Abstract
Cooperative Go-evolution using Structured Genetic algorithms is proposed as a new technique to solve the problem of identification of discrete-time multivariable systems, using a closed-loop Multi-Input Single Output simultaneous testing procedure. This identification technique is illustrated by identifying a two-inputs two-outputs plant model, and simulation results are presented that allows to conclude about the convergence effectiveness of the cooperative co-evolutionary identification technique when compared with a single population Structured Genetic Algorithm applied to the same identification problem.

Abstract
Using multiple classifiers for increasing learning accuracy is an active research area. In this paper we present a new general method for merging classifiers. The basic idea of Cascade Generalization is to sequentially run the set of classifiers, at each step performing an extension of the original data set by adding new attributes. The new attributes are derived from the probability class distribution given by a base classifier. This constructive step extends the representational language for the high level classifiers, relaxing their bias. Cascade Generalization produces a single but structured model for the data that combines the model class representation of the base classifiers. We have performed an empirical evaluation of Cascade composition of three well known classifiers: Naive Bayes, Linear Discriminant, and C4.5. Composite models show an increase of performance, sometimes impressive, when compared with the corresponding single models, with significant statistical confidence levels. © Springer-Veriag Berlin Heidelberg 1998.

Abstract
The simultaneous production of both a 2-D waveguide and a Bragg grating is reported. The samples used consisted of a three layer slab structure produced by flame hydrolysis deposition. They were exposed to a focused KrF excimer laser beam. The exposure was done through a non-absorbing quartz plate which contained a 6 mm long phase mask with a period of 1066 nm on its central part. A type II grating was obtained, with the periodic perturbation clearly observed under a microscope.

Abstract
We present a closed-loop technique for measuring wavelength shifts associated with fiber Bragg gratings by using a fused biconical wavelength division multiplexer (WDM). The spectral response of the WDM is actively tuned by stretching of the coupling region to maintain a fixed coupling ratio at the reflected Bragg wavelength. The closed-loop operation allows sensitivities usually associated with a highly selective WDM to be obtained without compromising the measurement range. A simple theoretical model is presented together with experimental results for temperature and strain measurements. (C) 1998 Optical Society of America.

Abstract
The fast development in electrical power networks and his consequent complexity, impose a more useful state estimation operational scheme, shortening the time interval between consecutive state estimations. Technical developments in distributed Energy Management Systems (EMS), based on fast data communication networks, open up the possibility of Parallel and Distributed State Estimation implementation. In this paper will be introduced and discussed some ideas for the implementation of Parallel ana Distributed State Estimation in electrical power systems. Will be boarding a solution methodology based on conventional state estimation algorithms applicable in local networks and will be analysed some results obtained with a IEEE test system so that we can appreciate the performances of the proposed method. An evaluation of the degree of natural decoupling in the state estimation problem is also performed, and will be compared with the results of computational experiments with standard WLS methods, in the integral and distributed version.

Abstract
This paper provides a comprehensive study on how to use Profibus networks to support real-time communications, that is, ensuring the transmission of the real-time messages before their deadlines. Profibus is based on a simplified Timed Token (TT) protocol, which is a well-proved solution for real-time communication systems. However, Profibus differences to the TT protocol prevent the application of the usual TT analysis. The main reason is that, conversely to the TT protocol, in the worst case, only one high-priority message is processed per token visit. The major contribution of this paper is to prove that, despite this shortcoming, it is possible to guarantee communication real-time behaviour with the Profibus protocol.