No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
ESCORE DE PONTOS PARA A IDENTIFICAÇÃO DE TUBERCULOSE PULMONAR DERIVADO POR INTELIGÊNCIA COMPUTACIONAL
Abstract
Tuberculosis is one of the diseases that most affects humanity due to its easy transmission through inhalation of the causative agent. A wide adoption of diagnosis tests is hampered by limitations of cost, time to completion and accuracy. The purpose of this study is to derive a point-score system using Computational Intelligence tools. Thus, different techniques will be evaluated, such as: Multiobjective and Mono-objective Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing and Approximate Linear Regression. Considering the format and area under ROC curve as well as the quantity of involved symptoms, Approximate Linear Regression technique performed best for the evaluated data base, achieving a sensitivity of 83.0% and specificity of 59.6%. Introdução A tuberculose é uma doença infectocontagiosa causada por uma bactéria que afeta principalmente os pulmões, cuja transmissão ocorre de forma direta através das vias aéreas. O diagnóstico da doença pode ser feito através de exames como a baciloscopia e a cultura. O primeiro apresenta um elevado falso-negativo. Já o segundo, que possui um melhor desempenho, leva de 4 a 6 semanas para ser concluído, e não é disponibilizado para todas as unidades de saúde. Neste contexto, escores de pontos podem representar uma ferramenta rápida e eficaz para o diagnóstico, permitindo uma ampla utilização na comunidade médica por sua simplicidade intrínseca. Técnicas de Inteligência Computacional (IC), em especial de otimização natural, são normalmente hábeis na solução de problemas complexos e, portanto, especialmente indicadas para a produção destes escores, desde que derivados utilizando um conjunto de dados certificado por especialistas da área. A proposta deste trabalho é obter um escore de pontos que auxilie à tomada de decisão médica através de técnicas de IC. A adoção deste método visa reduzir o número de pacientes suspeitos de tuberculose que são enviados ao isolamento respiratório desnecessariamente. Além de permitir uma melhor gestão dos recursos hospitalares, sua adoção pode levar a um decréscimo nas chances de transmissão da tuberculose nestes ambientes. A estrutura do trabalho é a seguinte: inicialmente, é realizada a formulação do escore e descritas, de forma sucinta, as técnicas de IC avaliadas. Em sequência, a base de dados e os principais resultados são apresentados. Encerrando, têm-se as conclusões e trabalhos futuros. 913
ResearchGate has not been able to resolve any citations for this publication.
This paper presents a systematic methodology for empirical modeling and optimization of surface roughness in CO2 laser nitrogen cutting of stainless steel. The surface roughness prediction model was developed in terms of laser power, cutting speed, assist gas pressure and focus position by using the artificial neural network (ANN). To cover a wider range of laser cutting parameters and obtain an experimental database for the ANN model development, Taguchi's L27 orthogonal array was implemented in the experimental plan. The developed ANN model was expressed as an explicit nonlinear function, while the influence of laser cutting parameters and their interactions on surface roughness were analyzed by generating 2D and 3D plots. The final goal of the experimental study focuses on the determination of the optimal laser cutting parameters for the minimization of surface roughness. Since the solution space of the developed ANN model is complex, and the possibility of many local solutions is great, simulated annealing (SA) was selected as a method for the optimization of surface roughness.
We review accuracy estimation methods and compare the two most common methods: crossvalidation and bootstrap. Recent experimental results on arti cial data and theoretical results in restricted settings have shown that for selecting a good classi er from a set of classiers (model selection), ten-fold cross-validation may be better than the more expensive leaveone-out cross-validation. We report on a largescale experiment|over half a million runs of C4.5 and a Naive-Bayes algorithm|to estimate the e ects of di erent parameters on these algorithms on real-world datasets. For crossvalidation, we vary the number of folds and whether the folds are strati ed or not � for bootstrap, we vary the number of bootstrap samples. Our results indicate that for real-word datasets similar to ours, the best method to use for model selection is ten-fold strati ed cross validation, even if computation power allows using more folds. 1
Engineering design problems are usually characterized by the presence of many conflicting objectives that the design has to fulfill. Therefore, it is natural to look at many engineering problems as multi-objective optimization problems, with continuous and integer variables. The case is commonly encountered in several process systems engineering problems and such courses modules begin to make part of the curriculum of chemical engineering education. The aim of the paper is to develop the teaching strategy used in the master-level program “EcoEnergy” given in ENSIACET (Toulouse, France) which presents the main concepts of mono and multi-objective genetic algorithms. The MULTIGEN algorithm is then applied to a gas turbine using natural gas as a fuel with a thermo-economic optimization taking into account both the maximization of an efficiency criterion and minimization of natural gas consumption, in order to reduce CO2 emissions. The students learn how to obtain and interpret Pareto fronts in multi-objective configurations.
Otimização de alternativas para desenvolvimento de campo de petróleo utilizando computação evolucionária
- L F Almeida
Almeida LF. Otimização de alternativas para
desenvolvimento de campo de petróleo utilizando
computação evolucionária [dissertação de mestrado].
Introdução à estatística, 10ª
- M F Triola
Triola MF. Introdução à estatística, 10ª. ed. Rio de
Janeiro: LTC Editora; 2008.
An intelligent system for managing the isolation of patients suspected of pulmonary tuberculosis
- Jbo Souza Filho
- App Vieira
- J M Seixas
- F S Aguiar
- Fcq Mello
- A L Kritski
Souza Filho JBO, Vieira APP, Seixas JM, Aguiar
FS, Mello FCQ, Kritski AL. An intelligent system
for managing the isolation of patients suspected of
pulmonary tuberculosis. In: 13th International
Conference on Intelligent Data Engineering and
Automated Learning, 2012, Natal, v. 1. p. 1-8.