Catálogo de publicaciones - libros

XML has become a key technology for interoperability, providing a common data model to applications. However, diverse data modeling choices may lead to heterogeneous XML structure and content. In this paper, information retrieval and database-related techniques have been jointly applied to effectively tolerate XML data diversity in the evaluation of flexible queries. Approximate structure and content matching is supported via a straightforward extension to standard XPath syntax. Also, we outline a query execution technique representing a first step toward efficiently addressing structural pattern queries together with predicate support over XML elements content.

The theory of fuzzy sets has been applied to social choice primarily in the contexts where one is given a set of individual fuzzy preference relations and the aim is to find a non-fuzzy choice set of winners or best alternatives. We discuss the problem of composing multi-member deliberative bodies starting from a set of individual fuzzy preference relations. We outline methods of aggregating these relations into a measure of how well each candidate represents each voter in terms of the latter’s preferences. Our main goal is to show how the considerations discussed in the context of individual non-fuzzy complete and transitive preference relations can be extended into the domain of fuzzy preference relations.

A brief introduction to basic modifiers is given. Any modifier with its dual and the corresponding negation form a DeMorgan triple similar to that of t-norms, t-conorms, and negation. The lattice structure of the unit interval with the usual partial order is similar to that of the set of all membership functions. This structure has a certain connection to implication, by means of the subsethood of fuzzy sets, and it is possible to create a similar expression for modifiers as the axiom of reflexivity is in modal logic. Also, other connections to modal logics can be found. This motivates to develop a formal semantics to modifier logic by means of that of modal logic. Actually, this kind of logic is so-called concerning either true or false statements about properties of modifiers. This version is based on graded possibility operations. Hence, semantic tools for weakening modifiers are derived. The corresponding things for substantiating modifiers are constructed by means of duality. Finally, some outlines for modifier systems are considered.

A neural network is developed to mimic a human brain. The neural network consists of units and links that connect between units. Various types of neural networks are categorized into two classes: (1) back-propagation hierarchical neural network and (2) mutual-connected neural network. Generally speaking, it is hard to fix the number of units to build a neural network for solving problems. So the number of units is decided on the basis of experts’ experience.

In this paper, we explain a learning method how to decide the structure of a neural network for problems. The learning method is named structural learning. Even if we give a sufficient number of units, the optimal structure will be decided in the process of learning.

The objective of the paper is to explain the structural learning of both hierarchical and mutual connecting neural networks. Both networks obtained and showed the sufficiently good results. In the stock forecast by a general neural network, the operation and the system cost are very large because a lot of numbers of hidden layer units in the network are used. This research tried the optimization of the network by the structured learning, and evaluated the practicality. ...

With the increment of users and information on the Web, mining processes inspired in the traditional data mining ones have been developed. This new recent area of investigation is called Web Mining. Within this area, we study the analysis of web log files in what is called Web Usage Mining. Different techniques of mining to discover usage patterns from web data can be applied in Web Usage Mining. We will also study in a more detailed way applications of Fuzzy Logic in this area. Specially, we apply fuzzy association rules to web log files, and we give initial traces about the application of Fuzzy Logic to personalization and user profile construction.

In this paper, we present a methodology for designing a Precisiated Natural Language (PNL) based deduction engine for automated Question Answering (QA) systems. QA is one type of information retrieval system, and is regarded as the next advancement beyond keyword-based search engines, as it requires deductive reasoning and use of domain/background knowledge. PNL, as discussed by Zadeh, is one representation of natural language based on constraint-centered semantics, which is convenient for computing with words. We describe a hybrid reasoning engine which supports a “multi-pipe” process flow to handle PNL-based deduction as well as other natural language phrases that do not match PNL protoforms. The resulting process flows in a nested form, from the inner to the outer layers: (a) PNL-based reasoning where all important concepts are pre-defined by fuzzy sets, (b) deduction-based reasoning which enables responses drawn from generated/new knowledge, and (c) key phrase based search when (a) and (b) are not possible. The design allows for two levels of response accuracy improvement over standard search, while retaining a minimum performance level of standard search capabilities.

The totality of human thoughts in a document set is modeled by a polyhedron. A point represents a THOUGHT, a simplex a CONCEPT, a connected component a COMPLETE CONCEPT, the simplicial structure the whole IDEA. The building block is the simplex; it represents the concept that is carried by a set of high frequency and nearby co-occurring keywords. The simplicial structure of the keywords provides an ”informal” formal language about human thoughts in a document set. The model theory of this language gives the desirable model.

In information systems (or database), generally, attribute values of objects are numeral or symbols, from application point of view, linguistic information or decision rules are widely used. Hence, fuzzy linguistic summaries would be very desirable and human consistent. In this paper, extracting fuzzy linguistic summaries from a continuous information system is discussed. Due to fuzzy linguistic summaries can not be extracted directly in the information system, fuzzy information system is used to discretize the continuous information system, and level cut set is used to obtain classical information system firstly. Then based on including degree theory and formal concept analysis (FCA), simple fuzzy linguistic summaries are extracted. To extract complex linguistic summaries, logical conjunctions ∨ , ∧ and → are used. An Example of checking quality of sweetened full cream milk powder is also provided.

We further extend a new approach to a linguistic summarization of time series proposed in our previous works (cf. Kacprzyk, Wilbik and Zadrożny  [1,2,3,4,5]) in which we put forward the use of a fuzzy linguistic quantifier driven aggregation of trends (partial scores) via the traditional Zadeh calculus of linguistically quantified propositions and the Sugeno integral. Here we use for this purpose the Choquet integral that has been widely advocated for many decision analytic and economic problems. The results are intuitively appealing and the method is effective and efficient.

The constantly increasing capabilities of database storage systems leads to an incremental collection of data by business organizations. The research area of Data Mining has become a paramount requirement in order to cope with the acquired information by locating and extracting patterns from these data volumes. Possibilistic networks comprise one prominent Data Mining technique that is capable of encoding dependence and independence relations between variables as well as dealing with imprecision. It will be argued that the learning of the network structure only provides an overview of the qualitative component, yet the more interesting information is contained inside the network parameters, namely the potential tables. In this paper we introduce a new visualization technique that allows for a detailed inspection of the quantitative component of possibilistic networks.