{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T12:37:14Z","timestamp":1740141434282,"version":"3.37.3"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2019,12,9]],"date-time":"2019-12-09T00:00:00Z","timestamp":1575849600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100010198","name":"Ministerio de Econom\u00eda, Industria y Competitividad","doi-asserted-by":"publisher","award":["DPI2016-79960-C3-2-P"],"award-info":[{"award-number":["DPI2016-79960-C3-2-P"]}],"id":[{"id":"10.13039\/501100010198","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7,24]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This paper reports the experience of using the PAELLA algorithm as a helper tool in robust regression instead of as originally intended for outlier identification and removal. This novel usage of the algorithm takes advantage of the occurrence vector calculated by the algorithm in order to strengthen the effect of the more reliable samples and lessen the impact of those that otherwise would be considered outliers. Following that aim, a series of experiments is conducted in order to learn how to better use the information contained in the occurrence vector. Using a contrively difficult artificial data set, a reference predictive model is fit using the whole raw dataset. The second experiment reports the results of fitting a similar predictive model but discarding the samples marked as outliers by PAELLA. The third experiment uses the occurrence vector provided by PAELLA in order to classify the observations in multiple bins and fit every possible model changing which bins are considered for fitting and which are discarded in that particular model. The fourth experiment introduces a sampling process before fitting in which the occurrence vector represents the likelihood of being considered in the training data set. The fifth experiment considers the sampling process as an internal step to be performed interleaved between the training epochs. The last experiment compares our approach using weighted neural networks to a state of the art method.<\/jats:p>","DOI":"10.1093\/jigpal\/jzz052","type":"journal-article","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T19:28:56Z","timestamp":1571081336000},"page":"418-429","source":"Crossref","is-referenced-by-count":0,"title":["Non-removal strategy for outliers in predictive models: The PAELLA algorithm case"],"prefix":"10.1093","volume":"28","author":[{"given":"Manuel","family":"Castej\u00f3n-limas","sequence":"first","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hector","family":"Alaiz-Moreton","sequence":"additional","affiliation":[{"name":"Department of Electrical, Systems and Automatic Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071 Le\u00f3n, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Fern\u00e1ndez-Robles","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Alfonso-Cend\u00f3n","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Camino","family":"Fern\u00e1ndez-Llamas","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"lidia","family":"S\u00e1nchez-Gonz\u00e1lez","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hilde","family":"P\u00e9rez","sequence":"additional","affiliation":[{"name":"Department of Mechanical, Informatics and Aerospace Engineering, Universidad de Le\u00f3n, Campus de Vegazana, S\/N, 24071, L\u00e9on, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,12,9]]},"reference":[{"key":"2020080108270521900_ref1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.csda.2016.07.002","article-title":"Robust methods for heteroskedastic regression","volume":"104","author":"Atkinson","year":"2016","journal-title":"Computational Statistics & Data Analysis"},{"key":"2020080108270521900_ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2017.07.018","article-title":"Neural network for regression problems with reduced training sets","volume":"95","author":"Bataineh","year":"2017","journal-title":"Neural Networks"},{"key":"2020080108270521900_ref3","doi-asserted-by":"crossref","DOI":"10.1002\/0471448354","volume-title":"Exploratory Data Mining and Data Cleaning","author":"Dasu","year":"2003"},{"key":"2020080108270521900_ref4","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.ins.2018.05.008","article-title":"An exponential-type kernel robust regression model for interval-valued variables","volume":"454\u2013455","author":"de A. Lima Neto","year":"2018","journal-title":"Information Sciences"},{"key":"2020080108270521900_ref5","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1080\/09208119608964830","article-title":"Generalization of the influence function method in mining subsidence","volume":"10","author":"Bello Garc\u00eda","year":"1996","journal-title":"International Journal of Surface Mining and Reclamation"},{"key":"2020080108270521900_ref6","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1504\/IJDMMM.2011.042936","article-title":"Development of neural network-based models to predict mechanical properties of hot dip galvanised steel coils","volume":"3","author":"Gonzalez-Marcos","year":"2011","journal-title":"International Journal of Data Mining, Modelling and Management"},{"key":"2020080108270521900_ref7","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.eswa.2018.03.022","article-title":"Robust detection of epileptic seizures based on l1-penalized robust regression of eeg signals","volume":"104","author":"Hussein","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"2020080108270521900_ref8","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1016\/j.asoc.2018.04.048","article-title":"Using robust generalized fuzzy modeling and enhanced symbolic regression to model tribological systems","volume":"69","author":"Kronberger","year":"2018","journal-title":"Applied Soft Computing"},{"key":"2020080108270521900_ref9","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/B:DAMI.0000031630.50685.7c","article-title":"Outlier detection and data cleaning in multivariate non-normal samples: the PAELLA algorithm","volume":"9","author":"Limas","year":"2004","journal-title":"Data Mining and Knowledge Discovery"},{"key":"2020080108270521900_ref10","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.knosys.2018.04.005","article-title":"Robust twin support vector regression via second-order cone programming","volume":"152","author":"L\u00f3pez","year":"2018","journal-title":"Knowledge-Based Systems"},{"key":"2020080108270521900_ref11","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1111\/j.1468-0394.1996.tb00182.x","article-title":"Importance of information pre-processing in the improvement of neural network results","volume":"13","author":"Men\u00e9ndez","year":"1996","journal-title":"Expert Systems"},{"key":"2020080108270521900_ref12","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1080\/0951192021000025698","article-title":"Intelligent methods helping the design of a manufacturing system for die extrusion rubbers","volume":"16","author":"Ordieres","year":"2003","journal-title":"International Journal of Computer Integrated Manufacturing"},{"key":"2020080108270521900_ref13","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1007\/s10845-008-0189-y","article-title":"Comparison of models created for the prediction of the mechanical properties of galvanized steel coils","volume":"21","author":"Ordieres-Mer\u00e9","year":"2010","journal-title":"Journal of Intelligent Manufacturing"},{"key":"2020080108270521900_ref14","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.isatra.2017.10.011","article-title":"Two stage neural network modelling for robust model predictive control","volume":"72","author":"Patan","year":"2018","journal-title":"ISA Transactions"},{"key":"2020080108270521900_ref15","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.neunet.2004.11.007","article-title":"TAO-robust backpropagation learning algorithm","volume":"18","author":"Pern\u00eda-Espinoza","year":"2005","journal-title":"Neural Networks"},{"key":"2020080108270521900_ref16","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","article-title":"On the momentum term in gradient descent learning algorithms","volume":"12","author":"Qian","year":"1999","journal-title":"Neural Networks"},{"key":"2020080108270521900_ref17","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.neunet.2018.02.004","article-title":"Robust latent regression with discriminative regularization by leveraging auxiliary knowledge","volume":"101","author":"Tao","year":"2018","journal-title":"Neural Networks"},{"key":"2020080108270521900_ref18","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.patcog.2018.04.005","article-title":"Robust regression for image binarization under heavy noise and nonuniform background","volume":"81","author":"Vo","year":"2018","journal-title":"Pattern Recognition"},{"key":"2020080108270521900_ref19","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/0003-2670(95)00552-8","article-title":"Neural networks with robust backpropagation learning algorithm","volume":"322","author":"Walczak","year":"1996","journal-title":"Analytica Chimica Acta"},{"key":"2020080108270521900_ref20","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.eswa.2017.01.054","article-title":"Composite quantile regression neural network with applications","volume":"76","author":"Xu","year":"2017","journal-title":"Expert Systems with Applications"}],"container-title":["Logic Journal of the IGPL"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jigpal\/article-pdf\/28\/4\/418\/33554795\/jzz052.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jigpal\/article-pdf\/28\/4\/418\/33554795\/jzz052.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T12:27:30Z","timestamp":1596284850000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jigpal\/article\/28\/4\/418\/5670471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,9]]},"references-count":20,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2019,12,9]]},"published-print":{"date-parts":[[2020,7,24]]}},"URL":"https:\/\/doi.org\/10.1093\/jigpal\/jzz052","relation":{},"ISSN":["1367-0751","1368-9894"],"issn-type":[{"type":"print","value":"1367-0751"},{"type":"electronic","value":"1368-9894"}],"subject":[],"published-other":{"date-parts":[[2020,8]]},"published":{"date-parts":[[2019,12,9]]}}}