发布求助
文献互助 智能选刊 最新文献

Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence最新文献

筛选
英文 中文
Rough Sets Divisibles Basados en Clustering Jerárquico
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-12-12 DOI: 10.4114/IA.V10I31.939
R. López, Miguel Angel Sanz Bobi
{"title":"Rough Sets Divisibles Basados en Clustering Jerárquico","authors":"R. López, Miguel Angel Sanz Bobi","doi":"10.4114/IA.V10I31.939","DOIUrl":"https://doi.org/10.4114/IA.V10I31.939","url":null,"abstract":"Desde que la teoria de rough sets fue propuesta por Pawlak en 1982, se ha aplicado en la extraccion de conocimiento de bases de datos de todo tipo. Sin embargo, se han detectado ciertos inconvenientes en casos complejos y de gran inconsistencia, como su falta de flexibilidad y su excesiva dependencia respecto a la discretizacion inicial de los atributos. Para superarlos aqui se propone una nueva tecnica hibrida, denominada rough sets divisibles, que combina rough sets de precision variable con clustering jerarquico y perceptrones. Asi se pretende analizar las clases de equivalencia que mediante rough sets no generan ninguna regla con objeto de ver si mediante alguna division se puede obtener alguna nueva regla cierta. Ademas, se incorpora el concepto de centro de clase de equivalencia, util en la asignacion de decisiones a ejemplos que no caen en ninguna region positiva y para la division de clases de equivalencia. Las comparaciones del metodo de rough sets clasico y el de los rough sets divisibles ante varios casos ejemplo muestran que este ultimo ofrece mejores resultados en la mayoria de los tests realizados.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84866884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Un modelo de minería de consultas para el diseño del contenido y la estructura de un sitio Web 用于网站内容和结构设计的查询挖掘模型
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-12-11 DOI: 10.4114/IA.V10I29.881
Ricardo Baeza-Yates, B. Poblete
{"title":"Un modelo de minería de consultas para el diseño del contenido y la estructura de un sitio Web","authors":"Ricardo Baeza-Yates, B. Poblete","doi":"10.4114/IA.V10I29.881","DOIUrl":"https://doi.org/10.4114/IA.V10I29.881","url":null,"abstract":"In this article we present a model for mining queries in Web sites. This model relates the information provided by queries found in a site, with the site's usage, content and structure. The main goal of our model is to discover in simple way, valuable information on how to improve the structure and content of the site, allowing the site to become more intuitive and adequate to the needs of its users. This model proposes the analysis of different types of queries registered in the usage logs of site, such as queries sent by users in the site's internal search engine and queries submitted in global Web search engines, that lead to documents in the site. These queries provide useful information about the topics that interest users visiting a Web site, and their browsing patterns indicate if the documents found in the site were satisfactory to the users needs. This model additionally proposes a visual validation of the hierarchic organization of the site, given by links between documents and their contents.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85481125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
La Técnica Mimética en Ausencia de Datos Originales: Aprendizaje y Revisión de Modelos 缺乏原始数据的模拟技术:学习和模型回顾
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-12-11 DOI: 10.4114/IA.V10I29.878
M. Quintana, José Hernandez Orallo, Ricardo Blanco Vega
{"title":"La Técnica Mimética en Ausencia de Datos Originales: Aprendizaje y Revisión de Modelos","authors":"M. Quintana, José Hernandez Orallo, Ricardo Blanco Vega","doi":"10.4114/IA.V10I29.878","DOIUrl":"https://doi.org/10.4114/IA.V10I29.878","url":null,"abstract":"The mimetic technique (or Multiple Combined Models, CMM) basically consists of using a generally accurate but incomprehensible model as an oracle to generate and label a random data set. This dataset is used, along with the original training data, to train a second comprehensible model, known as the mimetic model. This technique has been used to provide understandability to black box models without considerably sacrificing their accuracy. In this work we study the mimetic application in a scenario in which the original training data is not available. In this context we first determine the optimal size of the random data set, according to the minimum message length principle (MML). This result can be used in knowledge acquisition for expert systems. Secondly we apply the mimetic technique to model revision and show that in some change situations the mimetic model can be used as a transition model between the original model and the new model.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72384917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Sistemas multiclasificadores y de aprendizaje por capas basados en CIDIM 基于CIDIM的多分类和分层学习系统
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-12-11 DOI: 10.4114/IA.V10I29.877
Gonzalo Ramos Jimenez, J. C. Ávila, Rafael Morales Bueno
{"title":"Sistemas multiclasificadores y de aprendizaje por capas basados en CIDIM","authors":"Gonzalo Ramos Jimenez, J. C. Ávila, Rafael Morales Bueno","doi":"10.4114/IA.V10I29.877","DOIUrl":"https://doi.org/10.4114/IA.V10I29.877","url":null,"abstract":"In this paper we present two multiple classifier systems based on CIDIM. We also describe a layered learning approach that we have particularized using CIDIM as the basic classifier. CIDIM (Control of Induction by sample Division Method) is an algorithm that have been developed to induce accurate and small decision trees and to do this, it tries to reduce the overfitting using a local control of induction. The multiple classifier systems that we present (M-CIDIM and E-CIDIM) take advantage of the characteristics of CIDIM, but the approaches that have been developed can be extended to any other algorithm that shares the same characteristics.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74090765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Agrupamiento de Documentos Textualesmediante Métodos Concatenados
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-12-11 DOI: 10.4114/IA.V10I30.945
Leticia Arco, R. Bello, J. M. Mederos, Yoisy Pérez
{"title":"Agrupamiento de Documentos Textualesmediante Métodos Concatenados","authors":"Leticia Arco, R. Bello, J. M. Mederos, Yoisy Pérez","doi":"10.4114/IA.V10I30.945","DOIUrl":"https://doi.org/10.4114/IA.V10I30.945","url":null,"abstract":"Este trabajo tiene como objetivo mostrar una propuesta de agrupamiento de corpus textuales mediante metodos concatenados y su evaluacion a partir de resultados experimentales. Los algoritmos incluidos son Extended Star, SKWIC y Fuzzy SKWIC. El algoritmo Extended Star es considerado un metodo interno, mientras que los algoritmos SKWIC y Fuzzy SKWIC constituyen los dos metodos exteriores en las dos variantes de concatenacion propuestas: Extended Star SKWIC y Extended Star Fuzzy SKWIC. El primer metodo concatenado emplea una tecnica de agrupamiento dura y determinista y el segundo es un metodo borroso. Es ventajoso usar estos metodos concatenados principalmente cuando se desean realizar procesamientos posteriores a los grupos de documentos creados y cuando no se tiene un conocimiento previo del dominio. Finalmente, se muestra la viabilidad de los metodos concatenados propuestos a partir de la aplicacion, a la herramienta Corpus Miner que soporta dichos metodos, de un caso de estudio construido a partir de una coleccion de la agencia de noticias Reuters. Se evaluo la propuesta utilizando pruebas estadisticas no parametricas y se demostro que las variantes concatenadas superan los resultados del agrupamiento respecto a los algoritmos originales.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81810646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
El Efecto Baldwin en la Interrelación entre Evolución y Aprendizaje 进化与学习相互关系中的鲍德温效应
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-04-05 DOI: 10.4114/IA.V9I27.850
J. Reyes
{"title":"El Efecto Baldwin en la Interrelación entre Evolución y Aprendizaje","authors":"J. Reyes","doi":"10.4114/IA.V9I27.850","DOIUrl":"https://doi.org/10.4114/IA.V9I27.850","url":null,"abstract":"En este articulo se realiza una sintesis y un analisis de los trabajos mas relevantes en el estudio del Efecto Baldwin en la interrelacion entre evolucion y aprendizaje. Se explican las posibilidades en esa interrelacion, centrandose en los trabajos de demostracion en el campo computacional del Efecto Baldwin o asimilacion genotipica en tiempo evolutivo de los caracteres adquiridos en tiempo de vida. La mayor parte de los trabajos en la bibliografia cientifica del tema se centran en la capacidad de suavizacion de la superficie de busqueda al anadir el aprendizaje en cada individuo de la poblacion genetica, por lo que en este articulo se hace enfasis en el aspecto de asimilacion genetica que aparece siempre que el aprendizaje conlleve un coste en calidad asociado. Se comenta ademas el uso del Efecto Baldwin en la evolucion de controladores en robotica autonoma, usando aprendizaje conexionista y por refuerzo en controladores neuronales y proponiendo medidas cuantitativas de la asimilacion genotipica producida al actuar el efecto Baldwin.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74374362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Conceptos y Técnicas de Estereovisión por Computador
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-04-05 DOI: 10.4114/IA.V9I27.851
José M. López-Valles, Antonio Fernández-Caballero, M. Fernández, Politecnica de Cuenca
{"title":"Conceptos y Técnicas de Estereovisión por Computador","authors":"José M. López-Valles, Antonio Fernández-Caballero, M. Fernández, Politecnica de Cuenca","doi":"10.4114/IA.V9I27.851","DOIUrl":"https://doi.org/10.4114/IA.V9I27.851","url":null,"abstract":"La extraccion de la estructura tridimensional de una escena a partir de imagenes estereoscopicas es un problema que ha sido estudiado en las ultimas decadas por la comunidad de vision por computador. Los primeros trabajos estaban enfocados hacia los fundamentos de la correspondencia entre las imagenes y la geometria de la estereoscopia. La investigacion ha madurado significativamente a traves del tiempo y son muchos los avances que siguen produciendose en estereovision computacional, lo que ha permitido que la estereoscopia pueda ser aplicada a nuevos problemas. Este articulo presenta una panoramica general de los principales conceptos y tecnicas de estereovision por computador. Se incide fundamentalmente en el analisis geometrico y la calibracion en estereovision, en los principales retos que supone el problema de la correspondencia, asi como en las principales tecnicas usadas en vivion estereo por computador.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75280090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Aprendizaje automatico de programas logico-funcionales *** 逻辑功能程序的自动学习***
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-01-13 DOI: 10.4114/IA.V4I11.688
César Ferri Ramírez, José Hernandez Orallo, M. Quintana
{"title":"Aprendizaje automatico de programas logico-funcionales ***","authors":"César Ferri Ramírez, José Hernandez Orallo, M. Quintana","doi":"10.4114/IA.V4I11.688","DOIUrl":"https://doi.org/10.4114/IA.V4I11.688","url":null,"abstract":"En este trabajo se presenta un sistema para el aprendizaje de programas \u0000logico-funcionales a partir de ejemplos y de conocimiento previo. \u0000Esto supone una extension de la programacion logica inductiva. \u0000El marco se basa en dos operadores fundamentales, la generalizacion \u0000consistente restrictiva, inspirado en los sistemas de aprendizaje \u0000basados en generalizacion, y el narrowing inverso, inspirado en la \u0000inversion del operador deductivo del lenguaje de representacion, \u0000en este caso, los lenguajes logico-funcionales. Dichos operadores \u0000se combinan en un algoritmo con un caracter marcadamente evolutivo \u0000en el que dos niveles de poblaciones (de reglas y de programas sobre \u0000estas) se van modificando y combinando hasta llegar a una solucion \u0000satisfactoria segun el criterio de seleccion de hipotesis. El resultado \u0000es el sistema FLIP, un sistema de aprendizaje sobre un lenguaje \u0000de representacion universal de facil inteligibilidad que permite, entre \u0000otros, la induccion con o sin conocimiento previo de programas recursivos, \u0000de arboles de decision, y de clasificadores sobre datos no estructurados.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88198785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Minería y visualización de datos del mercado eléctrico español 西班牙电力市场数据的挖掘和可视化
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2006-01-05 DOI: 10.4114/IA.V10I29.880
Eugenio Francisco Sánchez Ubeda, A. Muñoz, J. Villar
{"title":"Minería y visualización de datos del mercado eléctrico español","authors":"Eugenio Francisco Sánchez Ubeda, A. Muñoz, J. Villar","doi":"10.4114/IA.V10I29.880","DOIUrl":"https://doi.org/10.4114/IA.V10I29.880","url":null,"abstract":"The available amount of data for the companies that operate in the Spanish electricity market is very high, and contains information which is potentially very valuable. The knowledge about the strategic behavior of a market agent competitors can be obtained from the supply curves, given a competitive advantage to the agent for its operation. In this article a methodology for the analysis of the supply curves based on Data Mining techniques is proposed, including many examples showing the type of knowledge that can be obtained from the available data. This approach, combined with a complete information system, is being used successfully for many years in Endesa.","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2006-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78929216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Simposio Argentino de Inteligencia Artificial
IF 2.3
Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence Pub Date : 2005-01-01 DOI: 10.4114/IA.V9126.843
Alejandro Zunino
{"title":"Simposio Argentino de Inteligencia Artificial","authors":"Alejandro Zunino","doi":"10.4114/IA.V9126.843","DOIUrl":"https://doi.org/10.4114/IA.V9126.843","url":null,"abstract":"","PeriodicalId":43470,"journal":{"name":"Inteligencia Artificial-Iberoamerical Journal of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":2.3,"publicationDate":"2005-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85114248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信