http://hdl.handle.net/2099/2065 3rd. Hispano-Polish Symposium Systems Analysis & Computer Science Mon, 20 May 2013 02:31:10 GMT 2013-05-20T02:31:10Z webmaster.bupc@upc.edu Universitat Politècnica de Catalunya. Servei de Biblioteques i Documentació no http://hdl.handle.net/2099/3677 Title: Editorial [3rd. Hispano-Polish Symposium on Systems Analysis and Computer Science: selection of papers] Authors: Hryniewicz, Olgierd; Esteva Massaguer, Francesc Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3677 1997-01-01T00:00:00Z Hryniewicz, Olgierd; Esteva Massaguer, Francesc no http://hdl.handle.net/2099/3498 Title: Neural networks learning as a multiobjective optimal control problem Authors: Krawczak, Maciej Abstract: The supervised learning process of multilayer feedforward neural networks can be considered as a class of multi-objective, multi-stage optimal control problem. An iterative parametric minimax method is proposed in which the original optimization problem is embedded into a weighted minimax formulation. The resulting auxiliary parametric optimization problems at the lower level have simple structures that are readily tackled by efficient solution methods, such as the dynamic programming or the error backpropagation algorithm. The analytical expression of the partial derivatives of systems performance indices with respect to the weighting vector in the parametric minimax formulation is derived. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3498 1997-01-01T00:00:00Z Krawczak, Maciej no Artificial neural networks, Supervised learning, Multi-objective optimization, Minimax solution The supervised learning process of multilayer feedforward neural networks can be considered as a class of multi-objective, multi-stage optimal control problem. An iterative parametric minimax method is proposed in which the original optimization problem is embedded into a weighted minimax formulation. The resulting auxiliary parametric optimization problems at the lower level have simple structures that are readily tackled by efficient solution methods, such as the dynamic programming or the error backpropagation algorithm. The analytical expression of the partial derivatives of systems performance indices with respect to the weighting vector in the parametric minimax formulation is derived. http://hdl.handle.net/2099/3497 Title: Testing satistical hipotheses in fuzzy environment Authors: Gregorzewski, Przemyslaw; Hryniewicz, Olgierd Abstract: In traditional statistics all parameters of the mathematical model and possible observations should be well defined. Sometimes such assumption appears too rigid for the real-life problems, especially while dealing with linguistic data or imprecise requirements. To relax this rigidity fuzzy methods are incorporated into statistics. We review hitherto existing achievements in testing statistical hypotheses in fuzzy environment, point out their advantages or disadvantages and practical problems. We propose also a formalization of that decision problem and indicate the directions of further investigations in order to construct a more general theory. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3497 1997-01-01T00:00:00Z Gregorzewski, Przemyslaw; Hryniewicz, Olgierd no Hypothesis testing, Fuzzy sets, Fuzzy data, Fussy hypothesis, Neyman-Pearson lemma, Bayesian approach In traditional statistics all parameters of the mathematical model and possible observations should be well defined. Sometimes such assumption appears too rigid for the real-life problems, especially while dealing with linguistic data or imprecise requirements. To relax this rigidity fuzzy methods are incorporated into statistics. We review hitherto existing achievements in testing statistical hypotheses in fuzzy environment, point out their advantages or disadvantages and practical problems. We propose also a formalization of that decision problem and indicate the directions of further investigations in order to construct a more general theory. http://hdl.handle.net/2099/3496 Title: A genetic algorithm for the multistage control of a fuzzy system in a fuzzy environment Authors: Kacprzyk, Janusz Abstract: We discuss a prescriptive approach to multistage optimal fuzzy control of a fuzzy system, given by a fuzzy state transition equation. Fuzzy constraints and fuzzy goals at consecutive control stages are given, and their confluence, Bellman and Zadeh's fuzzy decision, is an explicit performance function to be optimized. First, we briefly survey previous basic solution methods of dynamic programming (Baldwin and Pilsworth, 1982) and branch-and-bound (Kacprzyk, 1979), which are plagued by low numerical efficiency, and then sketch Kacprzyk's (1993a--e, 1994a) approach based on possibilistic interpolative reasoning aimed at enhancing the numerical efficiency but requiring a solution of a simplified auxiliary problem, and then some "readjustment" of the solution obtained. We propose a genetic algorithm for solving the problem considered. Real coding and specially defined operations of crossover, mutation, etc. are employed. The approach yields good results, and is quite efficient numerically Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3496 1997-01-01T00:00:00Z Kacprzyk, Janusz no Multistage fuzzy control, Fuzzy dynamic system, Fuzzy dynamic programming, Branch-and-bound, Interpolative reasoning, Genetic algorithm We discuss a prescriptive approach to multistage optimal fuzzy control of a fuzzy system, given by a fuzzy state transition equation. Fuzzy constraints and fuzzy goals at consecutive control stages are given, and their confluence, Bellman and Zadeh's fuzzy decision, is an explicit performance function to be optimized. First, we briefly survey previous basic solution methods of dynamic programming (Baldwin and Pilsworth, 1982) and branch-and-bound (Kacprzyk, 1979), which are plagued by low numerical efficiency, and then sketch Kacprzyk's (1993a--e, 1994a) approach based on possibilistic interpolative reasoning aimed at enhancing the numerical efficiency but requiring a solution of a simplified auxiliary problem, and then some "readjustment" of the solution obtained. We propose a genetic algorithm for solving the problem considered. Real coding and specially defined operations of crossover, mutation, etc. are employed. The approach yields good results, and is quite efficient numerically http://hdl.handle.net/2099/3495 Title: Multi-stage genetic fuzzy systems based on the iterative rule learning approach Authors: González Muñoz, Antonio; Herrera Triguero, Francisco Abstract: Genetic algorithms (GAs) represent a class of adaptive search techniques inspired by natural evolution mechanisms. The search properties of GAs make them suitable to be used in machine learning processes and for developing fuzzy systems, the so-called genetic fuzzy systems (GFSs). In this contribution, we discuss genetics-based machine learning processes presenting the iterative rule learning approach, and a special kind of GFS, a multi-stage GFS based on the iterative rule learning approach, by learning from examples. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3495 1997-01-01T00:00:00Z González Muñoz, Antonio; Herrera Triguero, Francisco no Fuzzy logic, Fuzzy rules, Genetic algoritms, Machine learning, GFS, Genetic fuzzy systems Genetic algorithms (GAs) represent a class of adaptive search techniques inspired by natural evolution mechanisms. The search properties of GAs make them suitable to be used in machine learning processes and for developing fuzzy systems, the so-called genetic fuzzy systems (GFSs). In this contribution, we discuss genetics-based machine learning processes presenting the iterative rule learning approach, and a special kind of GFS, a multi-stage GFS based on the iterative rule learning approach, by learning from examples. http://hdl.handle.net/2099/3494 Title: Weighting quantitative and qualitative variables in clustering methods Authors: Gibert Oliveras, Karina; Cortés, Ulises Abstract: Description of individuals in ill-structured domains produces messy data matrices. In this context, automated classification requires the management of those kind of matrices. One of the features involved in clustering is the evaluation of distances between individuals. Then, a special function to calculate distances between individuals partially simultaneously described by qualitative and quantitative variables is required. In this paper properties and details of the metrics used by Klass in this situation is presented --- Klass is a clustering system oriented to the classification of ill-structured domains which implements an adapted version of the reciprocal neighbors algorithm; it also takes advantage of any additional information that an expert can provide about the target concepts. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3494 1997-01-01T00:00:00Z Gibert Oliveras, Karina; Cortés, Ulises no Clustering, Metrics, Qualitative and quantitative variables, Messy data, Ill-structured domaines Description of individuals in ill-structured domains produces messy data matrices. In this context, automated classification requires the management of those kind of matrices. One of the features involved in clustering is the evaluation of distances between individuals. Then, a special function to calculate distances between individuals partially simultaneously described by qualitative and quantitative variables is required. In this paper properties and details of the metrics used by Klass in this situation is presented --- Klass is a clustering system oriented to the classification of ill-structured domains which implements an adapted version of the reciprocal neighbors algorithm; it also takes advantage of any additional information that an expert can provide about the target concepts. http://hdl.handle.net/2099/3493 Title: Sedàs: a semantic based general classifier system Authors: Valls Mateu, Aïda; Riaño Ramos, David; Torra Ferré, Vicenç Abstract: In this work we present the general classifier system Sedàs. We show how this system implements the description of the domain and how it builds similarity matrices and classification trees. The system uses a new semantics, introduced in [Torra96], to define a distance between qualitative values. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3493 1997-01-01T00:00:00Z Valls Mateu, Aïda; Riaño Ramos, David; Torra Ferré, Vicenç no Clustering, Knowledge representation, Knowledge-based systems, Sedàs In this work we present the general classifier system Sedàs. We show how this system implements the description of the domain and how it builds similarity matrices and classification trees. The system uses a new semantics, introduced in [Torra96], to define a distance between qualitative values. http://hdl.handle.net/2099/3492 Title: Towards Specifying with Inclusions Authors: Agustí Cullell, Jaume; Puigsegur i Figueras, Jordi; Schorlemmer, Wernher Marco Abstract: In this article we present a functional specification language based on inclusions between set expressions. Instead of computing with data individuals we deal with their classification into sets. The specification of functions and relations by means of inclusions can be considered as a generalization of the conventional algebraic specification by means of equations. The main aim of this generalization is to facilitate the incremental refinement of specifications. Furthermore, inclusional specifications admit a natural visual syntax which can also be used to visualize the reasoning process. We show that reasoning with inclusions is well captured by bi-rewriting, a rewriting technique introduced by Levy and Agustí [15]. However, there are still key problems to be solved in order to have executable inclusional specifications, necessary for rapid prototyping purposes. The article mainly points to the potentialities and difficulties of specifying with inclusions. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3492 1997-01-01T00:00:00Z Agustí Cullell, Jaume; Puigsegur i Figueras, Jordi; Schorlemmer, Wernher Marco no Diagrammatic reasoning, Visual languages, Declarative programming, Formal specification In this article we present a functional specification language based on inclusions between set expressions. Instead of computing with data individuals we deal with their classification into sets. The specification of functions and relations by means of inclusions can be considered as a generalization of the conventional algebraic specification by means of equations. The main aim of this generalization is to facilitate the incremental refinement of specifications. Furthermore, inclusional specifications admit a natural visual syntax which can also be used to visualize the reasoning process. We show that reasoning with inclusions is well captured by bi-rewriting, a rewriting technique introduced by Levy and Agustí [15]. However, there are still key problems to be solved in order to have executable inclusional specifications, necessary for rapid prototyping purposes. The article mainly points to the potentialities and difficulties of specifying with inclusions. http://hdl.handle.net/2099/3491 Title: Milord II: language description Authors: Puyol-Gruart, Josep; Sierra Garriga, Carlos Abstract: In this paper we describe the language Milord. The description is made in terms of computer language concepts and not in terms of the logical semantics underlying it. In this sense the paper complements others in which the focus of the description has been either the object level multi-valued language description, or the reflective component of the architecture, or even the several applications built using it. All the necessary elements to understand how a system programmed in Milord executes have room in this full description: types, facts, rules, modules, local logics, control rategies, ... Although the description is guided by the Milord language syntax, this is by no means a user's manual, which would deserve a much longer document, but a language summary description that places all the components of the language in their correct place. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3491 1997-01-01T00:00:00Z Puyol-Gruart, Josep; Sierra Garriga, Carlos no Expert systems, Knowledge-based systems, Languages, Uncertainty, Milord II In this paper we describe the language Milord. The description is made in terms of computer language concepts and not in terms of the logical semantics underlying it. In this sense the paper complements others in which the focus of the description has been either the object level multi-valued language description, or the reflective component of the architecture, or even the several applications built using it. All the necessary elements to understand how a system programmed in Milord executes have room in this full description: types, facts, rules, modules, local logics, control rategies, ... Although the description is guided by the Milord language syntax, this is by no means a user's manual, which would deserve a much longer document, but a language summary description that places all the components of the language in their correct place. http://hdl.handle.net/2099/3162 Title: Valuation based systems for multistage control Authors: Wierzchon, S.T. Abstract: In this paper a graphical technique for solving multistage control problems is introduced. Its applicability and generality is demonstrated on examples concerning deterministic systems with deterministic or fuzzy constraints and stochastic systems with fuzzy constraints. Wed, 01 Jan 1997 00:00:00 GMT http://hdl.handle.net/2099/3162 1997-01-01T00:00:00Z Wierzchon, S.T. no Valuation-based systems, Multistage control problems, Fuzzy control In this paper a graphical technique for solving multistage control problems is introduced. Its applicability and generality is demonstrated on examples concerning deterministic systems with deterministic or fuzzy constraints and stochastic systems with fuzzy constraints.