Mostrar el registro sencillo del ítem

dc.contributor.authorÁlvarez Macías, José Luisspa
dc.contributor.authorMata Vázquez, Jacintospa
dc.contributor.authorRiquelme Santos, José Cristóbalspa
dc.date.accessioned2020-10-27T00:21:29Z
dc.date.available2020-10-27T00:21:29Z
dc.date.issued2002-06-01
dc.identifier.issn2539-2115
dc.identifier.issn1657-2831
dc.identifier.urihttp://hdl.handle.net/20.500.12749/9062
dc.description.abstractEn este articulo presentamos un nuevo metodología denominado OBLIC, para inducción de reglas de clasificación oblicuas no jerárquicas a partir de un conjunto de datos etiquetados. La base del método es un algoritmo evolutivo con codificación real para los individuos y basado en la estrategia de Pittsburgh. Así, cada individuo esta compuesto por un conjunto de reglas de clasificación que dividen el espacio de búsqueda en regiones para cada una de las clases del conjunto de datos. La función de bondad determina la exactitud de cada individuo mediante la exploración de estas regiones. El modelo de clasificación es deducido a partir del mejor individuo obtenido durante el proceso evolutivo. Para analizar los resultados se ofrece una comparativa entre OBLIC, C4.5 y 0C1 sobre un conjunto de bases de datos del UCI Repositorio.spa
dc.format.mimetypeapplication/pdfspa
dc.language.isospaspa
dc.publisherUniversidad Autónoma de Bucaramanga UNAB
dc.relationhttps://revistas.unab.edu.co/index.php/rcc/article/view/1105/1077
dc.relation.urihttps://revistas.unab.edu.co/index.php/rcc/article/view/1105
dc.rightsDerechos de autor 2002 Revista Colombiana de Computación
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/
dc.sourceRevista Colombiana de Computación; Vol. 3 Núm. 1 (2002): Revista Colombiana de Computación; 7-20
dc.subjectInnovaciones tecnológicas
dc.subjectCiencia de los computadores
dc.subjectDesarrollo de tecnología
dc.subjectIngeniería de sistemas
dc.subjectInvestigaciones
dc.subjectTecnologías de la información y las comunicaciones
dc.subjectTIC´s
dc.titleMétodo de inducción de reglas de clasificación oblicuas mediante un algoritmo evolutivospa
dc.title.translatedOblique classification rule induction method using an evolutionary algorithmeng
dc.type.driverinfo:eu-repo/semantics/article
dc.type.localArtículospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.subject.keywordsTechnological innovationseng
dc.subject.keywordsComputer scienceeng
dc.subject.keywordsTechnology developmenteng
dc.subject.keywordsSystems engineeringeng
dc.subject.keywordsInvestigationseng
dc.subject.keywordsInformation and communication technologieseng
dc.subject.keywordsICT'seng
dc.subject.keywordsData miningeng
dc.subject.keywordsSupervised learningeng
dc.subject.keywordsClassificationeng
dc.subject.keywordsEvolutionary algorithmseng
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga UNABspa
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.relation.references[1) D. Ackley. A Connectionist Machine for Genetic Hillclimbing. Kluver Acad. Pub. 19871
dc.relation.references(2) C.L. Blake y C.J Merz. fhttp://www.ics.uci.edu/-fmlearn/MLRepository.htmlI. Irvine, CA: University of California, Department of Information and Computer Science. 1998.
dc.relation.referencesBreiman; Friedman; Olshen y Stone. Classification and Regression Trees. Wadsworth International Group. 1984.
dc.relation.referencesM.S. Chen; J. Han y P.S. Yu. Data Mining: An Overview from Database perspective.
dc.relation.referencesK.A. De Jong. An analysis of the behavoir of a class of genetic adaptive systems. PhD thesis, University of Michigan. 1975
dc.relation.referencesK.A. De Jong. Using Genetic Algorithms for Concepts Learning. Machine Learning, 13 161-188, 1993.
dc.relation.referencesL.J. Eshelman y J.D. Schaffer. Real-Coded Genetic Algorithms and Interval Schemata. Foundations of Genetic Algorithms 2. Morgan Kaufmann Pub. 1993. Fayyad;
dc.relation.referencesL.J. Eshelman y J.D. Schaffer. Real-Coded Genetic Algorithms and Interval Schemata. Foundations of Genetic Algorithms 2. Morgan Kaufmann Pub. 1993. Fayyad;
dc.relation.referencesFayyad; Piatetsky-Shapiro y Smyth. From Data Mining to Knowledge Discovery: An Overview. Advances in Knowledge Discovery and Data Mining, 1-34, 1996.
dc.relation.references. D.E. Goldberg Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Pub. Company, inc., 1989.
dc.relation.references10) S. Hampson y D. Volper. Linear function neurons: Structure and training. Biological Cybernetics, 53, 203-217, 1986.
dc.relation.references111 J.H. Holland. Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor, MI. 1975. [
dc.relation.references12) C.Z. Janikov. A Knowleged-Intensive Genetic Algorithm for Supervised Learning. Ma-chine Learning, 13 189-228, 1993.
dc.relation.referencesJ.R. Koza. Concept Formation and Decision Thee Induction using the Genetic Program-ming Paradimg. Springer-Verlag, 1991.
dc.relation.references[14) Z. Michalewicz. Genetics Algorithms + Data Structures = Evolution Programs, Third Edition. Springer-Verlag, 1999.
dc.relation.referencesM. Mitchell. An Introduction to Genetic Algorithms. MIT Press. 1996.
dc.relation.referencesS.K. Murthy; S. Kasif y S. Salzberg. A System for Induction of Obliques Decision Tress. Journal or Artificial Intelligence Research, 2 1-32, 1994.
dc.relation.referencesJ.R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann Pub., 1993.
dc.relation.referencesJ.R. Quinlan. Improved use of continuous attributes in C4.5. Journal of Artificial Intel-ligence Research, vol. 4, pp 77-90. 1996.
dc.relation.referencesG. Syswerda. Uniform crossover in Genetic Algorithms. 3th Int. Conference on Genetic Algorithms, 2-9, 1989
dc.relation.referencesP.E. Utgoff y C.E. Brodley. An incremental method for finding multivariate splits for decision trees. 7th International Conference on Machine Learning, 58-65, 1990.
dc.relation.referencesT. Van de Merckt. NFDT: A system that learns flexible concepts based on decision trees for numerical attributes. 9th Int. Workshop on Machine Learning, pp. 322-331, 1992.
dc.relation.referencesT. Van de Merckt. Decision trees in numerical attribute spaces. 13th International Joint Conference on Artificial Intelligence, pp. 1016-1021, 1993.
dc.relation.referencesD. Whitley. A Genetic Algorithm DatoriaL Technical Report CS-93-103. Colorado State University. 1993. A.H. Wright. Genetic Algorithm for Real Parameter Optimization. Morgan Kaufmann Pub., 1991.
dc.subject.lembDesarrollo tecnológicospa
dc.subject.lembInnovaciones tecnológicasspa
dc.subject.lembCiencias de la computaciónspa
dc.subject.lembTecnologías de la información y la comunicaciónspa
dc.subject.lembInvestigaciónspa
dc.identifier.repourlrepourl:https://repository.unab.edu.co
dc.description.abstractenglishIn this article we present a new methodology called OBLIC, for the induction of non-hierarchical oblique classification rules from a set of labeled data. The basis of the method is an evolutionary algorithm with real coding for individuals and based on the Pittsburgh strategy. Thus, each individual is composed of a set of classification rules that divide the search space into regions for each of the classes in the data set. The goodness function determines the correctness of each individual by exploring these regions. The classification model is deduced from the best individual obtained during the evolutionary process. To analyze the results, a comparison between OBLIC, C4.5 and 0C1 is offered on a set of databases from the UCI Repository.eng
dc.subject.proposalMinería de datosspa
dc.subject.proposalAprendizaje supervisadospa
dc.subject.proposalClasificaciónspa
dc.subject.proposalAlgoritmos evolutivosspa
dc.type.redcolhttp://purl.org/redcol/resource_type/CJournalArticle
dc.rights.creativecommonsAttribution-NonCommercial-ShareAlike 4.0 International*


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Attribution-NonCommercial-ShareAlike 4.0 International
Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution-NonCommercial-ShareAlike 4.0 International