A Multiobjective Evolutionary Approach to Concurrently Learn Rule and Data Bases of Linguistic Fuzzy-Rule-Based Systems

In this paper, we propose the use of a multiobjective evolutionary approach to generate a set of linguistic fuzzy-rule-based systems with different tradeoffs between accuracy and interpretability in regression problems. Accuracy and interpretability are measured in terms of approximation error and rule base (RB) complexity, respectively. The proposed approach is based on concurrently learning RBs and parameters of the membership functions of the associated linguistic labels. To manage the size of the search space, we have integrated the linguistic two-tuple representation model, which allows the symbolic translation of a label by only considering one parameter, with an efficient modification of the well known (2 + 2) Pareto archived evolution strategy (PAES). We tested our approach on nine real world datasets of different sizes and with different numbers of variables. Besides the (2 + 2)PAES, we have also used the well known nondominated sorting genetic algorithm (NSGA-II) and an accuracy-driven single-objective evolutionary algorithm (EA). We employed these optimization techniques both to concurrently learn rules and parameters and to learn only rules. We compared the different approaches by applying a nonparametric statistical test for pairwise comparisons, thus taking into consideration three representative points from the obtained Pareto fronts in the case of the multiobjective EAs. Finally, a data complexity measure, which is typically used in pattern recognition to evaluate the data density in terms of average number of patterns per variable, has been introduced to characterize regression problems. Results confirm the effectiveness of our approach, particularly for (possibly high dimensional) datasets with high values of the complexity metric.     

Sharing Context-Aware Road and Safety Information

We present an integrated vehicular system for the collection, management, and provision of context-aware information on traffic and driver location. This system uses an integrated vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication paradigm enriched with an information management system. The infrastructure manages vehicle-detected safety hazards and other relevant information, adapting them to the vehicle's context and driver's preferences. This vehicular integrated system resembles the concept of a smart road.     

Optimum design of long-span suspension bridges considering aeroelastic and kinematic constraints

Cable supported bridges are wind prone structures. Therefore, their aerodynamic behaviour must be studied in depth in order to guarantee their safe performance. In the last decades important achievements have been reached in the study of bridges under wind-induced actions. On the other hand, non-conventional design techniques such as sensitivity analysis or optimum design have not been applied although they have proved their feasibility in the automobile or aeronautic industries. The aim of this research work is to demonstrate how non-conventional design techniques can help designers when dealing with long span bridges considering their aeroelastic behaviour. In that respect, the comprehensive analytical optimum design problem formulation is presented. In the application example the optimum design of the challenging Messina Strait Bridge is carried out. The chosen initial design has been the year 2002 design proposal. Up to a 33% deck material saving has been obtained after finishing the optimization process.     

Subacute Plasmodium falciparum malaria in 43 patients returning from areas with chloroquine in Africa

PURPOSE: To identify clinical and biological features of subacute falciparum malaria, risk factors, and to evaluate the efficacy of curative treatment. PATIENTS AND METHODS: Diagnostic criteria were the association of apyrexia, anemia, little or no parasitemia and a high titer of anti-Plasmodium antibodies. Forty-three cases were observed in subjects returning from chloroquine-resistant areas in Africa. They were matched with controls for age, country of residence and duration of stay. Controls were missionaries who attended our unit for a routine medical check-up during the study period. RESULTS: The clinical presentation and biological features were similar to "malarial cachexia", a condition mainly described in non-immune children in endemic areas. Splenomegaly was present in 58% of the patients. Biological features included little or no parasitemia, an overall decrease in the blood cell count, an increased erythrocyte sedimentation rate and a high titer of anti-Plasmodium antibodies. This syndrome was not correlated with the frequency of chloroquine resistance, the area of stay (urban or rural) or to the kind of chemoprophylaxis. CONCLUSIONS: This study describes subacute resistant falciparum malaria in patients who had prolonged stay in chloroquine-resistant areas of Africa associating splenomegaly, cytopenia and a low or absent parasitemia. Subacute chloroquine-resistant malaria could be due to host factors which remained to be determined by prospective immunological studies. Curative treatment with mefloquine is effective.     

Oleuropein protects low density lipoprotein from oxidation

The Mediterranean diet, rich in fruit, vegetables, grain, and vegetable oil (mainly olive oil) is correlated with a lower incidence of coronary heart disease (CHD). Natural antioxidants contained in the Mediterranean diet might also play a role in the prevention of cardiovascular diseases, through inhibition of LDL oxidation. We tested this hypothesis "in vitro" by inducing LDL oxidation with copper sulphate and preincubating the samples with oleuropein, the bitter principle of olives, that is one of the major components of the polyphenolic fraction of olive oil. Oleuropein 10(-5) M effectively inhibited CuSO4-induced LDL oxidation, as assessed by various parameters. We demonstrate in this investigation that polyphenolic components of the Mediterranean diet interfere with biochemical events that are implicated in atherogenetic disease, thus proposing a new link between the Mediterranean diet and prevention of CHD.     

Turbo spin-echo sequences in magnetic resonance imaging of the brain: Physics and applications

Fast SE imaging provides considerable measure time reduction, high signal-to-noise ratios as well as similar contrast behavior compared to conventional SE sequences. Besides TR and TE_eff, echo train length (ETL), interecho time , and-space trajectory determine image contrast and image quality in fast SE sequences. True proton density contrast (CSF hypointense) and not too strong T2 contrast are essential requirements in routine brain MRI. A Turbo SE sequence with very short echo train length (ETL=3), short TE_eff and short interecho time (17 ms), and TR=2000 ms was selected for proton density contrast; a Turbo SE sequence with ETL=7, TE_eff=90 ms, =22 ms, and TR=3250 ms was selected for T₂-weighted images. Using both single-echo Turbo SE sequences yielded 50% measure time reduction compared to the conventional SE technique. Conventional SE and optimized Turbo SE sequences were compared in 150 patients resulting in very similar signal and contrast behavior. Furthermore, reduced flow artifacts in proton density—and especially in T₂-weighted Turbo SE images—and better contrast of high-intensity lesions in proton density-weighted Turbo SE images were found. Slightly reduced edge sharpness—mainly in T₂-weighted Turbo SE images—did not reduce diagnostic reliability. Differences between conventional and Turbo SE images concerning image contrast and quality are explained regarding special features of fast SE technique.Address for correspondence: Institut für Röntgendiagnostik, Klinikum der Universität Regensburg, Franz-Josef-Strauß-Allee 11, 93042 Regensburg, Germany. Additional reprints of this chapter may be obtained from the Reprints Department, Chapman & Hall, One Venn Plaza, New York, NY 10119.     

Shift-invariant interpattern association neural network

A shift-invariant neural network that uses the translation-invariant property of the modulus Fourier spectra with the heteroassociation interpattern association memory is proposed. A binary encoding of a spectral sampling of the training set is used to preserve the main features. Computer simulations and experimental demonstrations are provided that show the shift-invariant property of the proposed optical neural network.