1996, Vol. III, Núm. 3ESTYLF'95http://hdl.handle.net/2099/20622021-10-28T00:02:39Z2021-10-28T00:02:39ZEditorial [5th. Spanish Congress on Fuzzy Logic and Technology: selection of extended versions.]Marín, RoqueBarro Ameneiro, D. Senénhttp://hdl.handle.net/2099/36742017-02-07T16:04:32Z2007-10-15T10:55:41ZEditorial [5th. Spanish Congress on Fuzzy Logic and Technology: selection of extended versions.]
Marín, Roque; Barro Ameneiro, D. Senén
2007-10-15T10:55:41ZMarín, RoqueBarro Ameneiro, D. SenénLearning under hardware restrictions in CMOS fuzzy controlers able to extract rules from examplesVidal Verdú, FernandoNavas González, RafaelRodríguez-Vázquez, Ángelhttp://hdl.handle.net/2099/34812017-02-07T16:04:31Z2007-09-13T12:52:04ZLearning under hardware restrictions in CMOS fuzzy controlers able to extract rules from examples
Vidal Verdú, Fernando; Navas González, Rafael; Rodríguez-Vázquez, Ángel
Fuzzy controllers are able to incorporate knowledge expressed in if-then rules. These rules are given by experts or skilful operators. Problems arise when there are not experts or/and rules are not easy to find. Authors' proposal consists in an analog fuzzy controller which accepts structured
language as well as input/output data pairs, thus rules can be extracted or tuned from human or software controller operation. Learning from data pairs has to be carried out under hardware restrictions in linearity, range and resolution. In this paper, modelling of building blocks arranged in a neuro-fuzzy architecture is made and issues related to on-chip learning are
discussed. Computer simulations show that learning is possible for resolutions
up to 6 bits, affordable with the cheapest VLSI technologies.
2007-09-13T12:52:04ZVidal Verdú, FernandoNavas González, RafaelRodríguez-Vázquez, ÁngelFuzzy controllers are able to incorporate knowledge expressed in if-then rules. These rules are given by experts or skilful operators. Problems arise when there are not experts or/and rules are not easy to find. Authors' proposal consists in an analog fuzzy controller which accepts structured
language as well as input/output data pairs, thus rules can be extracted or tuned from human or software controller operation. Learning from data pairs has to be carried out under hardware restrictions in linearity, range and resolution. In this paper, modelling of building blocks arranged in a neuro-fuzzy architecture is made and issues related to on-chip learning are
discussed. Computer simulations show that learning is possible for resolutions
up to 6 bits, affordable with the cheapest VLSI technologies.Automatic synthesis of fuzzy logic controlersBarriga Barrios, ÁngelSánchez Solano, SantiagoJiménez, Carlos J.Galán, D.López, Diego R.http://hdl.handle.net/2099/34802017-02-07T16:04:31Z2007-09-13T12:17:27ZAutomatic synthesis of fuzzy logic controlers
Barriga Barrios, Ángel; Sánchez Solano, Santiago; Jiménez, Carlos J.; Galán, D.; López, Diego R.
This paper describes a design environment for the hardware realizations of fuzzy controllers which includes a set of CAD tools to ease the description, verification and synthesis of this kind of systems. Special emphasis is focused on the use of a standard hardware description language (VHDL) and compatibility with other integrated circuits design tools.
2007-09-13T12:17:27ZBarriga Barrios, ÁngelSánchez Solano, SantiagoJiménez, Carlos J.Galán, D.López, Diego R.This paper describes a design environment for the hardware realizations of fuzzy controllers which includes a set of CAD tools to ease the description, verification and synthesis of this kind of systems. Special emphasis is focused on the use of a standard hardware description language (VHDL) and compatibility with other integrated circuits design tools.Client/server architecture for fuzzy relational databasesMedina Rodríguez, Juan MiguelPons Capote, OlgaVila Miranda, María AmparoCubero Talavera, Juan Carloshttp://hdl.handle.net/2099/34792017-02-07T16:04:31Z2007-09-13T11:37:46ZClient/server architecture for fuzzy relational databases
Medina Rodríguez, Juan Miguel; Pons Capote, Olga; Vila Miranda, María Amparo; Cubero Talavera, Juan Carlos
This paper shows a FRDBMS architecture whose main characteristics are: 1) it is implemented entirely on classical RDBMS just using the resources provided by them, 2) it preserves all the operations and qualities of the host RDBMS and gives them more
power adding new capabilities to deal with "fuzzy" information and 3) it provides
a frame to develop applications which exploit fuzzy information.
2007-09-13T11:37:46ZMedina Rodríguez, Juan MiguelPons Capote, OlgaVila Miranda, María AmparoCubero Talavera, Juan CarlosThis paper shows a FRDBMS architecture whose main characteristics are: 1) it is implemented entirely on classical RDBMS just using the resources provided by them, 2) it preserves all the operations and qualities of the host RDBMS and gives them more
power adding new capabilities to deal with "fuzzy" information and 3) it provides
a frame to develop applications which exploit fuzzy information.Contributions to the symbolic processing of segments in computer visionCabrera Gámez, JuanHernández Tejara, Francisco MarioFalcón Martel, AntonioMéndez, J.http://hdl.handle.net/2099/34782017-02-07T16:04:31Z2007-09-13T11:16:08ZContributions to the symbolic processing of segments in computer vision
Cabrera Gámez, Juan; Hernández Tejara, Francisco Mario; Falcón Martel, Antonio; Méndez, J.
In this paper a processing methodology is introduced for the segment or intermediate level in the context of knowledge-based computer vision systems. The proposed methodology demonstrates how using simple Fuzzy Logic concepts it is possible to associate symbolic descriptions to the entities of this level. It provides with the basic mechanisms for performing symbolic computation, evidence combination, uncertainty management and spatial reasoning at the segment level.
2007-09-13T11:16:08ZCabrera Gámez, JuanHernández Tejara, Francisco MarioFalcón Martel, AntonioMéndez, J.In this paper a processing methodology is introduced for the segment or intermediate level in the context of knowledge-based computer vision systems. The proposed methodology demonstrates how using simple Fuzzy Logic concepts it is possible to associate symbolic descriptions to the entities of this level. It provides with the basic mechanisms for performing symbolic computation, evidence combination, uncertainty management and spatial reasoning at the segment level.Phrase structure grammars for the expression of vague voncepts in SpanishSobrino Cerdeiriña, AlejandroOlivas Varela, José Ángelhttp://hdl.handle.net/2099/34772017-02-07T16:04:31Z2007-09-13T10:53:49ZPhrase structure grammars for the expression of vague voncepts in Spanish
Sobrino Cerdeiriña, Alejandro; Olivas Varela, José Ángel
This paper characterizes grammars generating Spanish sentences of imprecise meaning. The basic grammar generating sentences onforming to the standard paradigm of fuzzy logic (Quantifier + Noun + Verb + Modifier + Adjective) is systematically deformed (by inversion, suppression or addition of nonterminal elements in its production rules) to produce a series of grammars generating grammatical, semantically acceptable semigrammatical or ungrammatical
sentences.
2007-09-13T10:53:49ZSobrino Cerdeiriña, AlejandroOlivas Varela, José ÁngelThis paper characterizes grammars generating Spanish sentences of imprecise meaning. The basic grammar generating sentences onforming to the standard paradigm of fuzzy logic (Quantifier + Noun + Verb + Modifier + Adjective) is systematically deformed (by inversion, suppression or addition of nonterminal elements in its production rules) to produce a series of grammars generating grammatical, semantically acceptable semigrammatical or ungrammatical
sentences.A dual approach in fuzzy linear programmingCadenas Figueredo, José ManuelJiménez Barrionuevo, Fernandohttp://hdl.handle.net/2099/34762017-02-07T16:04:31Z2007-09-13T10:30:21ZA dual approach in fuzzy linear programming
Cadenas Figueredo, José Manuel; Jiménez Barrionuevo, Fernando
In this paper, we propose a relationship of fuzzy duality. We use the Decomposition Theorem and some properties about Linear Programming with interval coefficients to define this relationship. Thus, a linear programming problem with fuzzy costs represented by membership functions L-R can be solved by means of two dual problems (linear programming problems with fuzzy
constraints).
Moreover, these results can be applied to multiobjective problems whose coefficients of the objective function are fuzzy numbers represented by linear membership functions.
2007-09-13T10:30:21ZCadenas Figueredo, José ManuelJiménez Barrionuevo, FernandoIn this paper, we propose a relationship of fuzzy duality. We use the Decomposition Theorem and some properties about Linear Programming with interval coefficients to define this relationship. Thus, a linear programming problem with fuzzy costs represented by membership functions L-R can be solved by means of two dual problems (linear programming problems with fuzzy
constraints).
Moreover, these results can be applied to multiobjective problems whose coefficients of the objective function are fuzzy numbers represented by linear membership functions.Neural methods for obtaining fuzzy rulesBenítez Sánchez, José ManuelBlanco Morón, ArmandoDelgado Calvo-Flores, MiguelRequena Ramos, Ignaciohttp://hdl.handle.net/2099/34752020-07-21T18:55:46Z2007-09-13T09:36:27ZNeural methods for obtaining fuzzy rules
Benítez Sánchez, José Manuel; Blanco Morón, Armando; Delgado Calvo-Flores, Miguel; Requena Ramos, Ignacio
In previous papers, we presented an empirical methodology based on
Neural Networks for obtaining fuzzy rules which allow a system to be
described, using a set of examples with the corresponding inputs and
outputs. Now that the previous results have been completed, we present
another procedure for obtaining fuzzy rules, also based on Neural Networks
with Backpropagation, with no need to establish beforehand the labels or
values of the variables that govern the system
2007-09-13T09:36:27ZBenítez Sánchez, José ManuelBlanco Morón, ArmandoDelgado Calvo-Flores, MiguelRequena Ramos, IgnacioIn previous papers, we presented an empirical methodology based on
Neural Networks for obtaining fuzzy rules which allow a system to be
described, using a set of examples with the corresponding inputs and
outputs. Now that the previous results have been completed, we present
another procedure for obtaining fuzzy rules, also based on Neural Networks
with Backpropagation, with no need to establish beforehand the labels or
values of the variables that govern the systemUsing fuzzy similiarity relations to revise and update a knwoledge baseRodríguez, Ricardo ÓscarGarcia, PereGodo Lacasa, Lluíshttp://hdl.handle.net/2099/34742017-02-07T16:04:32Z2007-09-13T09:13:55ZUsing fuzzy similiarity relations to revise and update a knwoledge base
Rodríguez, Ricardo Óscar; Garcia, Pere; Godo Lacasa, Lluís
Similarity-based models were first used by Ruspini to give semantics to fuzzy logic
([7]). In these models, incomplete information is represented by an evidential set, i.e. a set of possible worlds that are compatible with the evidence, together with a fuzzy similarity relation on the set of possible worlds that allows to describe the resemblance of arbitrary subsets of worlds to those belonging to the evidencial set. On the other hand, the question addressed by theory change formalisms is which kind of modifications have to be performed to a knowledge base when adding (retracting) a new
proposition to (from) that knowledge base. Revision and update are the two theory change operations which have received more attention in the literature.
In this paper we study a connection between similarity-based models and theory
change, coming from the fact that revision and updating operators have been
characterized by Katsuno and Mendelson in terms of pre-order relations in a
set of possible worlds. Pre-order relations arise in a natural way in the
similarity-based models.
2007-09-13T09:13:55ZRodríguez, Ricardo ÓscarGarcia, PereGodo Lacasa, LluísSimilarity-based models were first used by Ruspini to give semantics to fuzzy logic
([7]). In these models, incomplete information is represented by an evidential set, i.e. a set of possible worlds that are compatible with the evidence, together with a fuzzy similarity relation on the set of possible worlds that allows to describe the resemblance of arbitrary subsets of worlds to those belonging to the evidencial set. On the other hand, the question addressed by theory change formalisms is which kind of modifications have to be performed to a knowledge base when adding (retracting) a new
proposition to (from) that knowledge base. Revision and update are the two theory change operations which have received more attention in the literature.
In this paper we study a connection between similarity-based models and theory
change, coming from the fact that revision and updating operators have been
characterized by Katsuno and Mendelson in terms of pre-order relations in a
set of possible worlds. Pre-order relations arise in a natural way in the
similarity-based models.Representation of fuzzy knowledge bases using Petri nets: operation in the truth spaceBugarín Diz, Alberto JoséBarro Ameneiro, D. Senénhttp://hdl.handle.net/2099/34732017-02-07T16:04:32Z2007-09-12T13:03:58ZRepresentation of fuzzy knowledge bases using Petri nets: operation in the truth space
Bugarín Diz, Alberto José; Barro Ameneiro, D. Senén
In this paper the execution of Fuzzy Knowledge Bases in the truth space is briefly analyzed. The computational efficiency of the process is significantly increased by means of a parameterized description based on the linguistic truth values described by Baldwin. This permits executing the Fuzzy Knowledge Base through operations involving only simple numerical values, thus avoiding the direct analytic manipulation of possibility distributions. A Petri Net-based formalism that permits representing both the Fuzzy Knowledge Base and different dynamic processes performed onto it (execution following different strategies cycles and loops detection) is also presented. The paper focus on the algorithm for carrying out interferences in situations when information for all the input variables in the Fuzzy Knowledge Base is available.
2007-09-12T13:03:58ZBugarín Diz, Alberto JoséBarro Ameneiro, D. SenénIn this paper the execution of Fuzzy Knowledge Bases in the truth space is briefly analyzed. The computational efficiency of the process is significantly increased by means of a parameterized description based on the linguistic truth values described by Baldwin. This permits executing the Fuzzy Knowledge Base through operations involving only simple numerical values, thus avoiding the direct analytic manipulation of possibility distributions. A Petri Net-based formalism that permits representing both the Fuzzy Knowledge Base and different dynamic processes performed onto it (execution following different strategies cycles and loops detection) is also presented. The paper focus on the algorithm for carrying out interferences in situations when information for all the input variables in the Fuzzy Knowledge Base is available.