Lúcia Valéria

Bio: Lúcia Valéria is an academic researcher from Federal University of Technology - Paraná. The author has contributed to research in topics: Reconstruction algorithm & Flexibility (engineering). The author has an hindex of 1, co-authored 4 publications receiving 6 citations.

Etude d'algorithmes d'estimation robuste et developpement d'un systeme a base de connaissance pour l'identification

Abstract: Cette these se place dans un contexte general de conception intelligente assistee par ordinateur (c. I. A. O. ) pour l'identification de systemes. Elle aborde deux aspects distincts du sujet. Le premier est le probleme d'estimation robuste de modeles lineaires lorsque l'information a priori sur l'erreur de modelisation est disponible, non pas en terme probabiliste, mais sous la forme de bornes (approche de l'erreur inconnue mais bornee). Apres un rappel des principales familles d'algorithmes existantes dans cette approche, on s'interesse plus particulierement a la famille des algorithmes bases sur la reduction de domaines d'incertitude parametrique ellipsoidaux exterieurs. Une presentation unifiee ainsi qu'une interpretation de ces algorithmes en termes d'algorithmes d'identification robuste avec zone morte sont donnees. Puis une etude de proprietes de convergence est effectuee. Enfin une etude experimentale en simulation, permet d'analyser l'influence sur les performances de ces estimateurs, du choix de la borne, de l'ellipsoide de depart, et du rapport signal/bruit. L'autre aspect traite dans cette these, est relatif a l'application des techniques d'intelligence artificielle a la construction d'un logiciel de c. I. A. O. Pour l'identification. Le logiciel acai compose d'une interface homme/machine tres conviviale, d'une base de methodes d'identification (logiciel de c. A. O. Conventionnel), et d'un systeme a base de connaissance (s. B. C. ) est presente. Les objectifs de ce logiciel sont doubles: d'une part le systeme expert fournit une aide a l'utilisateur au niveau du choix des methodes disponibles dans le logiciel de c. A. O. Et du reglage de leurs parametres caracteristiques, et d'autre part, il effectue la supervision des traitements relatifs a l'identification, en vue d'ameliorer les performances et la robustesse des estimateurs. Enfin, une session d'identification supervisee en utilisant le logiciel acai est decrite

A Sparse Reconstruction Algorithm for Ultrasonic Images in

Abstract: Ultrasound imaging systems (UIS) are essential tools in nondestructive testing (NDT). In general, the quality of images depends on two factors: system hardware features and image reconstruction algorithms. This paper presents a new image reconstruction algorithm for ultrasonic NDT. The algorithm reconstructs images from A-scan signals acquired by an ultrasonic imaging system with a monostatic transducer in pulse-echo configuration. It is based on regularized least squares using a l1 regularization norm. The method is tested to reconstruct an image of a point-like reflector, using both simulated and real data. The resolution of reconstructed image is compared with four traditional ultrasonic imaging reconstruction algorithms: B-scan, SAFT, !-k SAFT and regularized least squares (RLS). The method demonstrates significant resolution improvement when compared with B-scan—about 91% using real data. The proposed scheme also outperforms traditional algorithms in terms of signal-to-noise ratio (SNR).

An object recognizing system for industrial applications

Abstract: On several automatic systems for manufacturing and assembly, specially on Flexible Manufacturing Systems (FMS), identifying mechanical parts produced and detecting their position and orientation are important issues related to the necessity of handling these parts by industrial robots. Currently, the recognizing process is performed by human check, but it may lead to increasing errors and accident probabilities. So the implementation of an effective automatic system, in order to recognize the parts, would not only avoid these risks but it would also improve the process velocity as well as its reliability This work presents an automatic system for free-form objects recognizing which identifies mechanical parts produced by a FMS. This system can recognize objects in a monochromatic image, captured by a charge couple device (CCD) camera. In addition to this, the system can be easily enabled to verify the parts orientation. This work used the concept of behavior vector, from the image indexing techniques, as a solution for the objects representation. Then, during the recognizing process, at least one hypothesis are generated by a backpropagation neural network trained to recognize the pattern vectors (known objects). Finally, the hypotheses are evaluated through a final verification process. As a result, the system offers quick and correct answers and also flexibility to be applied in other applications.

Comunicação, rotina e diagnóstico em adolescentes: implicações ambulatoriais

Abstract: Alguns aspectos pessoais e sociais destacam e indicam a adesão ao tratamento médico em adolescentes. Entre elas, percebe-se as características que envolvem a faixa etária, os comportamentos pessoais e sociais que se relacionam com a doença, as características pessoais dos pacientes, a forma e o regime com que o tratamento se dá, os problemas psicossociais intrínsecos e a relação médico-paciente.

Diagnóstico de Câncer de Cabeça e Pescoço Baseado em Redes Neurais e Dados de Impedanciometria

Abstract: This work reports the use of Neural Networks for classification of healthy and cancerous patients (head and neck cancer), based on anthropometrical and bioimpedance data. Using the proposed system, an accuracy rate of 85% was achieved, demonstrating the viability of this method. This result encourages the utilization of Neural Networks as classifiers using patient’s bioimpedance data as input. This technique allows early diagnose of cancer, when the prognosis can be better, therefore changing the cource of disease or suggesting a better treatment option.

Two Dimensional Signal And Image Processing

Abstract: Thank you for downloading two dimensional signal and image processing. As you may know, people have look hundreds times for their chosen novels like this two dimensional signal and image processing, but end up in malicious downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they juggled with some infectious virus inside their computer. two dimensional signal and image processing is available in our book collection an online access to it is set as public so you can download it instantly. Our digital library spans in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the two dimensional signal and image processing is universally compatible with any devices to read.

Robust estimation of parametric membership regions

Abstract: This paper is concerned with the robust identification of linear models when modelling error is bounded. A modified Hopfield's neural network is used to calculate a membership set for the model parameters, with the internal parameters of the network obtained using the valid-subspace technique. These parameters can be explicitly computed to guarantee the network convergence. A solution for the robust estimation problem with an unknown-but-bounded error corresponds to an equilibrium point of the network. A comparative analysis with alternative robust estimation methods is provided to illustrate the proposed approach.

Review and Comparison of Ellipsoidal Bounding Algorithms

Abstract: This chapter is concerned with the problem of robust system identification when no statistical information is available on the noise, but only a bound on its instantaneous values is known. First, various ellipsoidal outer bounding (EOB) algorithms are presented in a unified way. Then, two types of projection algorithms are described, and their link with the EOB algorithms is established. After that, the EOB algorithms are interpreted as robust identification algorithms with a dead zone. The performance of these algorithms is compared through computer simulations where the influence of the choice of the a priori error bound is more particularly studied.

Fuzzy trace identification algorithms for non-stationary systems

Abstract: In this paper, we propose fuzzy trace identification algorithms for identifying non-stationary stochastic systems. These algorithms are obtained by combining an adaptive trace identification algorithm with a fuzzy logic based supervisor. The supervision level uses the global parametric distance and the signal to noise ratio as inputs. A third input equal to the ratio between short term and long term estimated values of the output prediction error variance can also be used in order to provide faster convergence and better robustness of the parameter estimator in presence of model changes. The efficiency of the proposed identification methods is illustrated by means of simulation examples.

VIEnCoD-proposal of an environment CACSD integrated to an ERP system as a tool in the support to the control system development cycle based on VXIbus/LabWindows and MATLAB platform

Abstract: The paper presents the proposal of an CACSD (computer aided control system design) environment integrated with an ERP (enterprise resource planning) system, aimed at the study, design and optimization of controllers for the most varied shop floor plants, from mechatronics systems to industrial processes. More specific optimization, control and supervision methods in the the company are very important and necessary at the shop floor level; at this level, the motivation to integrate machines and production cells to the higher hierarchical levels of the company appears in a most expressive way. The VIEnCoD (virtual instrumentation based integrated environment for controller design) assists such objectives by giving integral support to the whole control system development cycle, from the phase of identification and modelling of the plant to controller synthesis.