Catálogo de publicaciones - libros

A dissimilarity measure for shapes described by their contour, the Cyclic Dynamic Time Warping (CDTW) dissimilarity, is introduced. The dissimilarity measure is based on Dynamic Time Warping of cyclic strings, i.e., strings with no definite starting/ending points. The Cyclic Edit Distance algorithm by Maes cannot be directly extended to compute the CDTW dissimilarity, as we show in the paper. We present an algorithm that computes the CDTW dissimilarity in (log) time, where and are the lengths of the cyclic strings. Shape retrieval with the new dissimilarity measure is experimentally compared with the WARP system on a standard corpus.

Model-Based Diagnosis allows to determine why a correctly designed system does not work as it was expected. In this paper, we propose a methodology for software diagnosis which is based on the combination of Design by Contract, Model-Based Diagnosis and Constraint Programming. The contracts are specified by assertions embedded in the source code. These assertions and an abstraction of the source code are transformed into constraints, in order to obtain the model of the system. Afterwards, a goal function is created for detecting which assertions or source code statements are incorrect. The application of this methodology is automatic and is based on Constraint Programming techniques. The originality of this work stems from the transformation of contracts and source code into constraints, in order to determine which assertions and source code statements are not consistent with the specification.

In this paper we introduce a system for early classification of several fault modes in a continuous process. Early fault classification is basic in supervision and diagnosis systems, since a fault could arise at any time, and the system must identify the fault as soon as possible. We present a computational framework to deal with the problem of early fault classification using Case-Based Reasoning. This work illustrates different techniques for case retrieval and reuse that have been applied at different times of fault evolution. The technique has been tested for a set of fourteen fault classes simulated in a laboratory plant.

We investigate mechanisms which can endow the computer with the ability of describing a human face by means of computer vision techniques. This is a necessary requirement in order to develop HCI approaches which make the user feel himself/herself perceived. This paper describes our experiences considering gender, race and the presence of moustache and glasses. This is accomplished comparing, on a set of 6000 facial images, two different face representation approaches: Principal Components Analysis (PCA) and Gabor filters. The results achieved using a Support Vector Machine (SVM) based classifier are promising and particularly better for the second representation approach.

The Job Shop Scheduling is a paradigm of Constraint Satisfaction Problems that has interested to researchers over the last years. In this work we propose a Genetic Algorithm hybridized with a local search method that searches over the space of semi-active schedules and a heuristic seeding method that generates active schedules stochastically. We report results from an experimental study over a small set of selected problem instances of common use, and also over a set of big problem instances that clarify the influence of each method in the Genetic Algorithm performance.

In this paper, two important issues concerning pattern recognition by neural networks are studied: a new model of hebbian learning, as well as the effect of the network capacity when retrieving patterns and performing clustering tasks. Particularly, an explanation of the energy function when the capacity is exceeded: the limitation in pattern storage implies that similar patterns are going to be identified by the network, therefore forming different clusters.

This ability can be translated as an unsupervised learning of pattern clusters, with one major advantage over most clustering algorithms: the number of data classes is automatically learned, as confirmed by the experiments. Two methods to reinforce learning are proposed to improve the quality of the clustering, by enhancing the learning of patterns relationships.

As a related issue, a study on the net capacity, depending on the number of neurons and possible outputs, is presented, and some interesting conclusions are commented.

Since its conception, the perimeter idea has been understood as a mean for boosting single-agent search algorithms when solving different problems with the same target node, . However, various results emphasize that the most remarkable contribution of perimeter search is that it is an efficient way for improving the original heuristic estimations. Henceforth, a natural question arises: whether it is feasible or not to increase even more the capabilities for improving (·) when using a perimeter-like approach. As it will be shown, the so-called “” idea can be widely considered as an alternative to the classical perimeter and as a baseline for the research in this area.

Rate distortion theory is one of the areas of information transmission theory with important applications in multimodal signal processing, as for example image processing, information bottleneck and steganalysis. This article present an image characterization method based on rate distortion analysis in the feature space. This space is coded using clustering as vector quantization (k-means). Since image information usually cannot be coded by single clusters, because there are image regions corresponding to groups of clusters, the rate and distortion are specifically defined. The rate distortion curve is analyzed, extracting specific features for implementing a database image classification system.

Models are used in science and engineering for experimentation, analysis, diagnosis or design. In some cases, they can be considered as numeric constraint satisfaction problems (). Many models are symmetrical . The consideration of symmetries ensures that -solver will find solutions if they exist on a smaller search space. Our work proposes a strategy to perform it. We transform the symmetrical into a new by means of addition of symmetry-breaking constraints before the search begins. The specification of a library of possible symmetries for numeric constraints allows an easy choice of these new constraints. The summarized results of the studied cases show the suitability of the symmetry-breaking constraints to improve the solving process of certain types of symmetrical . Their possible speed-up facilitates the application of modelling and solving larger and more realistic problems.

This paper proposes a new method for representing document collections with conceptual multidimensional spaces inferred from their contents. Such spaces are built from a set of interesting word co-occurrences, which are properly arranged into taxonomies to define orthogonal hierarchical dimensions. As a result, users can explore and analyze the contents of large document collections by making use of well-known OLAP operators (On-Line Analytic Processing) over these spaces.