookey","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangbok","family":"Ree","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,4,8]]},"reference":[{"issue":"1","key":"1914_CR1","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.patrec.2006.06.006","volume":"28","author":"A Ahmad","year":"2007","unstructured":"Ahmad A, Dey L (2007) A method to compute distance between two categorical values of same attribute in unsupervised learning for categorical data set. Pattern Recogn Lett 28(1):110\u2013118","journal-title":"Pattern Recogn Lett"},{"issue":"2","key":"1914_CR2","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s00354-013-0203-6","volume":"31","author":"NR Arora","year":"2013","unstructured":"Arora NR, Lee W (2013) Graph based ranked answers for keyword graph structure. N Gener Comput 31(2):115\u2013134","journal-title":"N Gener Comput"},{"issue":"1","key":"1914_CR3","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s11042-011-0798-x","volume":"61","author":"PK Atrey","year":"2012","unstructured":"Atrey PK, Ibrahim H, Hossain MA, Ramanna S, El-Saddik A (2012) Determining trust in media-rich websites using semantic similarity. Multimed Tools Appl 61(1):69\u201396","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"1914_CR4","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/s11042-009-0339-z","volume":"47","author":"M Batko","year":"2010","unstructured":"Batko M, Falchi F, Lucchese C, Novak D, Perego R, Rabitti F, Sedmidubsky J, Zezula P (2010) Building a web-scale image similarity search system. Multimed Tools Appl 47(3):599\u2013629","journal-title":"Multimed Tools Appl"},{"key":"1914_CR5","doi-asserted-by":"crossref","unstructured":"Bhaduri K, Matthews BL, Giannella C (2011) Algorithms for speeding up distance-based outlier detection. Proceedings of the 17th ACM SIGKDD international conference on Knowledge Discovery and Data Mining, pp 859\u2013867","DOI":"10.1145\/2020408.2020554"},{"key":"1914_CR6","doi-asserted-by":"crossref","unstructured":"Boriah S, Chandola V, Kumar V (2008) Similarity measures for categorical data: a comparative evaluation. In Proceedings of the 8th SIAM International Conference on Data Mining, pp 243\u2013254","DOI":"10.1137\/1.9781611972788.22"},{"key":"1914_CR7","unstructured":"Candan WSL, Vu Q, Agrawal D (2001) Retrieving and organizing web pages by \u201cInformation unit,\u201d. Proceedings of the 10th International Conference on World Wide Web, pp 230\u2013244"},{"key":"1914_CR8","doi-asserted-by":"crossref","unstructured":"Cheesman P, Kelly J, Self M, Stutz J, Taylor W, Freeman D (1988) AutoClass: a Bayesian classification system. International Conference on Machine Learning, pp 54\u201364","DOI":"10.1016\/B978-0-934613-64-4.50011-6"},{"issue":"1","key":"1914_CR9","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/0031-3203(93)90096-F","volume":"26","author":"TF Cox","year":"1993","unstructured":"Cox TF, Ferry G (1993) Discriminant analysis using non-metric multidimensional scaling. Pattern Recogn 26(1):145\u2013153","journal-title":"Pattern Recogn"},{"key":"1914_CR10","doi-asserted-by":"crossref","unstructured":"Das G, Mannila H (2000) Context-based similarity measures for categorical databases. Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery, pp 201\u2013210","DOI":"10.1007\/3-540-45372-5_20"},{"key":"1914_CR11","doi-asserted-by":"crossref","unstructured":"Dzogang F, Marsala C, Lesot MJ, Rifqi M (2012) An ellipsoidal k-means for document clustering. IEEE International Conference on Data Mining, pp 221\u2013230","DOI":"10.1109\/ICDM.2012.126"},{"key":"1914_CR12","doi-asserted-by":"crossref","unstructured":"Ganti V, Gehrke J, Ramakrishnan R, (1999) CACTUS-clustering categorical data using summaries. Proceedings of the 5th ACM SIGKDD International Conference on Knowledge discovery and Data Mining, pp 73\u201383","DOI":"10.1145\/312129.312201"},{"issue":"3","key":"1914_CR13","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s007780050005","volume":"8","author":"D Gibson","year":"2000","unstructured":"Gibson D, Kleinberg J, Raghavan P (2000) Clustering categorical data: an approach based on dynamical systems. VLDB J 8(3):222\u2013236","journal-title":"VLDB J"},{"issue":"4","key":"1914_CR14","doi-asserted-by":"crossref","first-page":"882","DOI":"10.2307\/2528080","volume":"22","author":"DW Goodall","year":"1996","unstructured":"Goodall DW (1996) A new similarity index based on probability. Biometrics 22(4):882\u2013907","journal-title":"Biometrics"},{"issue":"9","key":"1914_CR15","doi-asserted-by":"crossref","first-page":"1058","DOI":"10.1093\/comjnl\/bxr131","volume":"55","author":"J Gou","year":"2012","unstructured":"Gou J, Yi Z, Du L, Xiong T (2012) A local mean-based k-nearest centroid neighbor classifier. Comput J 55(9):1058\u20131071","journal-title":"Comput J"},{"issue":"5","key":"1914_CR16","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","volume":"25","author":"S Guha","year":"2000","unstructured":"Guha S, Rastogi R, Shim K (2000) ROCK: a robust clustering algorithm for categorical attributes. Inf Syst 25(5):345\u2013366","journal-title":"Inf Syst"},{"issue":"3","key":"1914_CR17","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1016\/j.is.2012.07.001","volume":"38","author":"T Hashem","year":"2013","unstructured":"Hashem T, Kulik L, Zhang R (2013) Countering overlapping rectangle privacy attack for moving kNN queries. Inf Syst 38(3):430\u2013453","journal-title":"Inf Syst"},{"issue":"3","key":"1914_CR18","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1023\/A:1009769707641","volume":"2","author":"Z Huang","year":"1998","unstructured":"Huang Z (1998) Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Disc 2(3):283\u2013304","journal-title":"Data Min Knowl Disc"},{"issue":"4","key":"1914_CR19","first-page":"1","volume":"3","author":"YP Huang","year":"2012","unstructured":"Huang YP, Lai SL (2012) Novel query-by-humming\/singing method with fuzzy inference system. J Converg 3(4):1\u20138","journal-title":"J Converg"},{"issue":"4","key":"1914_CR20","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1109\/91.784206","volume":"7","author":"Z Huang","year":"1999","unstructured":"Huang Z, Ng KM (1999) A fuzzy k-modes algorithm for clustering categorical data. IEEE Trans Fuzzy Syst 7(4):446\u2013452","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"1914_CR21","doi-asserted-by":"crossref","unstructured":"Hwang S, Yu H (2007) Mining and processing category ranking. The 22nd Annual ACM Symposium on Applied Computing, pp 441\u2013442","DOI":"10.1145\/1244002.1244103"},{"issue":"6","key":"1914_CR22","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1002\/(SICI)1097-4571(198711)38:6<420::AID-ASI3>3.0.CO;2-S","volume":"38","author":"WP Jones","year":"1987","unstructured":"Jones WP, Furnas GW (1987) Pictures of relevance: a geometric analysis of similarity measures. J Am Soc Inf Sci 38(6):420\u2013442","journal-title":"J Am Soc Inf Sci"},{"key":"1914_CR23","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"L Kaufman","year":"1990","unstructured":"Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley, New York"},{"issue":"2","key":"1914_CR24","first-page":"9","volume":"3","author":"HC Kuo","year":"2012","unstructured":"Kuo HC (2012) Automatic concept hierarchy construction from a distance. J Converg 3(2):9\u201314","journal-title":"J Converg"},{"key":"1914_CR25","doi-asserted-by":"crossref","unstructured":"Le SQ, Ho TB (2005) An association-based dissimilarity measure for categorical data. Pattern Recogn Lett 26(16):2549\u20132557","DOI":"10.1016\/j.patrec.2005.06.002"},{"issue":"6","key":"1914_CR26","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1109\/TIE.2010.2050292","volume":"58","author":"W Lee","year":"2011","unstructured":"Lee W, Leung CK, Lee J (2011) Mobile web navigation in digital ecosystems using rooted directed trees. IEEE Trans Ind Electron 58(6):2154\u20132162","journal-title":"IEEE Trans Ind Electron"},{"key":"1914_CR27","doi-asserted-by":"crossref","unstructured":"Lee W, Song J, Leung CK (2011) Categorical data skyline using classification tree. Asia-Pacific Web Conference, pp 181\u2013187","DOI":"10.1007\/978-3-642-20291-9_19"},{"issue":"3","key":"1914_CR28","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1016\/j.cie.2011.11.013","volume":"62","author":"W Lee","year":"2012","unstructured":"Lee W, Loh W, Sohn M (2012) Searching Steiner trees for web graph query. Comput Ind Eng 62(3):732\u2013739","journal-title":"Comput Ind Eng"},{"key":"1914_CR29","unstructured":"Lin D (1998) An information-theoretic definition of similarity. International Machine Learning Society, pp 296\u2013304"},{"issue":"2","key":"1914_CR30","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s11042-010-0612-1","volume":"60","author":"L Mekouar","year":"2012","unstructured":"Mekouar L, Iraqi Y, Boutaba R (2012) An analysis of peer similarity for recommendations in P2P systems. Multimed Tools Appl 60(2):277\u2013303","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"1914_CR31","doi-asserted-by":"crossref","first-page":"621","DOI":"10.3745\/JIPS.2012.8.4.621","volume":"8","author":"G Nagpal","year":"2012","unstructured":"Nagpal G, Uddin M, Kaur A (2012) A comparative study of estimation by analogy using data mining techniques. J Inf Process Syst 8(4):621\u2013665","journal-title":"J Inf Process Syst"},{"key":"1914_CR32","unstructured":"Noreault T, McGill M, Koll MB (1981) A performance evaluation of similarity measures, document term weighting schemes and representations in a boolean environment. Proceedings of the 3rd Annual ACM conference on Research and Development in Information Retrieval, pp 57\u201376"},{"issue":"2","key":"1914_CR33","first-page":"1469","volume":"3","author":"GH Orair","year":"2010","unstructured":"Orair GH, Teixeira CHC, Wang Y, Meira W Jr, Parthasarathy S (2010) Distance-based outlier detection: consolidation and renewed bearing. VLDB J 3(2):1469\u20131480","journal-title":"VLDB J"},{"key":"1914_CR34","doi-asserted-by":"crossref","unstructured":"Palmer CR, Faloutsos C (2003) Electricity based external similarity of categorical attributes. Proceedings of the 7th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, pp 486\u2013500","DOI":"10.1007\/3-540-36175-8_49"},{"issue":"2","key":"1914_CR35","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/0165-0114(93)90141-4","volume":"56","author":"CP Pappis","year":"1993","unstructured":"Pappis CP, Karacapilidis NI (1993) A comparative assessment of measures of similarity of fuzzy values. Fuzzy Sets Syst 56(2):171\u2013174","journal-title":"Fuzzy Sets Syst"},{"issue":"1","key":"1914_CR36","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s11042-010-0562-7","volume":"57","author":"J Perkio","year":"2012","unstructured":"Perkio J, Tuominen AJ, Vahakangas T, Myllymaki P (2012) Image similarity: from syntax to weak semantics. Multimed Tools Appl 57(1):5\u201327","journal-title":"Multimed Tools Appl"},{"issue":"5","key":"1914_CR37","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.is.2012.09.004","volume":"38","author":"PS Santos Jr","year":"2013","unstructured":"Santos PS Jr, Almeida JPA, Guizzardi G (2013) An ontology-based analysis and semantics for organizational structure modeling in the ARIS method. Inf Syst 38(5):690\u2013708","journal-title":"Inf Syst"},{"issue":"3","key":"1914_CR38","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1093\/comjnl\/bxr024","volume":"55","author":"G Spanakis","year":"2012","unstructured":"Spanakis G, Siolas G, Stafylopatis A (2012) Exploiting Wikipedia knowledge for conceptual hierarchical clustering of documents. Comput J 55(3):299\u2013312","journal-title":"Comput J"},{"key":"1914_CR39","doi-asserted-by":"crossref","unstructured":"Stull RB (1988) An introduction to boundary layer meteorology. Atmospheric Sciences Library","DOI":"10.1007\/978-94-009-3027-8"},{"key":"1914_CR40","unstructured":"The 1998 ACM Computing Classification System\u2014Association for Computing Machinery, http:\/\/www.acm.org\/about\/class\/1998\/"},{"key":"1914_CR41","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.ins.2011.12.005","volume":"190","author":"V Torra","year":"2012","unstructured":"Torra V, Narukawa Y (2012) On a comparison between Mahalanobis distance and Choquet integral: the Choquet-Mahalanobis operator. Inf Sci Int J 190:56\u201363","journal-title":"Inf Sci Int J"},{"issue":"2","key":"1914_CR42","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0165-0114(94)00308-T","volume":"73","author":"X Wang","year":"1995","unstructured":"Wang X, Baets B, De Kerre E (1995) A comparative study of similarity measures. Fuzzy Sets Syst 73(2):259\u2013268","journal-title":"Fuzzy Sets Syst"},{"key":"1914_CR43","doi-asserted-by":"crossref","unstructured":"Wong WK, Cheung DW, Kao B, Mamoulis N, (2009) Secure kNN computation on encrypted databases. Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data, pp 139\u2013152","DOI":"10.1145\/1559845.1559862"},{"key":"1914_CR44","doi-asserted-by":"crossref","unstructured":"Wu Z, Palmer M (1994) Verbs semantics and lexical selection. Proceedings of the 32nd Annual Meeting on Association for Computational Linguistics, pp 133\u2013138","DOI":"10.3115\/981732.981751"},{"key":"1914_CR45","doi-asserted-by":"crossref","unstructured":"Yang Y, Guan X, You J (2002) CLOPE: a fast and effective clustering algorithm for transactional data, Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 682\u2013687","DOI":"10.1145\/775047.775149"},{"key":"1914_CR46","doi-asserted-by":"crossref","unstructured":"Yu H, Ko I, Kim Y, Hwang SW, Han WS (2011) Exact indexing for support vector machines. Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp 709\u2013720","DOI":"10.1145\/1989323.1989398"},{"issue":"2","key":"1914_CR47","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s00778-009-0148-z","volume":"19","author":"Z Zhang","year":"2010","unstructured":"Zhang Z, Lu H, Ooi BC, Tung AKH (2010) Understanding the meaning of a shifted sky: a general framework on extending skyline query. VLDB J 19(2):181\u2013201","journal-title":"VLDB J"},{"issue":"2","key":"1914_CR48","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/0888-613X(87)90015-6","volume":"1","author":"R Zwick","year":"1987","unstructured":"Zwick R, Carlstein E, Budescu DV (1987) Measures of similarity among fuzzy concepts: a comparative analysis. Int J Approx Reason 1(2):221\u2013242","journal-title":"Int J Approx Reason"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1914-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-1914-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1914-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T08:53:30Z","timestamp":1746176010000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-1914-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,8]]},"references-count":48,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2015,5]]}},"alternative-id":["1914"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-1914-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2014,4,8]]}}}