{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:31:13Z","timestamp":1777494673067,"version":"3.51.4"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"European Union through the Projects Capacity for Rail\u2014C4R","award":["605650"],"award-info":[{"award-number":["605650"]}]},{"name":"Innovative Intelligent Rail\u2014In2Rail","award":["635900"],"award-info":[{"award-number":["635900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/tsmc.2017.2693209","type":"journal-article","created":{"date-parts":[[2017,5,2]],"date-time":"2017-05-02T18:21:26Z","timestamp":1493749286000},"page":"2754-2767","source":"Crossref","is-referenced-by-count":101,"title":["Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8445-395X","authenticated-orcid":false,"given":"Luca","family":"Oneto","sequence":"first","affiliation":[]},{"given":"Emanuele","family":"Fumeo","sequence":"additional","affiliation":[]},{"given":"Giorgio","family":"Clerico","sequence":"additional","affiliation":[]},{"given":"Renzo","family":"Canepa","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Papa","sequence":"additional","affiliation":[]},{"given":"Carlo","family":"Dambra","sequence":"additional","affiliation":[]},{"given":"Nadia","family":"Mazzino","sequence":"additional","affiliation":[]},{"given":"Davide","family":"Anguita","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2317880"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.910738"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2347136"},{"key":"ref32","author":"kecman","year":"2014","journal-title":"Models for Predictive Railway Traffic Management"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5625081"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2010.01.002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2617622"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2034742"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","author":"bishop","year":"1995","journal-title":"Neural Networks for Pattern Recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2168604"},{"key":"ref28","first-page":"100","article-title":"Stochastic delay prediction in large train networks","volume":"20","author":"berger","year":"2011","journal-title":"Proc 11th Workshop on Algorithmic Approaches for Transportation Modelling Optimization and Systems OASIcs—OpenAccess Series in Informatics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2012.12.005"},{"key":"ref29","first-page":"307","article-title":"Improving arrival time prediction of Thailand’s passenger trains using historical travel times","author":"pongnumkul","year":"2014","journal-title":"Proc Int Joint Conf Comput Sci Softw Eng"},{"key":"ref20","first-page":"573","article-title":"K-medoids clustering based on MapReduce and optimal search of medoids","author":"zhu","year":"2014","journal-title":"Proc the Conf on Comp Sci Educ"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/978-3-642-05465-5_10","article-title":"Efficient timetable information in the presence of delays","author":"m\u00fcller-hannemann","year":"2009","journal-title":"Proc Robust Online Large-Scale Optim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1049\/ic.2012.0048"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.32.4.380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2506540"},{"key":"ref101","first-page":"435","article-title":"PAC-Bayesian bounds based on the Rényi divergence","author":"b\u00e9gin","year":"2016","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2301140"},{"key":"ref100","first-page":"787","article-title":"Risk bounds for the majority vote: From a PAC-Bayesian analysis to a learning algorithm","volume":"16","author":"germain","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10696-013-9187-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.875977"},{"key":"ref51","first-page":"985","article-title":"Extreme learning machine: A new learning scheme of feedforward neural networks","author":"huang","year":"2004","journal-title":"Proc IEEE Int Joint Conf Neural Netw"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.110"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2424995"},{"key":"ref57","first-page":"31","article-title":"Representational learning with ELMs for big data","volume":"28","author":"kasun","year":"2013","journal-title":"IEEE Intell Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2363492"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2623634"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2013.2283741"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.04.013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957743"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2388435"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1061\/9780784413753.172"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.07.025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2292712"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2014.7004429"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-015-9333-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-014-9255-2"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/72.554194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.02.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2005.12.126"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.10.001"},{"key":"ref73","first-page":"117","article-title":"Preserving statistical validity in adaptive data analysis","author":"dwork","year":"2015","journal-title":"Proc Annu ACM Symp Theory Comput"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"dwork","year":"2014","journal-title":"Found Trends Theor Comput Sci"},{"key":"ref71","first-page":"2341","article-title":"Generalization in adaptive data analysis and holdout reuse","author":"dwork","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref70","first-page":"117","article-title":"Preserving statistical validity in adaptive data analysis","author":"dwork","year":"2015","journal-title":"Proc 47th Annu ACM Symp Theory Comput"},{"key":"ref76","year":"2016","journal-title":"Gruppo Ferrovie Dello Stato Italiane"},{"key":"ref77","year":"2016","journal-title":"Weather Data of Regione Liguria"},{"key":"ref74","article-title":"Generalization in adaptive data analysis and holdout reuse","author":"dwork","year":"2015","journal-title":"arXiv Preprint arXiv 1506 02629 (v2)"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa9375"},{"key":"ref78","year":"2016","journal-title":"Weather Data of Regione Lombardia"},{"key":"ref79","author":"takens","year":"1981","journal-title":"Detecting strange attractors in turbulence"},{"key":"ref60","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc USENIX\/ACM Symp Netw Syst Design Implement"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.procs.2015.07.286","article-title":"Big data analytics in the cloud: Spark on Hadoop vs MPI\/OpenMP on Beowulf","volume":"53","author":"reyes-ortiz","year":"2015","journal-title":"Proc Journal of Computer Science"},{"key":"ref61","first-page":"1235","article-title":"MLlib: Machine learning in apache spark","volume":"17","author":"meng","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref64","author":"white","year":"2012","journal-title":"Hadoop The Definitive Guide"},{"key":"ref65","year":"2016","journal-title":"Google Compute Engine"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.57"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013999503812"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033354"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2013.6691771"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972788.54"},{"key":"ref1","first-page":"437","article-title":"Condition based maintenance in railway transportation systems based on big data streaming analysis","author":"fumeo","year":"2015","journal-title":"Proc INNS Big Data Conf"},{"key":"ref109","first-page":"1006","article-title":"The ladder: A reliable leaderboard for machine learning competitions","author":"blum","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref95","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"bousquet","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/BF00935752"},{"key":"ref94","first-page":"529","article-title":"Computable shell decomposition bounds","volume":"5","author":"langford","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref107","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","author":"bergstra","year":"2011","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993593"},{"key":"ref106","first-page":"2113","article-title":"Gradient-based hyperparameter optimization through reversible learning","author":"maclaurin","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1214\/009053605000000282"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015187"},{"key":"ref91","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref104","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref90","author":"langford","year":"2005","journal-title":"Clever Methods of Overfitting"},{"key":"ref103","author":"catoni","year":"2007","journal-title":"Pac-Bayesian Supervised Classification The Thermodynamics of Statistical Learning"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.2307\/2526438"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.55"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2012.10.013"},{"key":"ref99","first-page":"109","article-title":"PAC-Bayes-empirical-Bernstein inequality","author":"tolstikhin","year":"2013","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1038\/nature02341"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2361857"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2014.7004436"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/NBiS.2015.47"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2387883"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957803"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2204047"},{"key":"ref16","first-page":"59","article-title":"An improved algorithm for high speed train’s maintenance data mining based on MapReduce","author":"bin","year":"2015","journal-title":"Proc Int Conf Cloud Comput Big Data"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2015.120"},{"key":"ref81","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2015.0038"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2235089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICITBS.2015.178"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2040176"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.45.712"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2202401"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280633"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2016.2572540"},{"key":"ref87","first-page":"381","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00010-0"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/8038140\/07917288.pdf?arnumber=7917288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:19:31Z","timestamp":1750216771000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7917288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":110,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2017.2693209","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10]]}}}