68 resultados para Nonparametric discriminant analysis


Relevância:

80.00% 80.00%

Publicador:

Resumo:

Foram estudados 125 países avaliados por um conjunto de 26 indicadores básicos, de saúde, econômicos e educacionais, usando-se três métodos estatísticos multivariados: Análise de Agrupamento, Análise de Componentes Principais e Análise de Variância Multivariada. As variáveis mais discriminatórias foram a expectativa de vida, as taxas de mortalidade infantil e de menores de cinco anos, as taxas de natalidade e de fertilidade e a taxa de matrícula no segundo grau para o sexo feminino. Os países foram ordenados de acordo com um índice de padrão de vida e separados em cinco grupos.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Zones of mixing between shallow groundwaters of different composition were unravelled by two-way regionalized classification, a technique based on correspondence analysis (CA), cluster analysis (ClA) and discriminant analysis (DA), aided by gridding, map-overlay and contouring tools. The shallow groundwaters are from a granitoid plutonite in the Funda o region (central Portugal). Correspondence analysis detected three natural clusters in the working dataset: 1, weathering; 2, domestic effluents; 3, fertilizers. Cluster analysis set an alternative distribution of the samples by the three clusters. Group memberships obtained by correspondence analysis and by cluster analysis were optimized by discriminant analysis, gridded memberships as follows: codes 1, 2 or 3 were used when classification by correspondence analysis and cluster analysis produced the same results; code 0 when the grid node was first assigned to cluster 1 and then to cluster 2 or vice versa (mixing between weathering and effluents); code 4 in the other cases (mixing between agriculture and the other influences). Code-3 areas were systematically surrounded by code-4 areas, an observation attributed to hydrodynamic dispersion. Accordingly, the extent of code-4 areas in two orthogonal directions was assumed proportional to the longitudinal and transverse dispersivities of local soils. The results (0.7-16.8 and 0.4-4.3 m, respectively) are acceptable at the macroscopic scale. The ratios between longitudinal and transverse dispersivities (1.2-11.1) are also in agreement with results obtained by other studies.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

A set of 25 quinone compounds with anti-trypanocidal activity was studied by using the density functional theory (DFT) method in order to calculate atomic and molecular properties to be correlated with the biological activity. The chemometric methods principal component analysis (PCA), hierarchical cluster analysis (HCA), stepwise discriminant analysis (SDA), Kth nearest neighbor (KNN) and soft independent modeling of class analogy (SIMCA) were used to obtain possible relationships between the calculated descriptors and the biological activity studied and to predict the anti-trypanocidal activity of new quinone compounds from a prediction set. Four descriptors were responsible for the separation between the active and inactive compounds: T-5 (torsion angle), QTS1 (sum of absolute values of the atomic charges), VOLS2 (volume of the substituent at region B) and HOMO-1 (energy of the molecular orbital below HOMO). These descriptors give information on the kind of interaction that occurs between the compounds and the biological receptor. The prediction study was done with a set of three new compounds by using the PCA, HCA, SDA, KNN and SIMCA methods and two of them were predicted as active against the Trypanosoma cruzi. (c) 2005 Elsevier SAS. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

The chemical composition of leaves of 57 trees of Cryptocarya mandioccana from three populations of southeastern Brazil was investigated through HPLC, assaying six flavonoids, seven styrylpyrones, and seven unidentified compounds. From 51 of the former trees, genotypes were obtained from 40 polymorphic loci of 19 isozymes. Cluster analyses of the phytochemical and genetical variation revealed that trees exhibited four chemotypes and five clusters from isozymes, respectively. Discriminant analyses from selected variables of the isozymic and chemical data sets were performed, respectively, in relation to the four chemotypes and the five isozyme clusters. The classification of individuals presented respective error estimates of 9.16% and 13.57%, indicating that the genetic data could explain the clusters from chernotypes and vice versa at acceptable error levels. Linear regressions with Dummy variable showed significant association of locus Skdh-2 with quercetin-3-O-beta-D-glucopyranoside and cryptofolione, indicating that its alleles would be responsible for the chemotype variation between individuals. (c) 2006 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Objectives: Diffuse uterine myohypertrophy (DUMH) is a condition clinically diagnosed by the presence of uterine bleeding, homogeneous and diffuse uterine enlargement, and absence of any myoendometrial cause of bleeding. Since the morphologic criteria for the diagnosis of this entity are still controversial, this study aimed to investigate the clinical presentation and the morphologic findings of the cases of DUMH presenting at the University Hospital of Botucatu, São Paulo, Brazil, Methods: We retrospectively studied 43 consecutive patients with DUMH submitted to hysterectomy (test group) and compared the findings with those obtained from 28 patients submitted to hysterectomy due to a prolapsed uterus (control group). There were no significant differences in age, weight or height between the two groups. Results: the uterine weight of the DUMH group (mean +/- S.D. 157.4 +/- 46.4 g) was significantly heavier than that of the control group (99.5 +/- 35.4 g) and myometrial thickness was significantly greater in the DUMH group (2.5 +/- 0.5 cm) than in the control group (1.9 +/- 0.4 cm). No positive correlation was observed between increased uterine weight and parity, but there was a positive correlation between uterine weight and myometrial thickness. on the basis of the present study, we suggest that the diagnosis of DUMH be made clinically and in cases of uterine weight greater than or equal to 120 g and myometrial thickness greater than or equal to 2.0 cm. In addition, 10 cases of each group were analyzed by morphometry to evaluate interstitial fibrosis and myometrial hypertrophy. The data showed that the increase in uterine weight in DUMH is caused by enlargement of individual myometrial fibers rather than accumulation of interstitial collagen. Conclusion: Discriminant analysis to estimate the diagnostic significance of a number of clinical and pathologic variables (age, parity, uterine weight and morphometric parameters) was able to differentiate cases of DUMH from controls in 100% of the patients.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

80.00% 80.00%

Publicador:

Resumo:

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

Relevância:

80.00% 80.00%

Publicador:

Resumo:

The results indicated potassium as the most important for the discrimination between groups of samples, followed by magnesium, calcium and sodium. As the area has been under intense sugar cane industrialisation, the soil and the river waters of the region receive a high content of vinasse rich in potassium. -from English summary

Relevância:

80.00% 80.00%

Publicador:

Resumo:

OBJECTIVE: To investigate the usefulness of assessing the immunoreactivity of cytokeratins 7 (CK7) and 20 (CK20) as well as several cytomorphologic parameters in effusions with metastatic adenocarcinomas in the search for the primary site of the tumor. STUDY DESIGN: From the files of the Pathology Department, A. C. Camargo Hospital, we studied cytologic smears from 73 metastatic adenocarcinomas originally from the breast, 63 from the ovary, 40 from the lung and 32 from the stomach, looking for morphologic parameters that could have discriminant potential in suggesting the primary site in a routine situation, including intranuclear inclusions, prominent nucleoli, mitosis, signet-ring cells, psammoma bodies, nuclear crease, binucleation and multinucleation, papillary features, acinar profile (including ball cells) and single cells. Immunoreactions were performed with monoclonal antibodies to CK7 (OV-TL 12/30 and CK20 (Ks 20.8) and included morphologic analysis. Both analyses were studied in a blind fashion regarding the primary site of the tumors. RESULTS: Positivity ratios for breast, ovary, stomach and lung cases were 67.6%, 63.5%, 29.7% and 45.5%, respectively, for CK7 and 17.2%, 15.8%, 13.5% and 32.2%, respectively, for CK20. Discriminant analysis of morphologic and immunocytochemical parameters had an error rate of 42.9% in recognizing the primary site and a Wilk's lambda of .7290. CONCLUSION: The more efficient parameter with discriminant function was the papillary appearance showed by CK7, which should be used in further studies with a similar scope. The set of parameters used in this study were insufficient to discriminate the primary site of female adenocarcinomas in effusions with significant accuracy.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

This paper presents the study of computational methods applied to histological texture analysis in order to identify plant species, a very difficult task due to the great similarity among some species and presence of irregularities in a given species. Experiments were performed considering 300 ×300 texture windows extracted from adaxial surface epidermis from eight species. Different texture methods were evaluated using Linear Discriminant Analysis (LDA). Results showed that methods based on complexity analysis perform a better texture discrimination, so conducting to a more accurate identification of plant species. © 2009 Springer Berlin Heidelberg.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

This study evaluated the Knoop hardness and polymerization depth of a dual-cured resin cement, light-activated at different distances through different thicknesses of composite resin. One bovine incisor was embedded in resin and its buccal surface was flattened. Dentin was covered with PVC film where a mold (0.8-mm-thick and 5 mm diameter) was filled with cement and covered with another PVC film. Light curing (40 s) was carried out through resin discs (2, 3, 4 or 5 mm) with a halogen light positioned 0, 1, 2 or 3 mm from the resin surface. After storage, specimens were sectioned for hardness measurements (top, center, and bottom). Data were subjected to split-plot ANOVA and Tukey's test (α=0.05). The increase in resin disc thickness decreased cement hardness. The increase in the distance of the light curing tip decreased hardness at the top region. Specimens showed the lowest hardness values at the bottom, and the highest at the center. Resin cement hardness was influenced by the thickness of the indirect restoration and by the distance between the light-curing unit tip and the resin cement surface.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Objective: This case-control study analyzed mass spectrometry fingerprinting patterns of culture media samples used for embryo culture to predict embryo implantation. Methods: The culture medium harvested after embryo transfer of 22 embryos from 13 patients was used for the experiments. After embryo transfer, the remaining culture media were collected and samples were split in positive (n=8) and negative (n=14) implantation groups according to implantation outcomes (100% or 0% of implantation). Samples were individually diluted and injected directly to the Electrospray ionization (ESI) MS coupled to a Quadrupole Time-of-flight MS (Q-ToF-MS).Ions relative intensities of each spectrum were considered. Data analysis was conducted in MatLab 7.0 version using Partial Least Squares - Discriminant Analysis toolbox. Results: There were 3027 observed ions at 100% and 0% implantation groups by ESI-Q-ToF-MS. The statistical model could categorize the samples in two clusters, based on their positive and negative implantation outcomes. Less intense ions present in the mass spectra with statistical significance have contributed to the major differences to group distinction. Conclusions: Positive and negative implantation embryos showed a specific biochemical pattern present in culture media, which could be detected as a fast, simple and non-invasive way. This biochemical profile could help the selection of the most viable embryo, improving single embryo transfer and thus eliminating the risk and undesirable outcomes of multiple pregnancies. © Todos os direitos reservados a SBRA - Sociedade Brasileira de Reprodução Assistida.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

The objective of this study was to define production environments by grouping different environmental factors and, consequently, to assess genotype by production environment interactions on weaning weight (WW) in the Angus populations of Brazil and Uruguay. Climatic conditions were represented by monthly temperature means (°C), minimum and maximum temperatures in winter and summer respectively and accumulated rainfall (mm/year). Mode in month of birth and weaning, and calf weight (kg) and age (days) at weaning were used as indicators of management conditions of 33 and 161 herds in 13 and 34 regions in Uruguay and Brazil, respectively. Two approaches were developed: (a) a bi-character analysis of extreme sub-datasets within each environmental factor (bottom and top 33% of regions), (b) three different production environments (including farms from both countries) were defined in a cluster analysis using standardized environmental factors. To identify the variables that influenced the cluster formation, a discriminant analysis was previously carried out. Management (month, age and weight at weaning) and climatic factors (accumulated rainfalls and winter and summer temperatures) were the most important factors in the clustering of farms. Bi or trivariate analyses were performed to estimate heritability and genetic correlations for WW in extreme sub-datasets within environmental factor or between clusters, using MTDFREML software. Heritability estimates of WW in the first approach ranged from 0.27 to 0.54, and genetic correlations between top and bottom sub-datasets within environmental factors, from -0.29 to 0.70. In the cluster approach, heritabilities were 0.58±0.04 for cluster 1, 0.31±0.01 for Cluster 2 and 0.40±0.02 for Cluster 3. Genetic correlations were 0.27±0.08, 0.32±0.09 and 0.33±0.09, between clusters 1 and 2, 1 and 3, and 2 and 3, respectively. Both approaches suggest the existence of genotype x environment interaction for weaning weight in Angus breed of Brazil and Uruguay. © 2012 Elsevier B.V.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Pós-graduação em Engenharia de Produção - FEB