Catálogo de publicaciones - libros

Artificial Neural Networks are bioinspired mathematical models that have been widely used to solve many complex problems. However, the training of a Neural Network is a difficult task since the traditional training algorithms may get trapped into local solutions easily. This problem is greater in Recurrent Neural Networks, where the traditional training algorithms sometimes provide unsuitable solutions. Some evolutionary techniques have also been used to improve the training stage, and to overcome such local solutions, but they have the disadvantage that the time taken to train the network is high. The objective of this work is to show that the use of some non-linear programming techniques is a good choice to train a Neural Network, since they may provide suitable solutions quickly. In the experimental section, we apply the models proposed to train an Elman Recurrent Neural Network in real-life Time Series Prediction problems.

The MultiCAD platform is a system that accepts the declarative description of a scene (e.g. a building) as input and generates the geometric descriptions that comply with the specific description. Its goal is to facilitate the transition from the intuitive hierarchical decomposition of the scene to its concrete geometric representation. The aim of the present work is to provide the existing system with an intelligent module that will capture, store and apply user preferences in order to eventually automate the task of solution selection. A combination of two components based on decision support and artificial intelligence methodologies respectively are currently being implemented. A method is also proposed for the fair and efficient comparison of the results.

At present, we have a dmFSQL server available for Oracle© Databases, programmed in PL/SQL. This server allows us to query a Fuzzy or Classical Database with the dmFSQL (data mining Fuzzy SQL) language for any data type. The dmFSQL language is an extension of the SQL language, which permits us to write flexible (or fuzzy) conditions in our queries to a fuzzy or traditional database. In this paper, we propose the use of the dmFSQL language for fuzzy queries as one of the techniques of Data Mining, which can be used to obtain the clustering results in real time. This enables us to evaluate the process of extraction of information (Data Mining) at both a practical and a theoretical level. We present a new version of the prototype, called DAPHNE, for clustering witch use dmFSQL. We consider that this model satisfies the requirements of Data Mining systems (handling of different types of data, high-level language, efficiency, certainty, interactivity, etc) and this new level of personal configuration makes the system very useful and flexible.

This paper explores Knowledge Management (KM) practices for use with portal technologies in Non- Governmental Organizations (NGOs). The aim is to help NGOs become true Civil Society Organizations (CSOs). In order to deal with more donors (at the top) and more beneficiaries (at the bottom), NGOs working in Humanitarian Aid and Social Development increasingly need systems to manage the creation, accessing and deployment information: within the NGOs themselves, between different NGOs that work together and, ultimately, between NGOs and Society as a whole. Put simply, NGOs are organizations that need an effective KM solution to tackle the problems that arise from both their local-global nature and from the difficulties of effective communication between and within NGOs and Civil Society. To address these problems, the underlying objectives, entities, activities, workflow and processes of the NGO will be considered from a KM framework. This paper presents the needs of a responsible, cooperative and participative NGO from a KM perspective, in order to promote the growth of Communities of Practice in local as well as in global network.

This paper argues that chances (risks or opportunities) can be discovered from our daily observations and background knowledge. A person can easily identify chances in a news article. In doing so, the person combines the new information in the article with some background knowledge. Hence, we develop a deductive system to discover relative chances of particular chance seekers. This paper proposes a chance discovery system that uses a general purpose knowledge base and specialised reasoning algorithms.

The adoption of COTS-based development brings with it many challenges about the identification and finding of candidate components for reuse. Particularly, the first stage in the identification of COTS candidates is currently carried out dealing with unstructured information on the Web, which makes the evaluation process highly costing when applying complex evaluation criteria. To facilitate the process, in this paper we introduce an early measurement procedure for functional suitability of COTS candidates, and we illustrate the proposal by evaluating components for an e-payment case study.

The capability to safely interrupt business process activities is an important requirement for advanced processaware information systems. Indeed, exceptions stemming from the application environment often appear while one or more application-related process activities are running. Safely interrupting an activity consists of preserving its context, i.e., saving the data associated with this activity. This is important since possible solutions for an exceptional situation are often based on the current data context of the interrupted activity. In this paper, a data classification scheme based on data relevance and on data update frequency is proposed and discussed with respect to two different real-world applications. Taking into account this classification, a correctness criterion for interrupting running activities while preserving their context is proposed and analyzed.

The definition of privacy given by Warren and Brandeis as the “right to be let alone” is described as the most comprehensive of rights and the right most valued by civilized men.

The documentation of IT projects is of paramount importance for the lasting benefit of a project’s outcome. However, different forms of documentation are needed to comply with the diverse needs of users. In order to avoid the maintenance of numerous versions of the same documentation, an integrated method from the field of reference modeling creating perspectives on configurable models is presented and evaluated against a case in the field of health care. The proposal of a holistic to-be model for process documentation provides useful hints towards the need of presenting a model that relates to a specific user’s perspective. Moreover, it helps to evaluate the applicability of configurable, company-specific models concerning the relative operating efficiency.

The output of investments in Information Systems and Technologies (IST) has been a topic of debate among the IST research community. The “Productivity Paradox of IST Investments” sustains that the investment in IST does not increase productivity.