{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T04:18:54Z","timestamp":1741753134938,"version":"3.38.0"},"reference-count":25,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2019,10,24]]},"DOI":"10.3233\/ida-184199","type":"journal-article","created":{"date-parts":[[2019,10,29]],"date-time":"2019-10-29T18:32:36Z","timestamp":1572373956000},"page":"1109-1129","source":"Crossref","is-referenced-by-count":2,"title":["Facing the full model selection problem in high volume datasets employing intelligent proxy models"],"prefix":"10.1177","volume":"23","author":[{"given":"\u00c1ngel","family":"D\u00edaz-Pacheco","sequence":"first","affiliation":[]},{"given":"Carlos A.","family":"Reyes-Garcia","sequence":"additional","affiliation":[]}],"member":"179","reference":[{"key":"10.3233\/IDA-184199_ref1","doi-asserted-by":"crossref","unstructured":"F. Alenezi and S. Mohaghegh, A data-driven smart proxy model for a comprehensive reservoir simulation, in: Information Technology (Big Data Analysis) (KACSTIT), Saudi International Conference on, IEEE, 2016, pp. 1\u20136.","DOI":"10.1109\/KACSTIT.2016.7756063"},{"key":"10.3233\/IDA-184199_ref2","doi-asserted-by":"crossref","unstructured":"B. Bansal and A. Sahoo, Full model selection using bat algorithm, in: Cognitive Computing and Information Processing (CCIP), 2015 International Conference on, IEEE, 2015, pp. 1\u20134.","DOI":"10.1109\/CCIP.2015.7100693"},{"issue":"3","key":"10.3233\/IDA-184199_ref4","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/j.patcog.2009.07.006","article-title":"A multi-model selection framework for unknown and\/or evolutive misclassification cost problems","volume":"43","author":"Chatelain","year":"2010","journal-title":"Pattern Recognition"},{"key":"10.3233\/IDA-184199_ref5","doi-asserted-by":"crossref","unstructured":"I. Couckuyt, F. De Turck, T. Dhaene and D. Gorissen, Automatic surrogate model type selection during the optimization of expensive black-box problems, in: Simulation Conference (WSC), Proceedings of the 2011 Winter, IEEE, 2011, pp.\u00a04269\u20134279.","DOI":"10.1109\/WSC.2011.6148114"},{"key":"10.3233\/IDA-184199_ref6","doi-asserted-by":"crossref","unstructured":"K. Crombecq, L. De Tommasi, D. Gorissen and T. Dhaene, A novel sequential design strategy for global surrogate modeling, in: Simulation Conference (WSC), Proceedings of the 2009 Winter, IEEE, 2009, pp. 731\u2013742.","DOI":"10.1109\/WSC.2009.5429687"},{"key":"10.3233\/IDA-184199_ref7","doi-asserted-by":"crossref","unstructured":"I. Cruz-Vega, C. Alberto Reyes Garc\u00eda, P. G\u00f3mez Gil, J. Manuel Ram\u00edrez Cort\u00e9s and J. de Jes\u00fas Rangel Magdaleno, Genetic algorithms based on a granular surrogate model and fuzzy aptitude functions, in: Evolutionary Computation (CEC), 2016 IEEE Congress on, IEEE, 2016, pp. 2122\u20132128.","DOI":"10.1109\/CEC.2016.7744050"},{"issue":"1","key":"10.3233\/IDA-184199_ref8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","article-title":"Mapreduce: Simplified data processing on large clusters","volume":"51","author":"Dean","year":"2008","journal-title":"Communications of the ACM"},{"key":"10.3233\/IDA-184199_ref9","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.ins.2014.03.043","article-title":"On the use of mapreduce for imbalanced big data using random forest","volume":"285","author":"del R\u00edo","year":"2014","journal-title":"Information Sciences"},{"issue":"Feb","key":"10.3233\/IDA-184199_ref10","first-page":"405","article-title":"Particle swarm model selection","volume":"10","author":"Escalante","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-184199_ref12","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/j.petrol.2015.07.012","article-title":"Development of an adaptive surrogate model for production optimization","volume":"133","author":"Golzari","year":"2015","journal-title":"Journal of Petroleum Science and Engineering"},{"key":"10.3233\/IDA-184199_ref13","doi-asserted-by":"crossref","unstructured":"M.T. Goodrich, N. Sitchinava and Q. Zhang, Sorting, searching, and simulation in the mapreduce framework, in: International Symposium on Algorithms and Computation, Springer, 2011, pp. 374\u2013383.","DOI":"10.1007\/978-3-642-25591-5_39"},{"issue":"Sep","key":"10.3233\/IDA-184199_ref14","first-page":"2039","article-title":"Evolutionary model type selection for global surrogate modeling","volume":"10","author":"Gorissen","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-184199_ref16","doi-asserted-by":"crossref","unstructured":"M.A. Khan, M.F. Uddin and N. Gupta, Seven v\u2019s of big data understanding big data to extract value, in: Proceedings of the 2014 Zone 1 Conference of the American Society for Engineering Education, April 2014, pp. 1\u20135.","DOI":"10.1109\/ASEEZone1.2014.6820689"},{"key":"10.3233\/IDA-184199_ref19","doi-asserted-by":"crossref","unstructured":"G. Lombardi, A. Rozza, C. Ceruti, E. Casiraghi and P. Campadelli, Minimum neighbor distance estimators of intrinsic dimension, in: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, 2011, pp. 374\u2013389.","DOI":"10.1007\/978-3-642-23783-6_24"},{"key":"10.3233\/IDA-184199_ref20","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.neucom.2015.09.111","article-title":"Extreme learning surrogate models in multi-objective optimization based on decomposition","volume":"180","author":"Pavelski","year":"2016","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-184199_ref21","doi-asserted-by":"crossref","unstructured":"M. Pilat and R. Neruda, Meta-learning and model selection in multi-objective evolutionary algorithms, in: Machine Learning and Applications (ICMLA), 2012 11th International Conference on, IEEE, Vol. 1, 2012, pp. 433\u2013438.","DOI":"10.1109\/ICMLA.2012.78"},{"key":"10.3233\/IDA-184199_ref23","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.neucom.2014.05.077","article-title":"Multi-objective model type selection","volume":"146","author":"Rosales-P\u00e9rez","year":"2014","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-184199_ref24","doi-asserted-by":"crossref","unstructured":"J. S\u00e1nchez-Monedero, P.A. Guti\u00e9rrez, M. P\u00e9rez-Ortiz and C. Herv\u00e1s-Mart\u00ednez, An n-spheres based synthetic data generator for supervised classification, in: International Work-Conference on Artificial Neural Networks, Springer, 2013, pp.\u00a0613\u2013621.","DOI":"10.1007\/978-3-642-38679-4_62"},{"key":"10.3233\/IDA-184199_ref25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.strusafe.2016.05.001","article-title":"Surrogate-enhanced stochastic search algorithms to identify implicitly defined functions for reliability analysis","volume":"62","author":"Sundar","year":"2016","journal-title":"Structural Safety"},{"key":"10.3233\/IDA-184199_ref27","doi-asserted-by":"crossref","unstructured":"C. Thornton, F. Hutter, H.H. Hoos and K. Leyton-Brown, Auto-weka: Combined selection and hyperparameter optimization of classification algorithms, in: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2013, pp. 847\u2013855.","DOI":"10.1145\/2487575.2487629"},{"key":"10.3233\/IDA-184199_ref28","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.compstruc.2016.10.004","article-title":"A proper infill sampling strategy for improving the speed performance of a surrogate-assisted evolutionary algorithm","volume":"178","author":"Vincenzi","year":"2017","journal-title":"Computers & Structures"},{"issue":"1","key":"10.3233\/IDA-184199_ref29","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/TKDE.2013.109","article-title":"Data mining with big data","volume":"26","author":"Wu","year":"2014","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/IDA-184199_ref30","doi-asserted-by":"crossref","unstructured":"K. Yu, L. Ji and X. Zhang, Kernel nearest-neighbor algorithm, Neural Processing Letters 15(2) (2002), 147\u2013156.","DOI":"10.1023\/A:1015244902967"},{"key":"10.3233\/IDA-184199_ref31","doi-asserted-by":"crossref","unstructured":"T. Yu and D. Wilkinson, Coevolution of simulator proxies and sampling strategies for petroleum reservoir modeling, in: Evolutionary Computation, 2009. CEC\u201909. IEEE Congress on, IEEE, 2009, pp. 2677\u20132684.","DOI":"10.1109\/CEC.2009.4983278"},{"issue":"11","key":"10.3233\/IDA-184199_ref32","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2934664","article-title":"Apache spark: A unified engine for big data processing","volume":"59","author":"Zaharia","year":"2016","journal-title":"Communications of the ACM"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-184199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T05:55:25Z","timestamp":1741672525000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-184199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,24]]},"references-count":25,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/ida-184199","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"type":"print","value":"1088-467X"},{"type":"electronic","value":"1571-4128"}],"subject":[],"published":{"date-parts":[[2019,10,24]]}}}