No abstract

No abstract

Abstract. An important parameter to analyze the efficiency of the heart as a pump is Cardiac Ejection Fraction (EF), which is clinically highly correlated to the functional status of the heart. Diverse non invasive methods can be applied to measure EF, like Computer Tomography, Magnetic Resonance, Echocardiography, and others. Nevertheless, none of these techniques can be used to continuous monitoring of such parameter. On the other hand, electrical impedance tomography (EIT) may be applied to accomplish this goal. In addition, low cost and high portability are also EIT's features that justify the research for solutions involving such technique to monitor EF. EIT consists in reconstruct images of the conductivity distribution of the interior of a conductor domain by applying electric currents and measuring electrical potential on the boundary of the body. Mathematically, EIT can be classified as a non-linear inverse problem. This work proposes a method for the continuous estimation of cardiac ejection fraction, addressing it as an optimization problem. The models used in our approach assume that recent two-dimensional magnetic resonance images of the patient are available, and use them to reduce the search space. Another important feature is the parametrization of the geometry of internal inclusions inside the domain, which also reduces the cost of the method. This work proposes a Hybrid Iterated Local Search (ILS) heuristic for EIT inverse problem using Levenberg-Marquardt Method as local search. Experiments are performed on two-dimensional images with synthetically generated data for electric potentials. Two different protocols for current injection are tested in such experiments and preliminary results are presented.

No abstract

High failure rates are a worrying and relevant problem in Brazilian universities. From a data set of student transcripts, we performed a study case for both general and Computer Science contexts, in which Data Mining Techniques were used to find patterns concerning failures. The knowledge acquired can be used for better educational administration and also build intelligent systems to support students’ decision making.