{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T14:03:17Z","timestamp":1784556197670,"version":"3.55.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T00:00:00Z","timestamp":1559520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T00:00:00Z","timestamp":1559520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["ICT-2013-612944"],"award-info":[{"award-number":["ICT-2013-612944"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["H2020-688797"],"award-info":[{"award-number":["H2020-688797"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003407","name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["ARS01 01259"],"award-info":[{"award-number":["ARS01 01259"]}],"id":[{"id":"10.13039\/501100003407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s40537-019-0207-2","type":"journal-article","created":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T09:03:38Z","timestamp":1559552618000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["DENCAST: distributed density-based clustering for multi-target regression"],"prefix":"10.1186","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8366-6059","authenticated-orcid":false,"given":"Roberto","family":"Corizzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianvito","family":"Pio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelangelo","family":"Ceci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donato","family":"Malerba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,6,3]]},"reference":[{"issue":"6","key":"207_CR1","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1109\/TSMCB.2004.836890","volume":"34","author":"M Cannataro","year":"2004","unstructured":"Cannataro M, Congiusta A, Pugliese A, Talia D, Trunfio P. Distributed data mining on grids: services, tools, and applications. IEEE Trans Syst Man Cybern B. 2004;34(6):2451\u201365.","journal-title":"IEEE Trans Syst Man Cybern B"},{"key":"207_CR2","first-page":"226","volume":"96","author":"M Ester","year":"1996","unstructured":"Ester M, Kriegel H-P, Sander J, Xu X, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. Kdd. 1996;96:226\u201331.","journal-title":"Kdd"},{"key":"207_CR3","doi-asserted-by":"crossref","unstructured":"He Y, Tan H, Luo W, Mao H, Ma D, Feng S, Fan J. MR-DBSCAN: an efficient parallel density-based clustering algorithm using MapReduce. In: Proceeding of ICPADS. 2011. p. 473\u201380.","DOI":"10.1109\/ICPADS.2011.83"},{"key":"207_CR4","doi-asserted-by":"crossref","unstructured":"Cordova I, Moh T-S. DBSCAN on resilient distributed datasets. In: High performance computing & simulation. 2015. p. 531\u201340.","DOI":"10.1109\/HPCSim.2015.7237086"},{"key":"207_CR5","doi-asserted-by":"crossref","unstructured":"Han D, Agrawal A, Liao WK, Choudhary A. A novel scalable DBSCAN algorithm with Spark. In: International parallel and distributed processing symposium workshops. 2016. p. 1393\u2013402.","DOI":"10.1109\/IPDPSW.2016.57"},{"key":"207_CR6","first-page":"55","volume-title":"Proceeding of ICML","author":"H Blockeel","year":"1998","unstructured":"Blockeel H, Raedt LD, Ramon J. Top\u2013down induction of clustering trees. In: Shavlik JW, editor. Proceeding of ICML. Madison: Morgan Kaufmann; 1998. p. 55\u201363."},{"issue":"3","key":"207_CR7","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1109\/TII.2016.2604758","volume":"13","author":"M Ceci","year":"2017","unstructured":"Ceci M, Corizzo R, Fumarola F, Malerba D, Rashkovska A. Predictive modeling of PV energy production: how to set up the learning task for a better prediction? IEEE Trans Ind Inform. 2017;13(3):956\u201366.","journal-title":"IEEE Trans Ind Inform"},{"key":"207_CR8","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/s10618-018-0605-7","volume":"33","author":"M Ceci","year":"2019","unstructured":"Ceci M, Corizzo R, Malerba D, Rashkovska A. Spatial autocorrelation and entropy for renewable energy forecasting. Data Mining Knowl Discov. 2019;33:698\u2013729.","journal-title":"Data Mining Knowl Discov"},{"key":"207_CR9","doi-asserted-by":"publisher","first-page":"9347","DOI":"10.1109\/ACCESS.2018.2805299","volume":"6","author":"X Chen","year":"2018","unstructured":"Chen X, Cai X, Liang J, Liu Q. Ensemble learning multiple lssvr with improved harmony search algorithm for short-term traffic flow forecasting. IEEE Access. 2018;6:9347\u201357.","journal-title":"IEEE Access"},{"issue":"7","key":"207_CR10","first-page":"0179763","volume":"12","author":"B-C Liu","year":"2017","unstructured":"Liu B-C, Binaykia A, Chang P-C, Tiwari MK, Tsao C-C. Urban air quality forecasting based on multi-dimensional collaborative support vector regression (svr): a case study of beijing-tianjin-shijiazhuang. PLoS ONE. 2017;12(7):0179763.","journal-title":"PLoS ONE"},{"key":"207_CR11","doi-asserted-by":"crossref","unstructured":"Liu J, Sun L, Li Q, Ming J, Liu Y, Xiong H. Functional zone based hierarchical demand prediction for bike system expansion. In: Proceeding of ACM SIGKDD 2017. New York: ACM; 2017. p. 957\u201366.","DOI":"10.1145\/3097983.3098180"},{"key":"207_CR12","doi-asserted-by":"crossref","unstructured":"Li Y, Zheng Y, Zhang H, Chen L. Traffic prediction in a bike-sharing system. In: SIGSPATIAL. New York: ACM; 2015. p. 33.","DOI":"10.1145\/2820783.2820837"},{"issue":"1","key":"207_CR13","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s10994-016-5546-z","volume":"104","author":"ES Xioufis","year":"2016","unstructured":"Xioufis ES, Tsoumakas G, Groves W, Vlahavas IP. Multi-target regression via input space expansion: treating targets as inputs. Mach Learn. 2016;104(1):55\u201398.","journal-title":"Mach Learn"},{"key":"207_CR14","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.ecoinf.2017.12.001","volume":"43","author":"NG Dincer","year":"2018","unstructured":"Dincer NG, Akku\u015f \u00d6. A new fuzzy time series model based on robust clustering for forecasting of air pollution. Ecol Inform. 2018;43:157\u201364.","journal-title":"Ecol Inform"},{"issue":"2","key":"207_CR15","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1007\/s10618-012-0278-6","volume":"25","author":"D Stojanova","year":"2012","unstructured":"Stojanova D, Ceci M, Appice A, Dzeroski S. Network regression with predictive clustering trees. Data Mining Knowl Discov. 2012;25(2):378\u2013413.","journal-title":"Data Mining Knowl Discov"},{"key":"207_CR16","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.ins.2017.10.021","volume":"425","author":"G Pio","year":"2018","unstructured":"Pio G, Serafino F, Malerba D, Ceci M. Multi-type clustering and classification from heterogeneous networks. Inform Sci. 2018;425:107\u201326.","journal-title":"Inform Sci"},{"key":"207_CR17","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ecoinf.2012.10.006","volume":"13","author":"D Stojanova","year":"2013","unstructured":"Stojanova D, Ceci M, Appice A, Malerba D, D\u017eeroski S. Dealing with spatial autocorrelation when learning predictive clustering trees. Ecol Inform. 2013;13:22\u201339.","journal-title":"Ecol Inform"},{"key":"207_CR18","doi-asserted-by":"crossref","unstructured":"Charikar MS. Similarity estimation techniques from rounding algorithms. In: Proceeding of the 34th annual ACM symposium on theory of computing. New York: ACM; 2002. p. 380\u20138.","DOI":"10.1145\/509907.509965"},{"issue":"6191","key":"207_CR19","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1126\/science.1242072","volume":"344","author":"A Rodriguez","year":"2014","unstructured":"Rodriguez A, Laio A. Clustering by fast search and find of density peaks. Science. 2014;344(6191):1492\u20136.","journal-title":"Science"},{"issue":"5","key":"207_CR20","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell. 2002;24(5):603\u201319.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"207_CR21","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40537-017-0087-2","volume":"4","author":"C Sreedhar","year":"2017","unstructured":"Sreedhar C, Kasiviswanath N, Reddy PC. Clustering large datasets using k-means modified inter and intra clustering (km-i2c) in hadoop. J Big Data. 2017;4(1):27.","journal-title":"J Big Data"},{"issue":"1","key":"207_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s40537-016-0060-5","volume":"3","author":"H Zhang","year":"2016","unstructured":"Zhang H, Raitoharju J, Kiranyaz S, Gabbouj M. Limited random walk algorithm for big graph data clustering. J Big Data. 2016;3(1):26.","journal-title":"J Big Data"},{"issue":"1","key":"207_CR23","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s40537-015-0027-y","volume":"2","author":"A Kaur","year":"2015","unstructured":"Kaur A, Datta A. A novel algorithm for fast and scalable subspace clustering of high-dimensional data. J Big Data. 2015;2(1):17.","journal-title":"J Big Data"},{"issue":"2","key":"207_CR24","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/304181.304187","volume":"28","author":"M Ankerst","year":"1999","unstructured":"Ankerst M, Breunig MM, Kriegel H-P, Sander J. Optics: ordering points to identify the clustering structure. SIGMOD Rec. 1999;28(2):49\u201360.","journal-title":"SIGMOD Rec."},{"key":"207_CR25","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/B978-012722442-8\/50016-1","volume-title":"Proceedings 2003 VLDB Conference","author":"Charu C. Aggarwal","year":"2003","unstructured":"Aggarwal CC, Han J, Wang J, Yu PS. A framework for clustering evolving data streams. In: VLDB. 2003. p. 81\u201392."},{"issue":"1","key":"207_CR26","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.datak.2006.01.013","volume":"60","author":"D Birant","year":"2007","unstructured":"Birant D, Kut A. ST-DBSCAN: an algorithm for clustering spatial-temporal data. Data Knowl Eng. 2007;60(1):208\u201321.","journal-title":"Data Knowl Eng"},{"key":"207_CR27","doi-asserted-by":"crossref","unstructured":"Wu Y-P, Guo J-J, Zhang X-J. A linear DBSCAN algorithm based on LSH. In: International conference on machine learning and cybernetics, vol. 5. IEEE. 2007. p. 2608\u201314.","DOI":"10.1109\/ICMLC.2007.4370588"},{"key":"207_CR28","unstructured":"Berchtold S, Keim DA, Kriegel H-P. The X-tree: an index structure for high-dimensional data. In: Proceedings of VLDB \u201996, San Francisco, CA, USA. 1996. p. 28\u201339."},{"key":"207_CR29","first-page":"12","volume":"9","author":"F Huang","year":"2017","unstructured":"Huang F, Zhu Q, Zhou J, Tao J, Zhou X, Jin D, Tan X, Wang L. Research on the parallelization of the DBSCAN clustering algorithm for spatial data mining based on the Spark platform. Rem Sens. 2017;9:12.","journal-title":"Rem Sens"},{"issue":"2","key":"207_CR30","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc. 2005;67(2):301\u201320.","journal-title":"J R Stat Soc"},{"issue":"337","key":"207_CR31","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1080\/01621459.1972.10481216","volume":"67","author":"R Barlow","year":"1972","unstructured":"Barlow R, Brunk H. The isotonic regression problem and its dual. J Am Stat Assoc. 1972;67(337):140\u20137.","journal-title":"J Am Stat Assoc"},{"key":"207_CR32","first-page":"5","volume":"30","author":"C Ababei","year":"2018","unstructured":"Ababei C, Moghaddam MG. A survey of prediction and classification techniques in multicore processor systems. IEEE Trans Parallel Distrib Syst. 2018;30:5.","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"207_CR33","volume-title":"Time series analysis: forecasting and control","author":"GE Box","year":"2015","unstructured":"Box GE, Jenkins GM, Reinsel GC, Ljung GM. Time series analysis: forecasting and control. 5th ed. Oxford: Wiley; 2015.","edition":"5"},{"key":"207_CR34","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.bdr.2019.04.001","volume":"16","author":"R Corizzo","year":"2019","unstructured":"Corizzo R, Ceci M, Japkowicz N. Anomaly detection and repair for accurate predictions in geo-distributed Big Data. Big Data Res. 2019;16:18\u201335.","journal-title":"Big Data Res"},{"issue":"3","key":"207_CR35","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/j.patcog.2012.09.023","volume":"46","author":"D Kocev","year":"2013","unstructured":"Kocev D, Vens C, Struyf J, D\u017eeroski S. Tree ensembles for predicting structured outputs. Pattern Recogn. 2013;46(3):817\u201333.","journal-title":"Pattern Recogn"},{"issue":"5","key":"207_CR36","first-page":"216","volume":"5","author":"H Borchani","year":"2015","unstructured":"Borchani H, Varando G, Bielza C, Larra\u00f1aga P. A survey on multi-output regression. Wiley Interdiscip Rev. 2015;5(5):216\u201333.","journal-title":"Wiley Interdiscip Rev"},{"key":"207_CR37","doi-asserted-by":"crossref","unstructured":"Brudnak M. Vector-valued support vector regression. In: IJCNN\u201906. IEEE international joint conference on neural networks. 2006. p. 1562\u20139.","DOI":"10.1109\/IJCNN.2006.246619"},{"issue":"9","key":"207_CR38","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1016\/j.patrec.2013.01.015","volume":"34","author":"S Xu","year":"2013","unstructured":"Xu S, An X, Qiao X, Zhu L, Li L. Multi-output least-squares support vector regression machines. Pattern Recogn Lett. 2013;34(9):1078\u201384.","journal-title":"Pattern Recogn Lett"},{"key":"207_CR39","doi-asserted-by":"crossref","unstructured":"Appice A, D\u017eeroski S. Stepwise induction of multi-target model trees. In: European conference on machine learning. Berlin: Springer; 2007. p. 502\u20139.","DOI":"10.1007\/978-3-540-74958-5_46"},{"key":"207_CR40","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735\u201380.","journal-title":"Neural Comput"},{"key":"207_CR41","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I. Spark: cluster computing with working sets. In: Proceeding of HotCloud\u201910. 2010. p. 10."},{"key":"207_CR42","doi-asserted-by":"crossref","unstructured":"Ravichandran D, Pantel P, Hovy E. Randomized algorithms and NLP: using locality sensitive hash function for high speed noun clustering. In: Meeting on association for computational linguistics. ACL \u201905. 2005. p. 622\u20139.","DOI":"10.3115\/1219840.1219917"},{"key":"207_CR43","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.ins.2015.07.046","volume":"326","author":"LN Ferreira","year":"2016","unstructured":"Ferreira LN, Zhao L. Time series clustering via community detection in networks. Inform Sci. 2016;326:227\u201342.","journal-title":"Inform Sci"},{"key":"207_CR44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139924801","volume-title":"Mining of massive datasets","author":"J Leskovec","year":"2014","unstructured":"Leskovec J, Rajaraman A, Ullman JD. Mining of massive datasets. 2nd ed. New York: Cambridge University Press; 2014.","edition":"2"},{"key":"207_CR45","unstructured":"Andoni A, Indyk P, Laarhoven T, Razenshteyn I, Schmidt L. Practical and optimal lsh for angular distance. In: Proceedings of the 28th international conference on neural information processing systems, volume 1. NIPS\u201915. Cambridge: MIT Press. 2015. p. 1225\u201333."},{"key":"207_CR46","doi-asserted-by":"crossref","unstructured":"Tian X, Guo Y, Zhan J, Wang L. Towards memory and computation efficient graph processing on spark. In: International conference on Big Data (Big Data). 2017. p. 375\u201382.","DOI":"10.1109\/BigData.2017.8257948"},{"key":"207_CR47","first-page":"599","volume":"14","author":"JE Gonzalez","year":"2014","unstructured":"Gonzalez JE, Xin RS, Dave A, Crankshaw D, Franklin MJ, Stoica I. Graphx: graph processing in a distributed dataflow framework. OSDI. 2014;14:599\u2013613.","journal-title":"OSDI"},{"key":"207_CR48","doi-asserted-by":"crossref","unstructured":"Hyndman RJ, Khandakar Y, et al. Automatic time series for forecasting: the forecast package for r. Technical report. Monash University, Department of Econometrics and Business Statistics. 2007.","DOI":"10.18637\/jss.v027.i03"},{"key":"207_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13748-012-0035-5","volume":"2","author":"TH Fanaee","year":"2013","unstructured":"Fanaee TH, Gama J. Event labeling combining ensemble detectors and background knowledge. Progr Artif Intell. 2013;2:1\u201315.","journal-title":"Progr Artif Intell"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0207-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-019-0207-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0207-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T23:47:52Z","timestamp":1591055272000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-019-0207-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,3]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["207"],"URL":"https:\/\/doi.org\/10.1186\/s40537-019-0207-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,3]]},"assertion":[{"value":"18 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"43"}}