Jorge Barreto

The scope of an ICAT (“Intelligent Computer-Aided Instruction”) is to provide an environment for the student to learn efficiently and pleasantly. The student must then be free to try to solve the proposed problem using a strategy he thinks is the best one. The traditional way is using an expert system that solves the same problem and then compares both

To describe and discuss the activities deployed by EVIPNet Brazil in 2013, highlighting the network's actions to promote evidence-based decision-making for the development and implementation of health policies. A descriptive approach was employed to present the actions carried out by EVIPNet Brazil in 2013, especially processes relating to capacity-building, product development, and event participation. In 2013, 10 training programs were carried out (four technical meetings and six workshops), involving 34 institutions and 193 participants. One evidence brief for policy was reviewed and republished, and five others were developed. Moreover, one process of deliberative dialogue was conducted. A scientific paper was published on the experience of EVIPNet Brazil in the development of evidence-informed polices. The first issue of the EVIPNet Brazil Newsletter was published, along with the posting of news articles online. EVIPNet Brazil's actions were presented on national and international lectures, conferences, and round tables. The impacts of EVIPNet Brazil may be observed in the federal, state, and local contexts. A successful development, implementation, and monitoring of evidence-informed policies depends on actions such as those carried out by EVIPNet, including professional capacity-building to help expand and consolidate the network, creation of new local Health Evidence Centers to encourage the use of evidence in decision-making, production of evidence briefs for health policies, and organization of deliberative dialogues.

Keywords. Modelling; optimal systems; physiological models; system analysis; cardiology.A physiological system is made of many coupled parts. To study the global behavior, we must couple together simple but meaningful models of each isolated subsystem. We present a methodology to build such subsystem models (which we call “reduced models”) which are interpretable in physiological terms and represent only the aspects of behavior essential for the study of interaction in the global system. We use both phenomenological and mechanistic modelling. This last approach is done in three interrelated levels of complexity. The “meaning” of the parameters of the simple models is found by using the relations between the levels and also the principle of “Teleonomy” which states that a system optimized by the natural selection must maximize some cost function. Specific aspects of our method are explained on a case study: a model of the pulmonary arterial tree to be used as a building block in a model of the whole cardiovascular system.

Keywords. Modelling, large-scale systems, bond-graphs, minimal realization; cardiology.The notion of Structural Minimality of a composite system is introduced. Informally, a composite system is nonminimal if, being formed of controllable and observable subsystems, it is uncontrollable and/or unobservable. Using Bond-graphs and the causal stroke assignment algorithm, a criterium to detect structural minimality is presented. The notion is applied to concrete examples, in particular to the choice of a cardiac fiber model to be used in a ventricle model for simulation purposes.

hlmanne-mail: J.Oehlmann@visolution.deKinderklinik Universitt LeipzigDr. Michael Achenbache-mail: Michael.Achenbach@rz.uni-jena.deCDPI - Centro de Diagnostico Medico Por Imagem, Rio de JanairoDr. Romeu Cortes Domingues, Dra. Fabiola Procaci KestelmanSonitec Diagnostico Medico por Imagem Ltda, FlorianopilisDra. Marcella SchaefferDMI - Diagnostico Medico por Imagem Ltda, Sao Jose - SCDr. Luiz Felipe Nobre2. General InformationThe Cyclops Project has been started as a...

ABSTRACT This paper shows the fuzzy analogical reasoning for medical diagnosis in modeling how an expert reasons. Normally this process involves imprecision and so, medical entities are modeled using fuzzy sets. The diagnostic for a patient is obtained by a syntactic similarity or the similarity grade to a previous case. It is shown the results of an expert system implementation in rheumatology Key words Expert system, Fuzzy System, Analogical Reasoning, Medical Diagnosis

... [4] Brasil, LM, “Uma proposta de arquitetura para sistema especialista híbrido ea correspondente metodologia de elicitação/representação do conhecimento”, Exame de Qualificação de Doutorado em Engenharia Elétrica, UFSC, Florianópolis, 1996. ...

A new methodology for developing Expert System (ES) is presented in this paper. It has learning ability to extract knowledge by a simple knowledge base using the learning by examples paradigm. The choice of a simple knowledge base was motivated by the fact that, in this case, it is easier to have consistence in putting together the several pieces of knowledge. So, the problems attached with knowledge elicitation phase are simplified.

The Knowledge Acquisition (KA) process consists on extracting and representing knowledge of a domain expert. In this work, one of the goals is to minimize the intrinsic difficulties of the KA process. We have obtained all possible rules from the domain expert in a short time and also a set of examples. Other goal, we are proposed a Hybrid Expert System (HES) to minimize the problems of the KA task using a new methodology. Building this kind of hybrid architecture has led us to use many tools: symbolic paradigm, connectionist paradigm, fuzzy logic and, Genetic Algorithm (GA). Another aim goal of this paper is to present two new algorithms, e.g., the first one is a learning algorithm to be applied to fuzzy feed-forward neural networks, as well as complexity problems to optimize the network topology. The second one is for extracting fuzzy rules of a trained fuzzy neural network. The learning algorithm was inspired on the classical back-propagation algorithm. It owns some variations due...

A simple but very efficient technique of 3D object reconstruction and recognition is presented here. An optical and computer vision based measurement system is used to acquire the object's data. The recognition algorithm is a distance calculator. It is used to compute the proximity of the object's shape under test and a reference object's geometry shape. Here, as an application example, we presents a human face recognition case. The effectiveness of the algorithm is demonstrated here in two tests in which the same person is compared with himself within different facial expressions and with others persons with different faces expressions too. The results are presented in a comparative chart.

Different from traditional methods which use two-dimensional images and gray levels to recognize human faces, this article shows a known shape extraction methodology applied to the extraction of 3D human faces conjugated with a conventional and non conventional algorithms for face verification. The SORFACE project involves two main knowledge areas, 3D shape extraction and pattern recognition. The first is based on Fourier Profilometry and the second on Case Base Reasoning - CBR and Artificial Neural Networks - ANN, which perform a symbolic and connectionist recognition system. Although these methodologies themselves are not new, the goal of this work is conjugate all in a face verification application problem and shows the results. Are commented too the benefits achieved by this 3D extraction technique over the illumination and geometric positioning problems. This is only viable today thanks to the increase of processing capacity of the new computers. This article describes all the ...

Utilizando-se da Natureza como fonte de inspiração e a Robótica como artefato artificial, este artigo trata que o comportamento visual biológico gerado pode ser modelado e transmitido para um artefato computacional. Este artigo também apresenta o resultado de um robô com capacidade de perceber o ambiente e decidir ações, mediante as informações colhidas pelo seu sistema perceptivo visual. Entre as aplicações estão: transporte de peças e ferramentas; escavação e transporte de minérios; exploração submarina; exploração espacial e vigilância.

Once talking about the possibilities of creating `thinking machines', Turing properly said that this task should start by defining of what is understood as `machines' and of what is `think'. Regarding the pursuit of modeling intelligence, two large avenues were opened by researchers in almost the same epoch: Symbolic Artificial Intelligence -- SAI -- and Connectionist Artificial Intelligence -- CAI -- based respectively on symbols and rules and in artificial neurons. It seems that the time is come to start thinking (and acting) to establish a standard of comparison, that could objectively tell how far we have gone along the road of constructing ever better AI systems. Devising an Intelligence Quotient IQ -- for machines or any intelligent system would be, perhaps, an advancement but unfortunately, the history of the development of techniques to measure human IQ, the first source checked to find applications to AI, points to a very fuzzy zone. Admitting that possibility, ...

The objective of this article is to study patterns which represent human faces in 3D and are associated to lin-ear separate class problems, where Artificial Neural Net-work -ANN recognition approach is used. The first step of the study was an experiment which resulted in giving the conditions to the hypothesis of 3D human faces be-long to the linear separate class. Low complexity nets that develop precise face classification task in "yes" and "no" classes were found through the use of evolutionary pro-gramming in the architecture of three layers feedforward ANNs. Through this analysis, the use of Perceptron and Adaline proves, by tests, the linear separation on the human face recognition, because these ANNs are only capable to classify linearly separated patterns.

Neural networks are used as associative memories to build an expert system for diagnostic. Similarly to expert systems implemented using symbolic manipulation, here the knowledge is introduced by a knowledge engineer using a collection of known cases. Fuzzy sets are used as interpretation for connection values and/or excitation state of units. The main result is that the proposed neural network allows not only to find a solution in some cases, but also to suggest to obtain more clinical data if the data available is insufficient to conclude. To illustrate the approach the case of two diseases with similar symptoms (difficult diagnostic) is used.

Electroluminescence measurements under continuous voltage have been carried out on devices with embedded silicon nanocrystals. Silicon excess has been achieved by means of LPCVD in a CMOS compatible procedure. Luminescence under continuous voltage is produced by the appearance of highly luminescent spots on the sample. The intensity flowing through the device reaches a saturation regime as well as the emitted power. This translates to a maximum electrluminescence efficiency for a given value of current intensity.

We present here early results of a potentially fast, efficient and reliable method to extract and recognize the shape of a general 3D external biological morphology. A computer vision based measurement system is used to acquire the 3D shape data. The recognition algorithm proposed here is based on distance calculation and is used to compute the proximity of the biologic

The Knowledge Acquisition (KA) process consists on extracting and representing knowledge of a domain expert. In this work, one of the goals is to minimize the intrinsic difficulties of the KA process. We have obtained all possible rules from the domain expert in a short time and also a set of examples. Other goal, we are proposed a Hybrid Expert