Catálogo de publicaciones - libros

Auscultation of the heart is a medical technique that still today is used to provide a fast diagnosis about the heart condition. Compression of the heart sounds (or phonocardiogram) is very convenient to reduce bandwidth in telediagnosis systems that aid the physician in the evaluation of the cardiovascular state. The compression algorithm used depends on several parameters, which can take a diversity of values. Genetic algorithms have been used to obtain the optimal set of values for the compression parameters that optimize the performance of the compression for a test set of cardiac recordings. The optimized results were obtained very quickly, and optimal values agreed for (almost) all the test records.

The article presents an integrated resolution of the joint production and maintenance scheduling problem in hybrid flowshop. Two resolution methods are used on the basis of a new coding to represent a joint production and maintenance scheduling: Taboo search where we proposed an algorithm for the generation of a joint initial solution and neighbourhood, and GA where we proposed new joint operators for crossover and mutation. Computational experiments are conducted on a large set of instances and the resulting genetic algorithm gives the best results so far.

In this paper, we confront a variant of the cutting-stock problem with multiple objectives. The starting point is a solution calculated by a heuristic algorithm, termed , that aims to optimize the two main objectives, i.e. the number of cuts and the number of different patterns. Here, we propose a multi-objective genetic algorithm to optimize other secondary objectives such as changeovers, completion times of orders pondered by priorities and open stacks. We report experimental results showing that the multi-objective genetic algorithm is able to improve the solutions obtained by on the secondary objectives.

We consider the , a job shop scheduling problem with uncertain task durations and flexible due dates, with different objective functions and a GA as solving method. We propose a method to generate benchmark problems with variable uncertainty and analyse the performance of the objective functions in terms of the objective values and the sensitivity to variations in the uncertainty.

In this paper we propose a hybrid method, combining heuristics and local search, to solve flow shop scheduling problems under uncertainty. This method is compared with a genetic algorithm from the literature, enhanced with three new multi-objective functions. Both single objective and multi-objective approaches are taken for two optimisation goals: minimisation of completion time and fulfilment of due date constraints. We present results for newly generated examples that illustrate the effectiveness of each method.

One of the most important feature of the Neural Gas is its ability to preserve the topology in the projection of highly dimensional input spaces to lower dimensions vector quantizations. For this reason, the Neural Gas has proven to be a valuable tool in data mining applications.

In this paper an incremental ensemble method for the combination of various Neural Gas models is proposed. Several models are trained with bootstrap samples of the data, the “codebooks” with similar Voronoi polygons are merged in one fused node and neighborhood relations are established by linking similar fused nodes. The aim of combining the Neural Gas is to improve the quality and robustness of the topological representation of the single model. We have called this model .

Computational experiments show that the model effectively preserves the topology of the input space and improves the representation of the single Neural Gas model. Furthermore, the explicitly shows the neighborhood relations of it prototypes. We report the performance results using synthetic and real datasets, the latter obtained from a benchmark site.

Multiobjective optimization problems have become an important issue at many engineering problems. A tradeoff between several design criteria is required and important efforts are made for the development of Multiobjective Optimization Techniques and, in particular, Evolutionary Multiobjective Optimization. Usually these algorithms produce a set of optimum solutions in Pareto sense, there is not a unique solution. The designer (Decision Maker) has to finally select one solution for each particular problem, then he has to select from a set of Pareto solutions, the most adequate solution according to his preferences. It is widely accepted that visualization tools are valuable tools to provide the Decision Maker (DM) with a meaningful way to analyze Pareto set and then to help to select an adequate solution. This work describes a new graphical way to represent high dimensional and large sets of Pareto solutions, allowing an easier analysis, and helping the DM to select an adequate solution.

Conductive plastics have become an alternative to traditional metallic cabinets to shield boxes from electromagnetic interferences. The wide range of available conductivities with these materials can satisfy any particular design. A design with an outer metallic layer and an inner layer of conductive dielectric can obtain advantages from both materials. In this paper the design by means of genetic algorithms of electronic systems cabinets made of new plastic materials to reduce electromagnetic radiated interferences in enclosures with an aperture is described. This optimization procedure requires the use of electromagnetic simulators with a high computational cost. A 2D simulation tool is used in this work for evaluating 3D structures, reducing drastically the computation time. The relationship between obtained solutions and skin depth parameter is evaluated to help in design procedures. A commercial 3D full wave electromagnetic tool has been used to validate the obtained results.

In this paper we present a software tool for the automatic design of collective behaviors in animated feature films. The most successful existing commercial solutions used in animation studios require an explicit knowledge by the designer of the AI or other techniques and involve the hand design of many parameters. Our main motivation consists in developing a design tool that permits creating the behaviors of the characters from a high level perspective, using general concepts related to the final desired objectives, and to judge these behaviors from a visual point of view, thus abstracting the designer from the computational techniques in the system core. In this case, a bioinspired approach has been followed consisting in the incremental generation of controllers for simulated agents using evolution. An example of flocking activity is created with the system.

In this paper we propose a method for building possibilistic temporal constraint networks that better summarizes the huge set of mined timed-stamped sequences from a temporal data mining process. It belongs to the well-known second-order data mining problem, where the vast amount of simple sequences or patterns needs to be summarized further. It is a very important topic because the huge number of temporal associations extracted in the temporal data mining step makes the knowledge discovery process practically unmanageable for human experts. The method is based on the Theory of Evidence of Shafer as a mathematical tool for obtaining the fuzzy measures involved in the temporal network. This work also presents briefly a practical example describing an application of this proposal in the Intensive Care domain.