{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:12:57Z","timestamp":1759133577576},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,7,15]],"date-time":"2017-07-15T00:00:00Z","timestamp":1500076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s10844-017-0472-5","type":"journal-article","created":{"date-parts":[[2017,7,15]],"date-time":"2017-07-15T06:13:53Z","timestamp":1500099233000},"page":"619-636","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["One-pass MapReduce-based clustering method for mixed large scale data"],"prefix":"10.1007","volume":"52","author":[{"given":"Mohamed Aymen","family":"Ben HajKacem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiheb-Eddine Ben","family":"N\u2019cir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadia","family":"Essoussi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,15]]},"reference":[{"issue":"2","key":"472_CR1","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.datak.2007.03.016","volume":"63","author":"A Ahmad","year":"2007","unstructured":"Ahmad, A., & Dey, L. (2007). A k-mean clustering algorithm for mixed numeric and categorical data. Data Knowledge Engineering, 63(2), 503\u2013527.","journal-title":"Data Knowledge Engineering"},{"issue":"6","key":"472_CR2","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1016\/j.eswa.2014.11.050","volume":"42","author":"MW Ayech","year":"2015","unstructured":"Ayech, M. W., & Ziou, D (2015). Segmentation of Terahertz imaging using k-means clustering based on ranked set sampling. Expert Systems with Applications, 42(6), 2959\u20132974.","journal-title":"Expert Systems with Applications"},{"issue":"7","key":"472_CR3","doi-asserted-by":"publisher","first-page":"622","DOI":"10.14778\/2180912.2180915","volume":"5","author":"B Bahmani","year":"2012","unstructured":"Bahmani, B., Moseley, B., Vattani, A., Kumar, R., & Vassilvitskii, S. (2012). Scalable k-means++. Proceedings of the VLDB Endowment, 5(7), 622\u2013633.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"472_CR4","doi-asserted-by":"crossref","unstructured":"Ben Haj Kacem, M. A., Ben N\u2019cir, C. E., & Essoussi, N (2015). MapReduce-based k-prototypes clustering method for big data. In Proceedings of data science and advanced analytics (pp. 1\u20137).","DOI":"10.1109\/DSAA.2015.7344894"},{"key":"472_CR5","unstructured":"Ben HajKacem, M. A., N\u2019cir, C. E., & Essoussi, N (2016). An accelerated MapReduce-based K-prototypes for big data. In Proceedings of software technologies: applications and foundations (pp. 1\u201313)."},{"issue":"03","key":"472_CR6","doi-asserted-by":"publisher","first-page":"1550013","DOI":"10.1142\/S0218001415500135","volume":"29","author":"CE Ben N\u2019Cir","year":"2015","unstructured":"Ben N\u2019Cir, C. E., & Essoussi, N (2015). Using sequences of words for non-disjoint grouping of documents. International Journal of Pattern Recognition and Artificial Intelligence, 29(03), 1550013.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"issue":"1","key":"472_CR7","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., & Ghemawat, S. (2008). Mapreduce: simplified data processing on large clusters. Communications of the ACM, 51(1), 107\u2013113.","journal-title":"Communications of the ACM"},{"issue":"05","key":"472_CR8","doi-asserted-by":"publisher","first-page":"1555009","DOI":"10.1142\/S0218001415550095","volume":"29","author":"H Du","year":"2015","unstructured":"Du, H., Wang, Y., & Dong, X (2015). Texture image segmentation using affinity propagation and spectral clustering. International Journal of Pattern Recognition and Artificial Intelligence, 29(05), 1555009.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"472_CR9","doi-asserted-by":"crossref","unstructured":"Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S. H., Qiu, J., & Fox, G. (2010). Twister: a runtime for iterative mapreduce. In Proceedings of the 19th ACM international symposium on high performance distributed computing (pp. 810\u2013818). ACM.","DOI":"10.1145\/1851476.1851593"},{"issue":"1","key":"472_CR10","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/restud\/rdq016","volume":"78","author":"K Eliaz","year":"2011","unstructured":"Eliaz, K., & Spiegler, R (2011). Consideration sets and competitive marketing. The Review of Economic Studies, 78(1), 235\u2013262.","journal-title":"The Review of Economic Studies"},{"issue":"2","key":"472_CR11","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.ijinfomgt.2014.10.007","volume":"35","author":"A Gandomi","year":"2015","unstructured":"Gandomi, A., & Haider, M. (2015). Beyond the hype: big data concepts, methods, and analytics. International Journal of Information Management, 35(2), 137\u2013144.","journal-title":"International Journal of Information Management"},{"key":"472_CR12","doi-asserted-by":"crossref","unstructured":"Gorodetsky, V. (2014). Big data: opportunities, challenges and solutions. In Information and communication technologies in education, research, and industrial applications (pp. 3\u201322).","DOI":"10.1007\/978-3-319-13206-8_1"},{"key":"472_CR13","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1016\/j.neucom.2013.04.011","volume":"120","author":"J Ji","year":"2013","unstructured":"Ji, J., Bai, T., Zhou, C., Ma, C., & Wang, Z. (2013). An improved k-prototypes clustering algorithm for mixed numeric and categorical data. Neurocomputing, 120, 590\u2013596.","journal-title":"Neurocomputing"},{"issue":"2","key":"472_CR14","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11227-014-1185-y","volume":"69","author":"A Hadian","year":"2014","unstructured":"Hadian, A., & Shahrivari, S (2014). High performance parallel k-means clustering for disk-resident datasets on multi-core CPUs. The Journal of Supercomputing, 69(2), 845\u2013863.","journal-title":"The Journal of Supercomputing"},{"key":"472_CR15","unstructured":"Han, J., Pei, J., & Kamber, M. (2011). Data mining: concepts and techniques. Elsevier."},{"key":"472_CR16","doi-asserted-by":"crossref","unstructured":"He, C., Chang, J., & Chen, X. (2010). Using the triangle inequality to accelerate TTSAS cluster algorithm. In Electrical and control engineering (ICECE) (pp. 2507\u20132510). IEEE.","DOI":"10.1109\/iCECE.2010.620"},{"issue":"1","key":"472_CR17","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s10844-014-0307-6","volume":"43","author":"SF Hussain","year":"2014","unstructured":"Hussain, S. F., Mushtaq, M., & Halim, Z (2014). Multi-view document clustering via ensemble method. Journal of Intelligent Information Systems, 43(1), 81\u201399.","journal-title":"Journal of Intelligent Information Systems"},{"key":"472_CR18","unstructured":"Huang, Z. (1997). Clustering large data sets with mixed numeric and categorical values. In Proceedings of the 1st Pacific-Asia conference on knowledge discovery and data mining (pp. 21\u201334)."},{"issue":"3","key":"472_CR19","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain, A. K., Murty, M. N., & Flynn, PJ (1999). Data clustering: a review. ACM computing surveys (CSUR), 31(3), 264\u2013323.","journal-title":"ACM computing surveys (CSUR)"},{"key":"472_CR20","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.is.2013.11.002","volume":"42","author":"Y Kim","year":"2014","unstructured":"Kim, Y., Shim, K., Kim, M. S., & Lee, J. S. (2014). DBCURE-MR: an efficient density-based clustering algorithm for large data using MapReduce. Information Systems, 42, 15\u201335.","journal-title":"Information Systems"},{"issue":"4","key":"472_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/2094114.2094118","volume":"40","author":"KH Lee","year":"2012","unstructured":"Lee, K. H., Lee, Y. J., Choi, H., Chung, Y. D., & Moon, B (2012). Parallel data processing with MapReduce: a survey. AcM sIGMoD Record, 40(4), 11\u201320.","journal-title":"AcM sIGMoD Record"},{"issue":"4","key":"472_CR22","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/TKDE.2002.1019208","volume":"14","author":"C Li","year":"2002","unstructured":"Li, C., & Biswas, G. (2002). Unsupervised learning with mixed numeric and nominal data. Knowledge and Data Engineering, 14(4), 673\u2013690.","journal-title":"Knowledge and Data Engineering"},{"issue":"1","key":"472_CR23","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1016\/j.eswa.2006.09.039","volume":"34","author":"HH Liu","year":"2008","unstructured":"Liu, H. H., & Ong, C. S. (2008). Variable selection in clustering for marketing segmentation using genetic algorithms. Expert Systems with Applications, 34(1), 502\u2013510.","journal-title":"Expert Systems with Applications"},{"key":"472_CR24","doi-asserted-by":"crossref","unstructured":"Ludwig, S. A. (2015). Mapreduce-based fuzzy c-means clustering algorithm: implementation and scalability. In International journal of machine learning and cybernetics (pp. 1\u201312).","DOI":"10.1007\/s13042-015-0367-0"},{"key":"472_CR25","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1007\/11430919_45","volume-title":"Pacific-Asia conference on knowledge discovery and data mining","author":"M Nanni","year":"2005","unstructured":"Nanni, M. (2005). Speeding-up hierarchical agglomerative clustering in presence of expensive metrics, Pacific-Asia conference on knowledge discovery and data mining (pp. 378\u2013387). Berlin Heidelberg: Springer."},{"issue":"3","key":"472_CR26","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1109\/TPAMI.2007.53","volume":"29","author":"MK Ng","year":"2007","unstructured":"Ng, M. K., Li, M. J., Huang, J. Z., & He, Z (2007). On the impact of dissimilarity measure in k-modes clustering algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(3), 503\u2013507.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"472_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.is.2016.02.007","volume":"60","author":"S Shahrivari","year":"2016","unstructured":"Shahrivari, S., & Jalili, S. (2016). Single-pass and linear-time k-means clustering based on MapReduce. Information Systems, 60, 1\u201312.","journal-title":"Information Systems"},{"key":"472_CR28","doi-asserted-by":"crossref","unstructured":"Talbot, J., Yoo, R. M., & Kozyrakis, C. (2011). Phoenix++: modular MapReduce for shared-memory systems. In Proceedings of the second international workshop on MapReduce and its applications (pp. 9\u201316). ACM.","DOI":"10.1145\/1996092.1996095"},{"issue":"10","key":"472_CR29","doi-asserted-by":"publisher","first-page":"11994","DOI":"10.1016\/j.eswa.2009.05.029","volume":"36","author":"CF Tsai","year":"2009","unstructured":"Tsai, C. F., Hsu, Y. F., Lin, C. Y., & Lin, W. Y. (2009). Intrusion detection by machine learning: A review. Expert Systems with Applications, 36(10), 11994\u201312000.","journal-title":"Expert Systems with Applications"},{"key":"472_CR30","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/RBME.2010.2083647","volume":"3","author":"R Xu","year":"2010","unstructured":"Xu, R., & Wunsch, D. C. (2010). Clustering algorithms in biomedical research: a review. Biomedical Engineering, IEEE Reviews, 3, 120\u2013154.","journal-title":"Biomedical Engineering, IEEE Reviews"},{"key":"472_CR31","doi-asserted-by":"crossref","unstructured":"Xu, X., Jeger, J., & Kriegel, H. P. (2002). A fast parallel clustering algorithm for large spatial databases. In High performance data mining (pp. 263\u2013290).","DOI":"10.1007\/0-306-47011-X_3"},{"issue":"9","key":"472_CR32","doi-asserted-by":"publisher","first-page":"6225","DOI":"10.1016\/j.eswa.2010.02.102","volume":"37","author":"G Wang","year":"2010","unstructured":"Wang, G., Hao, J., Ma, J., & Huang, L (2010). A new approach to intrusion detection using artificial neural networks and fuzzy clustering. Expert Systems with Applications, 37(9), 6225\u20136232.","journal-title":"Expert Systems with Applications"},{"key":"472_CR33","unstructured":"White, T. (2012). Hadoop: the definitive guide. O\u2019Reilly Media Inc."},{"issue":"10\u201310","key":"472_CR34","first-page":"95","volume":"10","author":"M Zaharia","year":"2010","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I (2010). Spark: cluster computing with working sets. HotCloud, 10(10\u201310), 95.","journal-title":"HotCloud"},{"key":"472_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, W., Ma, H., & He, Q. (2009). Parallel k-means clustering based on mapreduce. In Proceedings of cloud computing (pp 674\u2013679).","DOI":"10.1007\/978-3-642-10665-1_71"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-017-0472-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10844-017-0472-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-017-0472-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T23:12:39Z","timestamp":1558480359000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10844-017-0472-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,15]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["472"],"URL":"https:\/\/doi.org\/10.1007\/s10844-017-0472-5","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,15]]},"assertion":[{"value":"20 December 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2017","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2017","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}