Parkinson's disease identification through Optimum-Path Forest

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.

Measurement of associated production of vector bosons and top quark-antiquark pairs in pp collisions at √s=7 TeV

The first measurement of vector-boson production associated with a top quark-antiquark pair in proton-proton collisions at √s=7 TeV is presented. The results are based on a data set corresponding to an integrated luminosity of 5.0 fb-1, recorded by the CMS detector at the LHC in 2011. The measurement is performed in two independent channels through a trilepton analysis of tt̄Z events and a same-sign dilepton analysis of tt̄V (V=W or Z) events. In the trilepton channel a direct measurement of the tt̄Z cross section σtt̄Z=0.28-0.11+0.14 (stat)-0.03+0.06 (syst) pb is obtained. In the dilepton channel a measurement of the tt̄V cross section yields σtt̄V=0.43-0.15+0.17 (stat)-0.07+0.09 (syst) pb. These measurements have a significance, respectively, of 3.3 and 3.0 standard deviations from the background hypotheses and are compatible, within uncertainties, with the corresponding next-to-leading order predictions of 0.137-0.016+0.012 and 0.306-0.053+0.031 pb. © 2013 CERN. Published by the American Physical Society.

SPECTRUM OF STOCHASTIC ADDING MACHINES AND FIBERED JULIA SETS

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Semliki Forest Virus as a Vector: Pros and Cons for Its Use in Biopharmaceuticals Production

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Interface para classificação de dados por máquinas de vetores de suporte

In this project the Pattern Recognition Problem is approached with the Support Vector Machines (SVM) technique, a binary method of classification that provides the best solution separating the data in the better way with a hiperplan and an extension of the input space dimension, as a Machine Learning solution. The system aims to classify two classes of pixels chosen by the user in the interface in the interest selection phase and in the background selection phase, generating all the data to be used in the LibSVM library, a library that implements the SVM, illustrating the library operation in a casual way. The data provided by the interface is organized in three types, RGB (Red, Green and Blue color system), texture (calculated) or RGB + texture. At last the project showed successful results, where the classification of the image pixels was showed as been from one of the two classes, from the interest selection area or from the background selection area. The simplest user view of results classification is the RGB type of data arrange, because it’s the most concrete way of data acquisition

Generalized interval vector spaces and interval optimization

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Classification of handwriting patterns in patients with Parkinson´s disease, using a biometric sensor

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Estimativa da irradiação solar global pelo método de Angstrom-Prescott e técnicas de aprendizado de máquinas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Artificial immune systems for classification of petroleum well drilling operations

This paper presents two approaches of Artificial Immune System for Pattern Recognition (CLONALG and Parallel AIRS2) to classify automatically the well drilling operation stages. The classification is carried out through the analysis of some mud-logging parameters. In order to validate the performance of AIS techniques, the results were compared with others classification methods: neural network, support vector machine and lazy learning.

Classificação de tábuas de madeira usando processamento de imagens digitais e aprendizado de máquina

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Effects of nutritional support on hospital outcome in dogs and cats

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Social support and infant malnutrition: a case-control study in an urban area of Southeastern Brazil

The relationship between malnutrition and social support was first suggested in the mid-1990s. Despite its plausibility, no empirical studies aimed at obtaining evidence of this association could be located. The goal of the present study was to investigate such evidence. A case-control study was carried out including 101 malnourished children (weight-for-age National Center for Health Statistics/WHO 5th percentile) aged 12-23 months, who were compared with 200 well-nourished children with regard to exposure to a series of factors related to their social support system. Univariate and multiple logistic regressions were carried out, odds ratios being adjusted for per capita family income, mother's schooling, and number of children. The presence of an interaction between income and social support variables was also tested. Absence of a partner living with the mother increased risk of malnutrition (odds ratio 2.4 (95 % CI 1.19, 4.89)), even after adjustment for per capita family income, mother's schooling, and number of children. The lack of economic support during adverse situations accounted for a very high risk of malnutrition (odds ratio 10.1 (95 % CI 3.48, 29.13)) among low-income children, but had no effect on children of higher-income families. Results indicate that receiving economic support is an efficient risk modulator for malnutrition among low-income children. In addition, it was shown that the absence of a partner living with the mother is an important risk factor for malnutrition, with an effect independent from per capita family income, mother's schooling, and number of children.

The thrust and the relation factor kr in linear induction machines

This paper shows a new manner to establish the thrust of a linear induction machine. A new factor is established, named ''Relation Factor, which provides conditions to establish the thrust and other important variables of the linear and sector induction machines.

Nutritional support and outcome in hospitalized dogs and cats

This study investigated the effect of assisted nutritional support on the outcome and time of hospitalization (TH) of dogs and cats. The study compared two groups of 400 hospitalized animals. The animals in group 1 did not receive assisted nutritional support because they were hospitalized before the clinical nutrition service was implemented; animals in group 2 were nutritionally managed. Animals in group 1 received a low-cost diet with no consumption control. Group 2 animals had their maintenance energy requirement (MER) calculated, received a high-protein and high-energy super-premium diet, had their caloric intake (CI) monitored, and received enteral and parenteral nutritional support when necessary. The statistical analysis of the results included the standard T test (group 1 versus group 2) and chisquare and Spearman's correlation to evaluate group 2 (CI and outcome, body condition score (BCS) and outcome, BCS and CI). For group 2, favorable outcome (FO), defined as the percent responding to therapy and dis-charged from the hospital, was 83%, and the TH was 8.59 days. These values were lower (P < .001) for group 1 (63.2% FO and TH of 5.7 days). For group 2, 65.5% of the animals received voluntary consumption (93.1% outcome), 14.5% received enterai support (67.9% FO), 6.5% received parenteral support (68% FO), and 6.17% did not eat (38.5% FO), demonstrating an association between the type of nutritional support and outcome (P < .01). Group 2 animals that received 0% to 33% of their MER had 62.9% FO, and those receiving more than 67% had 94.3% FO, which shows that lower mortality rates are associated with higher CI (P < .001). TH was higher for animals with higher CI (P < .001). The BCS did not correlate with Cl (P > .05) but did correlate with outcome (P < .01). FO was 68.7% for animals with low BCS, 85.7% for animals with ideal BCS, and 86.6% for overweight animals. Nutritional support could allow for longer therapies, thus increasing the TH and FO rate.