{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:56:52Z","timestamp":1781024212065,"version":"3.54.1"},"reference-count":97,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007835","name":"Silesian University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.asoc.2026.115341","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:17:52Z","timestamp":1777591072000},"page":"115341","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Comparison of algorithms for unsupervised clustering of binary data"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2098-2232","authenticated-orcid":false,"given":"Karolina","family":"Widzisz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3605-0398","authenticated-orcid":false,"given":"Mateusz","family":"Kania","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2895-7969","authenticated-orcid":false,"given":"Joanna","family":"Zyla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1793-9546","authenticated-orcid":false,"given":"Andrzej","family":"Pola\u0144ski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115341_bib0005","series-title":"Machine Learning","volume":"vol. 1","author":"Mitchell","year":"1997"},{"key":"10.1016\/j.asoc.2026.115341_bib0010","series-title":"Data Clustering: Algorithms and Applications","author":"Reddy","year":"2018"},{"key":"10.1016\/j.asoc.2026.115341_bib0015","series-title":"Cluster analysis 5th ed","author":"Everitt","year":"2011"},{"key":"10.1016\/j.asoc.2026.115341_bib0020","series-title":"Finding Groups in Data: an Introduction to Cluster Analysis","volume":"vol. 344","author":"Kaufman","year":"2009"},{"key":"10.1016\/j.asoc.2026.115341_bib0025","series-title":"Handbook of Cluster Analysis","author":"Hennig","year":"2015"},{"key":"10.1016\/j.asoc.2026.115341_bib0030","first-page":"1","article-title":"Experimental comparisons of clustering approaches for data representation","volume":"14","author":"Anand","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.asoc.2026.115341_bib0035","article-title":"Clustering algorithms: a comparative approach","volume":"55","author":"Rodriguez","year":"2019","journal-title":"PLOS ONE"},{"key":"10.1016\/j.asoc.2026.115341_bib0040","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1093\/bioinformatics\/btl406","article-title":"Evaluation and comparison of gene clustering methods in microarray analysis","volume":"22","author":"Thalamuthu","year":"2006","journal-title":"Bioinformatics"},{"key":"10.1016\/j.asoc.2026.115341_bib0045","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1080\/03610926.2013.806665","article-title":"The clustering of categorical data: a comparison of a model-based and a distance-based approach","volume":"43","author":"Anderlucci","year":"2014","journal-title":"Commun. Stat. - Theory Methods"},{"key":"10.1016\/j.asoc.2026.115341_bib0050","doi-asserted-by":"crossref","first-page":"S44","DOI":"10.1080\/13102818.2014.949045","article-title":"Clustering performance comparison using K-means and expectation maximization algorithms","volume":"28","author":"Jung","year":"2014","journal-title":"Biotechnol. Biotechnol. Equip."},{"key":"10.1016\/j.asoc.2026.115341_bib0055","series-title":"Model-Based Clustering and Classification for Data Science: with Applications in R","volume":"vol. 50","author":"Bouveyron","year":"2019"},{"key":"10.1016\/j.asoc.2026.115341_bib0060","series-title":"Proc. Of the 20th International Conference on Very Large Databases","first-page":"487","article-title":"Fast algorithms for mining association rules","author":"Agrawal","year":"1994"},{"key":"10.1016\/j.asoc.2026.115341_bib0065","doi-asserted-by":"crossref","first-page":"2705","DOI":"10.1016\/S0031-3203(01)00242-4","article-title":"On the use of Bernoulli mixture models for text classification","volume":"35","author":"Juan","year":"2002","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2026.115341_bib0070","doi-asserted-by":"crossref","first-page":"1544","DOI":"10.1007\/s11538-013-9859-9","article-title":"On the fractal geometry of DNA by the binary image analysis","volume":"75","author":"Cattani","year":"2013","journal-title":"Bull. Math. Biol."},{"key":"10.1016\/j.asoc.2026.115341_bib0075","series-title":"The Essential Guide to Image Processing","first-page":"69","article-title":"Basic binary image processing","author":"Bovik","year":"2009"},{"key":"10.1016\/j.asoc.2026.115341_bib0080","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1093\/bib\/bbx119","article-title":"Principal component analysis of binary genomics data","volume":"20","author":"Song","year":"2019","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.asoc.2026.115341_bib0085","series-title":"Intelligent Computing in Bioinformatics","first-page":"126","article-title":"Concept mining of binary gene expression data","author":"He","year":"2014"},{"key":"10.1016\/j.asoc.2026.115341_bib0090","doi-asserted-by":"crossref","first-page":"6371","DOI":"10.1182\/blood-2022-164610","article-title":"Identification of genetic subtypes in follicular lymphoma","volume":"140","author":"Shelton","year":"2022","journal-title":"Blood"},{"key":"10.1016\/j.asoc.2026.115341_bib0095","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1093\/bioinformatics\/btn479","article-title":"Chemical substructures that enrich for biological activity","volume":"24","author":"Klekota","year":"2008","journal-title":"Bioinformatics"},{"key":"10.1016\/j.asoc.2026.115341_bib0100","doi-asserted-by":"crossref","first-page":"3233","DOI":"10.1016\/j.csda.2007.09.007","article-title":"Block clustering with Bernoulli mixture models: comparison of different approaches","volume":"52","author":"Govaert","year":"2008","journal-title":"Comput. Stat. Data Anal."},{"key":"10.1016\/j.asoc.2026.115341_bib0105","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.neucom.2013.03.021","article-title":"Machine learning using Bernoulli mixture models: clustering, rule extraction and dimensionality reduction","volume":"119","author":"Saeed","year":"2013","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115341_bib0110","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the em algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. r. stat. soc.: ser. B (methodol.)"},{"key":"10.1016\/j.asoc.2026.115341_bib0115","series-title":"The EM Algorithm and Extensions","volume":"vol. 382","author":"McLachlan","year":"2007"},{"key":"10.1016\/j.asoc.2026.115341_bib0120","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.3150\/19-BEJ1173","article-title":"Reliable clustering of Bernoulli mixture models","volume":"26","author":"Najafi","year":"2020","journal-title":"Bernoulli"},{"key":"10.1016\/j.asoc.2026.115341_bib0125","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1111\/j.1755-0998.2010.02868.x","article-title":"Spatially explicit Bayesian clustering models in population Genetics","volume":"10","author":"Fran\u00e7ois","year":"2010","journal-title":"Mol. Ecol. Resour."},{"key":"10.1016\/j.asoc.2026.115341_bib0130","series-title":"Digital Design and Computer Architecture","author":"Harris","year":"2015"},{"key":"10.1016\/j.asoc.2026.115341_bib0135","doi-asserted-by":"crossref","first-page":"113","DOI":"10.2307\/2346482","article-title":"The analysis of multivariate binary data","volume":"21","author":"Cox","year":"1972","journal-title":"Appl. Stat."},{"key":"10.1016\/j.asoc.2026.115341_bib0140","series-title":"Proceedings of the 2005 SIAM International Conference on Data Mining, SIAM","first-page":"526","article-title":"On clustering binary data","author":"Li","year":"2005"},{"key":"10.1016\/j.asoc.2026.115341_bib0145","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1007\/s11634-018-0350-1","article-title":"Convex clustering for binary data","volume":"13","author":"Choi","year":"2019","journal-title":"Adv. Data Anal. Classif."},{"key":"10.1016\/j.asoc.2026.115341_bib0150","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0167-9473(96)00021-7","article-title":"Comparison of the mixture and the classification maximum likelihood in cluster analysis with binary data","volume":"23","author":"Govaert","year":"1996","journal-title":"Comput. Stat. Data Anal."},{"key":"10.1016\/j.asoc.2026.115341_bib0155","series-title":"Proc. Of tJoint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR)","first-page":"635","article-title":"Em initialisation for Bernoulli mixture learning","author":"Juan","year":"2004"},{"key":"10.1016\/j.asoc.2026.115341_bib0160","first-page":"43","article-title":"A survey of binary similarity and distance measures","volume":"8","author":"Choi","year":"2010","journal-title":"J. syst. cybern. inform."},{"key":"10.1016\/j.asoc.2026.115341_bib0165","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s10994-005-5316-9","article-title":"A unified view on clustering binary data","volume":"62","author":"Li","year":"2006","journal-title":"Mach. Learn."},{"key":"10.1016\/j.asoc.2026.115341_bib0170","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.3150\/19-BEJ1173","article-title":"Reliable clustering of Bernoulli mixture models","volume":"26","author":"Najafi","year":"2020","journal-title":"Bernoulli"},{"key":"10.1016\/j.asoc.2026.115341_bib0175","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0167-8655(02)00189-7","article-title":"Classification of binary vectors by using \u03b4SC distance to minimize stochastic complexity","volume":"24","author":"Franti","year":"2003","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.asoc.2026.115341_bib0180","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.csda.2009.07.013","article-title":"On multivariate binary data clustering and feature weighting","volume":"54","author":"Bouguila","year":"2010","journal-title":"Comput. Stat. Data Anal."},{"key":"10.1016\/j.asoc.2026.115341_bib0185","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TKDE.2010.263","article-title":"Feature selection based on class-dependent densities for high-dimensional binary data","volume":"24","author":"Javed","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.asoc.2026.115341_bib0190","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1007\/s10618-019-00635-1","article-title":"Efficient mixture model for clustering of sparse high dimensional binary data","volume":"33","author":"Smieja","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.asoc.2026.115341_bib0195","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1109\/TKDE.2020.2992529","article-title":"Encoding high-cardinality string categorical variables","volume":"34","author":"Cerda","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.asoc.2026.115341_bib0200","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","article-title":"Hierarchical grouping to optimize an objective function","volume":"58","author":"Ward","year":"1963","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.asoc.2026.115341_bib0205","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1002\/j.1538-7305.1950.tb00463.x","article-title":"Error detecting and error correcting codes","volume":"29","author":"Hamming","year":"1950","journal-title":"The Bell system technical journal"},{"key":"10.1016\/j.asoc.2026.115341_bib0210","doi-asserted-by":"crossref","first-page":"1672","DOI":"10.1002\/int.21990","article-title":"New similarity measures of intuitionistic fuzzy sets based on the jaccard index with its application to clustering","volume":"33","author":"Hwang","year":"2018","journal-title":"Int. J. Intell. Syst."},{"key":"10.1016\/j.asoc.2026.115341_bib0215","first-page":"547","article-title":"\u00c9tude comparative de LA distribution florale dans une portion des alpes ET des Jura","volume":"37","author":"Jaccard","year":"1901","journal-title":"Bull Soc Vaudoise Sci Nat"},{"key":"10.1016\/j.asoc.2026.115341_bib0220","series-title":"5th Berkeley Symp. Math. Statist. Probability","first-page":"281","article-title":"Classification and analysis of multivariate observations","author":"MacQueen","year":"1967"},{"key":"10.1016\/j.asoc.2026.115341_bib0225","first-page":"100","article-title":"Algorithm as 136: a K-means clustering algorithm","volume":"28","author":"Hartigan","year":"1979","journal-title":"J. R. Stat. Soc, C (appl. Stat.)"},{"key":"10.1016\/j.asoc.2026.115341_bib0230","series-title":"Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms","first-page":"1027","article-title":"K-means++ the advantages of careful seeding","author":"Arthur","year":"2007"},{"key":"10.1016\/j.asoc.2026.115341_bib0235","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/0098-3004(84)90020-7","article-title":"FCM: the fuzzy C-means clustering algorithm","volume":"10","author":"Bezdek","year":"1984","journal-title":"Comput. Geosci."},{"key":"10.1016\/j.asoc.2026.115341_bib0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocs.2026.102811","article-title":"Dpgmm: a new r package for efficient and robust Gaussian mixture modeling of 1d and 2d data","volume":"95","author":"Zyla","year":"2026","journal-title":"J. Comput. Sci."},{"key":"10.1016\/j.asoc.2026.115341_bib0245","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"Hubert","year":"1985","journal-title":"J. Classif."},{"key":"10.1016\/j.asoc.2026.115341_bib0250","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s00357-024-09482-2","article-title":"Normalised clustering accuracy: an asymmetric external cluster validity measure","volume":"42","author":"Gagolewski","year":"2025","journal-title":"J. Classif."},{"key":"10.1016\/j.asoc.2026.115341_bib0255","series-title":"Assessment metrics for imbalanced learning, imbalanced learning: foundations, algorithms, and applications","first-page":"187","author":"Japkowicz","year":"2013"},{"key":"10.1016\/j.asoc.2026.115341_bib0260","series-title":"2010 20th International Conference on Pattern Recognition","first-page":"3121","article-title":"The balanced accuracy and its posterior distribution","author":"Brodersen","year":"2010"},{"key":"10.1016\/j.asoc.2026.115341_bib0265","series-title":"An error metric for binary images, robust computer vision 5978","author":"Baddeley","year":"1992"},{"key":"10.1016\/j.asoc.2026.115341_bib0270","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genom."},{"key":"10.1016\/j.asoc.2026.115341_bib0275","series-title":"Data clustering: 50 years beyond K-means, pattern rez cognition letters 31","first-page":"651","author":"Jain","year":"2010"},{"key":"10.1016\/j.asoc.2026.115341_bib0280","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-49539-6","article-title":"Efficient partition of integer optimization problems with one-hot encoding","volume":"9","author":"Okada","year":"2019","journal-title":"Sci. Rep."},{"key":"10.1016\/j.asoc.2026.115341_bib0285","doi-asserted-by":"crossref","first-page":"177","DOI":"10.2307\/1924713","article-title":"Dummy variables: mechanics v. Interpretation","author":"Suits","year":"1984","journal-title":"Rev. Econ. Stat."},{"key":"10.1016\/j.asoc.2026.115341_bib0290","doi-asserted-by":"crossref","first-page":"10823","DOI":"10.1080\/03610926.2016.1248783","article-title":"An evaluation of common methods for dichotomization of continuous variables to discriminate disease status","volume":"46","author":"Nelson","year":"2017","journal-title":"Commun. Stat.-Theory Methods"},{"key":"10.1016\/j.asoc.2026.115341_bib0295","author":"Meila"},{"key":"10.1016\/j.asoc.2026.115341_bib0300","doi-asserted-by":"crossref","DOI":"10.1142\/S0219876218500123","article-title":"Initializing the em algorithm for univariate gaussian, multi-component, heteroscedastic mixture models by dynamic programming partitions","volume":"15","author":"Polanski","year":"2018","journal-title":"Int. J. Comput. Methods"},{"key":"10.1016\/j.asoc.2026.115341_bib0305","series-title":"Machine Learning: A Probabilistic Perspective, Adaptive Computation and Machine Learning Series","author":"Murphy","year":"2012"},{"key":"10.1016\/j.asoc.2026.115341_bib0310","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v053.i09","article-title":"fastcluster: Fast hierarchical, agglomerative clustering routines for r and Python","volume":"53","author":"M\u00fcllner","year":"2013","journal-title":"J. Stat. Softw."},{"key":"10.1016\/j.asoc.2026.115341_bib0315","series-title":"R: A Language and Environment for Statistical Computing","year":"2022"},{"key":"10.1016\/j.asoc.2026.115341_bib0320","author":"Mouselimis"},{"key":"10.1016\/j.asoc.2026.115341_bib0325","first-page":"1","article-title":"Comparison of internal validity indices for fuzzy clustering","author":"Cebeci","year":"2019","journal-title":"J. Agric. Inform."},{"key":"10.1016\/j.asoc.2026.115341_bib0330","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1002\/widm.53","article-title":"Algorithms for hierarchical clustering: an overview","volume":"2","author":"Murtagh","year":"2012","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"10.1016\/j.asoc.2026.115341_bib0335","series-title":"International Conference on Database Theory","first-page":"420","article-title":"On the surprising behavior of distance metrics in high dimensional space","author":"Aggarwal","year":"2001"},{"key":"10.1016\/j.asoc.2026.115341_bib0340","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1093\/sysbio\/45.3.380","article-title":"The probabilistic basis of jaccard\u2019s index of similarity","volume":"45","author":"Real","year":"1996","journal-title":"Syst. Biol."},{"key":"10.1016\/j.asoc.2026.115341_bib0345","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/j.patrec.2006.11.010","article-title":"A fuzzy extension of the RAND index and other related indexes for clustering and classification assessment","volume":"28","author":"Campello","year":"2007","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.asoc.2026.115341_bib0350","series-title":"Encyclopedia of Machine Learning and Data Mining","first-page":"414","article-title":"Error rate","author":"Ting","year":"2017"},{"key":"10.1016\/j.asoc.2026.115341_bib0355","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"1978","journal-title":"Ann. Stat."},{"key":"10.1016\/j.asoc.2026.115341_bib0360","first-page":"1","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Cali\u0144ski","year":"1974","journal-title":"Commun. Stat.-theory Methods"},{"key":"10.1016\/j.asoc.2026.115341_bib0365","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"10.1016\/j.asoc.2026.115341_bib0370","series-title":"A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters","author":"Dunn","year":"1973"},{"key":"10.1016\/j.asoc.2026.115341_bib0375","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1080\/01969727408546059","article-title":"Well-separated clusters and optimal fuzzy partitions","volume":"4","author":"Dunn","year":"1974","journal-title":"J. cybern."},{"key":"10.1016\/j.asoc.2026.115341_bib0380","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1016\/j.jmva.2006.11.013","article-title":"Comparing clusterings\u2014an information based distance","volume":"98","author":"Meil\u0103","year":"2007","journal-title":"J. Multivar. Anal."},{"key":"10.1016\/j.asoc.2026.115341_bib0385","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"A cluster separation measure","author":"Davies","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. PAMI-1"},{"key":"10.1016\/j.asoc.2026.115341_bib0390","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Nav. res. logist. q."},{"key":"10.1016\/j.asoc.2026.115341_bib0395","series-title":"Introduction to data mining, Pearson education India","author":"Tan","year":"2016"},{"key":"10.1016\/j.asoc.2026.115341_bib0400","author":"Palacio-Ni\u00f1o"},{"key":"10.1016\/j.asoc.2026.115341_bib0405","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1093\/oxfordjournals.aob.a083391","article-title":"A new method for determining the type of distribution of plant individuals","volume":"18","author":"Hopkins","year":"1954","journal-title":"Ann. Bot."},{"key":"10.1016\/j.asoc.2026.115341_bib0410","first-page":"99","article-title":"Comparing individual means in the analysis of variance","volume":"5","author":"John","year":"1948","journal-title":"Biometrics"},{"key":"10.1016\/j.asoc.2026.115341_bib0415","doi-asserted-by":"crossref","first-page":"72","DOI":"10.2307\/1412159","article-title":"The proof and measurement of association between two things","volume":"15","author":"Spearman","year":"1904","journal-title":"Am. J. Psychol."},{"key":"10.1016\/j.asoc.2026.115341_bib0420","author":"Forsyth"},{"key":"10.1016\/j.asoc.2026.115341_bib0435","author":"Aha"},{"key":"10.1016\/j.asoc.2026.115341_bib0440","author":"Mitchell"},{"key":"10.1016\/j.asoc.2026.115341_bib0445","author":"Kushmerick"},{"key":"10.1016\/j.asoc.2026.115341_bib0450","series-title":"Proceedings of the Third Annual Conference on Autonomous Agents, AGENTS 1999, Seattle, WA, USA, May 1\u20135, 1999, ACM","first-page":"175","article-title":"Learning to remove internet advertisements","author":"Kushmerick","year":"1999"},{"key":"10.1016\/j.asoc.2026.115341_bib0455","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1038\/s41587-020-0465-8","article-title":"Systematic comparison of single-cell and single-nucleus rna-sequencing methods","volume":"38","author":"Ding","year":"2020","journal-title":"Nat. Biotechnol."},{"key":"10.1016\/j.asoc.2026.115341_bib0460","series-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics","first-page":"149","article-title":"Gamred\u2014adaptive filtering of high-throughput biological data","volume":"vol. 17","author":"Marczyk","year":"2020"},{"key":"10.1016\/j.asoc.2026.115341_bib0465","series-title":"Data Clustering: Theory, Algorithms, and Applications","author":"Gan","year":"2020"},{"key":"10.1016\/j.asoc.2026.115341_bib0470","series-title":"A General Coefficient of Similarity and Some of Its Properties, Biometrics","first-page":"857","author":"Gower","year":"1971"},{"key":"10.1016\/j.asoc.2026.115341_bib0475","article-title":"Differential analysis of binarized single-cell RNA sequencing data captures biological variation","volume":"3","author":"Bouland","year":"2021","journal-title":"NAR Genom. Bioinform."},{"key":"10.1016\/j.asoc.2026.115341_bib0480","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1016\/j.patrec.2013.04.007","article-title":"An optimization for binarization methods by removing binary artifacts","volume":"34","author":"Ram\u00edrez-Orteg\u00f3n","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.asoc.2026.115341_bib0485","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1093\/bioinformatics\/18.4.555","article-title":"Binary analysis and optimization-based normalization of gene expression data","volume":"18","author":"Shmulevich","year":"2002","journal-title":"Bioinformatics"},{"key":"10.1016\/j.asoc.2026.115341_bib0490","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0144059","article-title":"A comparison study on similarity and dissimilarity measures in clustering continuous data","volume":"10","author":"Shirkhorshidi","year":"2015","journal-title":"PLOS ONE"},{"key":"10.1016\/j.asoc.2026.115341_bib0495","series-title":"Intelligent Computing Methodologies: 13th International Conference, ICIC 2017, Liverpool, UK, August 7\u201310, 2017, Proceedings, Part III 13","first-page":"719","article-title":"A comparison of distance metrics in semi-supervised hierarchical clustering methods","author":"Aljohani","year":"2017"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626007891?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626007891?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:57:00Z","timestamp":1781020620000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626007891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":97,"alternative-id":["S1568494626007891"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115341","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Comparison of algorithms for unsupervised clustering of binary data","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115341","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115341"}}