{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T14:39:56Z","timestamp":1771684796206,"version":"3.50.1"},"reference-count":24,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,12,16]]},"abstract":"<jats:p>Neural networks have been successfully applied for modeling time series. However, the results of long-term prediction are not satisfied. In this paper, the modified Meta-Learning is applied to the neural model. The normal Meta-Learning is modified by time-varying learning rates and adding a momentum term to improve convergence speed and robustness property. The stability of the learning process is proven. Finally, two experiments are presented to evaluate the proposed method. The first one shows an improvement in earthquakes prediction in the long-term, and the second one is a classical Benchmark problem. In both experiments, the modified Meta-Learning technique minimizes remarkably the mean square error index.<\/jats:p>","DOI":"10.3233\/jifs-210173","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T12:43:46Z","timestamp":1634647426000},"page":"6375-6388","source":"Crossref","is-referenced-by-count":1,"title":["Neural networks for long-term earthquake prediction using modified meta-learning"],"prefix":"10.1177","volume":"41","author":[{"given":"Mario","family":"Maya","sequence":"first","affiliation":[{"name":"Departamento de Control Automatico CINVESTAV-IPN (National Polytechnic Institute) Mexico City, Mexico"}]},{"given":"Wen","family":"Yu","sequence":"additional","affiliation":[{"name":"Departamento de Control Automatico CINVESTAV-IPN (National Polytechnic Institute) Mexico City, Mexico"}]},{"given":"Luciano","family":"Telesca","sequence":"additional","affiliation":[{"name":"Institute of Methodologies for Environmental Analysis, National Research Council, Tito (PZ), Italy"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-210173_ref1","unstructured":"Chatfield C. , The analysis of time series: an introduction, Florida, US: CRC Press, 2004."},{"key":"10.3233\/JIFS-210173_ref8","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.eswa.2015.10.021","article-title":"A recommendation system formeta-modeling: A meta-learning based approach","volume":"46","author":"Cui","year":"2016","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-210173_ref9","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.ins.2015.09.048","article-title":"Randomized algorithms for nonlinear systemidentification with deep learning modification","volume":"364\u2013365","author":"de la Rosa","year":"2016","journal-title":"Information Sciences"},{"issue":"13","key":"10.3233\/JIFS-210173_ref10","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.ifacol.2018.07.326","article-title":"Non-linear system modeling using LSTM neuralnetworks","volume":"51","author":"Gonzalez","year":"2018","journal-title":"IFAC-PapersOnLine"},{"issue":"5","key":"10.3233\/JIFS-210173_ref11","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1142\/S0129065710002516","article-title":"Automated Nonlinear System Modeling with MultipleFuzzy Neural Networks and Kernel Smoothing","volume":"20","author":"Yu","year":"2010","journal-title":"InternationalJournal of Neural Systems"},{"key":"10.3233\/JIFS-210173_ref13","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1023\/A:1019956318069","article-title":"A perspective view and survey ofmeta-learning","volume":"18","author":"Vilalta","year":"2002","journal-title":"Artif Intell Rev"},{"key":"10.3233\/JIFS-210173_ref14","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1111\/j.2044-8279.1985.tb02625.x","article-title":"The role of meta-learning in study process","volume":"55","author":"Biggs","year":"1985","journal-title":"Br JEduc Psychol"},{"key":"10.3233\/JIFS-210173_ref17","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.ins.2019.06.005","article-title":"A meta-learning recommender system for hyperparametertuning: Predicting when tuning improves SVM classifiers","volume":"501","author":"Mantovani","year":"2019","journal-title":"Information Sciences"},{"key":"10.3233\/JIFS-210173_ref18","unstructured":"Gupta A. , et al., Meta-Reinforcement Learning of Structured Exploration Strategies, NIPS, 2018."},{"issue":"10-12","key":"10.3233\/JIFS-210173_ref19","doi-asserted-by":"crossref","first-page":"2006","DOI":"10.1016\/j.neucom.2009.09.020","article-title":"Meta-learning for time series forecastingand forecast combination","volume":"73","author":"Lemke","year":"2010","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-210173_ref23","doi-asserted-by":"crossref","unstructured":"Brazdil P. , Giraud-Carrier C. and Soares C. , Vilalta R Metalearning: applications to data mining, Springer, Berlin, (2009).","DOI":"10.1007\/978-3-540-73263-1"},{"key":"10.3233\/JIFS-210173_ref25","doi-asserted-by":"crossref","unstructured":"Yu W. and Li X. , Discrete-time neuro identification without robustmodification, IEE Proc-Control Theory Appl Col 150(3) (2003).","DOI":"10.1049\/ip-cta:20030204"},{"key":"10.3233\/JIFS-210173_ref26","doi-asserted-by":"crossref","unstructured":"Sontag E.D. , Input to State Stability: Basic Concepts and Results, In: P. Nistri, G. Stefani, (eds) Nonlinear and Optimal Control Theory, Lecture Notes in Mathematics, vol. 1932. Springer, Berlin, Heidelberg, 2008.","DOI":"10.1007\/978-3-540-77653-6_3"},{"key":"10.3233\/JIFS-210173_ref27","doi-asserted-by":"crossref","unstructured":"Box G. , Jenkins G. and Reinsel G. , Time Series Analysis: Forecasting and Control, 4th Ed, Wiley, 2008.","DOI":"10.1002\/9781118619193"},{"key":"10.3233\/JIFS-210173_ref29","unstructured":"Schoukens J. , Suykens J. and Ljung L. , Wiener-Hammerstein benchmark, 15th IFAC Symposiumon System Identification, Saint-Malo, France, 2009."},{"issue":"1","key":"10.3233\/JIFS-210173_ref31","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.ejor.2020.05.038","article-title":"Retail sales forecasting with meta-learning","volume":"288","author":"Ma","year":"2020","journal-title":"European Journal of Operational Research"},{"key":"10.3233\/JIFS-210173_ref32","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1007\/BF02551274","article-title":"Aproximation by superposition of sigmoidal activationfunction","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math Control Signals Syst"},{"key":"10.3233\/JIFS-210173_ref33","doi-asserted-by":"crossref","unstructured":"Narendra K.S. and Parthasarathy K. , Gradient methods for optimization of dynamical systems containing neural networks, IEEE Transactions of Neural Networks, 1991, pp. 252\u2013262.","DOI":"10.1109\/72.80336"},{"issue":"2","key":"10.3233\/JIFS-210173_ref34","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/S0005-1098(01)00028-0","article-title":"Input-to-State Stability for Discrete-TimeNonlinear Systems","volume":"37","author":"Jiang","year":"2001","journal-title":"Automatica"},{"issue":"1","key":"10.3233\/JIFS-210173_ref35","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/s11069-016-2579-3","article-title":"Earthquake magnitude prediction in Hindukush region using machinelearning techniques","volume":"85","author":"Asim","year":"2017","journal-title":"Natural Hazards"},{"issue":"5","key":"10.3233\/JIFS-210173_ref36","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1007\/s00521-015-2121-7","article-title":"Medium\u2013large earthquake magnitude prediction in Tokyo with artificial neural networks","volume":"28","author":"Asencio-Cort\u00e9s","year":"2017","journal-title":"Neural Computing andApplications"},{"issue":"2","key":"10.3233\/JIFS-210173_ref37","first-page":"159","article-title":"Earthquake magnitude prediction based onartificial neural networks: A survey","volume":"7","author":"Florido","year":"2016","journal-title":"Croatian Operational Research Review"},{"issue":"11","key":"10.3233\/JIFS-210173_ref38","doi-asserted-by":"crossref","first-page":"3456","DOI":"10.4236\/cs.2016.711294","article-title":"A BP artificial neural network modelfor earthquake magnitude prediction in Himalayas, India","volume":"7","author":"Narayanakumar","year":"2016","journal-title":"Circuits Syst"},{"key":"10.3233\/JIFS-210173_ref40","doi-asserted-by":"crossref","unstructured":"Maya M. and Yu W. , Short-term prediction of the earthquake through Neural Networks and Meta-Learning, 16th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE19), Mexico City, Mexico, 2019.","DOI":"10.1109\/ICEEE.2019.8884562"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-210173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T01:49:48Z","timestamp":1769996988000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-210173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,16]]},"references-count":24,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jifs-210173","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,16]]}}}