107 resultados para Supervised and Unsupervised Classification
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
Non-Hodgkin lymphomas are of many distinct types, and different classification systems make it difficult to diagnose them correctly. Many of these systems classify lymphomas only based on what they look like under a microscope. In 2008 the World Health Organisation (WHO) introduced the most recent system, which also considers the chromosome features of the lymphoma cells and the presence of certain proteins on their surface. The WHO system is the one that we apply in this work. Herewith we present an automatic method to classify histological images of three types of non-Hodgkin lymphoma. Our method is based on the Stationary Wavelet Transform (SWT), and it consists of three steps: 1) extracting sub-bands from the histological image through SWT, 2) applying Analysis of Variance (ANOVA) to clean noise and select the most relevant information, 3) classifying it by the Support Vector Machine (SVM) algorithm. The kernel types Linear, RBF and Polynomial were evaluated with our method applied to 210 images of lymphoma from the National Institute on Aging. We concluded that the following combination led to the most relevant results: detail sub-band, ANOVA and SVM with Linear and RBF kernels.
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
No município de Itatiba-SP, no período de março a julho de 2007, foi realizado um experimento com o objetivo de avaliar doses de nitrogênio e potássio e espaçamentos entre plantas na produtividade e classificação de brócolos para indústria. O experimento foi instalado sob delineamento de blocos ao acaso, com os tratamentos em esquema fatorial 5 x 4, e três repetições, sendo avaliadas as doses de nitrogênio-potássio: 105-105; 157,5-157,5; 210-210; 262,5-262,5 e 315-315 kg ha-1 de N e K2O e os espaçamentos entre plantas: 0,2; 0,3; 0,4 e 0,5 m. O espaçamento entre linhas foi de 0,8 m. Foram avaliados o teor foliar de nitrogênio (TN) e de potássio (TP), produtividade de inflorescência (PI), produtividade de floretes (PF), rendimento industrial (RI) e classificação dos floretes com base em seu comprimento: PF5 (<5 cm); PF57 (>5 e <7 cm); PF79 (>7 e <9 cm) e PF9 (>9 cm). Maiores espaçamentos entre plantas proporcionaram maior TN e menores PI e PF. As doses NK e os espaçamentos entre plantas não influenciaram significativamente o TP e o RI. As maiores produtividades de inflorescências (22,08 t ha-1) e de floretes (17,09 t ha-1) foram obtidas com 0,20 m entre plantas e 315 kg ha-1 de N e de K2O. Maior percentagem de floretes na classe PF5 foi obtida no menor espaçamento entre plantas. As doses NK e os espaçamentos entre plantas não influenciaram as percentagens de floretes nas classes PF79 e PF9.
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Pesquisas visando a redução de perdas de grãos e sementes durante o armazenamento têm ocupado destaque em vários países. Dentro deste contexto, a avaliação da eficácia de um índice de qualidade de boa aplicabilidade, com metodologia simples e de resposta imediata visando tomadas rápidas de decisão é de suma importância. O presente trabalho, conduzido no Laboratório de Processamento de Produtos Agrícolas UNESP, Botucatu/SP teve como objetivos: (a) estabelecer correspondência entre o nível de ácidos graxos livres e as classes de vigor em sementes; (b) estabelecer correspondência entre o nível de ácidos graxos livres e a classificação comercial por tipos, em grãos de arroz (Oryza sativa L.). A correspondência entre o nível de ácidos livres e as classes de vigor em sementes foi avaliada utilizando-se sementes envelhecidas artificialmente, obtendo-se assim níveis diferenciados de vigor. A correspondência entre o nível de ácidos graxos livres e a classificação por tipos, em grãos de arroz, foi realizada utilizando-se amostras de arroz com as porcentagens máximas de grãos defeituosos permitidos pela legislação vigente. Utilizou-se a análise de variância de um delineamento inteiramente ao acaso e, para comparação entre médias, aplicou-se o teste de Tukey ao nível de 5% de probabilidade. Por meio dos resultados obtidos, observou-se que o teste de acidez graxa mostrou-se exeqüível para avaliar o vigor de sementes de arroz. Na pesquisa que buscava uma correspondência entre os valores de acidez graxa e classificação comercial, os dados revelaram a tendência do nível de ácidos graxos livres acompanhar a classificação comercial por tipos.
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Continuing development of new materials makes systems lighter and stronger permitting more complex systems to provide more functionality and flexibility that demands a more effective evaluation of their structural health. Smart material technology has become an area of increasing interest in this field. The combination of smart materials and artificial neural networks can be used as an excellent tool for pattern recognition, turning their application adequate for monitoring and fault classification of equipment and structures. In order to identify the fault, the neural network must be trained using a set of solutions to its corresponding forward Variational problem. After the training process, the net can successfully solve the inverse variational problem in the context of monitoring and fault detection because of their pattern recognition and interpolation capabilities. The use of structural frequency response function is a fundamental portion of structural dynamic analysis, and it can be extracted from measured electric impedance through the electromechanical interaction of a piezoceramic and a structure. In this paper we use the FRF obtained by a mathematical model (FEM) in order to generate the training data for the neural networks, and the identification of damage can be done by measuring electric impedance, since suitable data normalization correlates FRF and electrical impedance.
Resumo:
The development of strategies for structural health monitoring (SHM) has become increasingly important because of the necessity of preventing undesirable damage. This paper describes an approach to this problem using vibration data. It involves a three-stage process: reduction of the time-series data using principle component analysis (PCA), the development of a data-based model using an auto-regressive moving average (ARMA) model using data from an undamaged structure, and the classification of whether or not the structure is damaged using a fuzzy clustering approach. The approach is applied to data from a benchmark structure from Los Alamos National Laboratory, USA. Two fuzzy clustering algorithms are compared: fuzzy c-means (FCM) and Gustafson-Kessel (GK) algorithms. It is shown that while both fuzzy clustering algorithms are effective, the GK algorithm marginally outperforms the FCM algorithm. (C) 2008 Elsevier Ltd. All rights reserved.
Resumo:
This work presents a bibliometric profile of Bioethics Journal according to the following journal databases: MEDLINE, LILACS, The Philosopher' s Index, Ulrich's, SciELO and Qualis classification system (Brazil). We found that: from 38 titles indexed in MEDLINE, 25 (66%) still exist; the country with the highest number is the U. S. A (36%); most Bioethics journals appeared in the 1990's (47%), and 36% have less than 10 years of existence. From those that disappeared (34%), the average survival time was about 4 years. There are only 12 countries with indexed journals. In Brazil, from 3 Bioethics journals, only one is (partially) indexed. English is the preponderant language (45%). Only 3% of journals are monthly. LILACS has two additional publications (Acta Bioethica, Chile, and Revista Latino Americana, Colombia). SciELO has only Acta Bioethica. In Ulrich's database, there are eight additional publications. In "Qualis" classification system there are four journals.
Different nutritional-state indicators of HIV-positive individuals undergoing antiretroviral therapy
Resumo:
This study aimed at learning about the nutritional profile of HIV-positive individuals undergoing antiretroviral therapy and at comparing the performance of nutritional-state indicators. A transversal study was performed on 94 patients attending the Tropical Diseases Outpatient Hospital of Botucatu Medical School (FMB)-UNESP. The body mass index (BMI) and the classification by Papini-Berto (PB) were used to evaluate nutritional state, aiming at detecting malnutrition and obesity. The waist-to-hips ratio (W/HR) and waist circumference (WC) were adopted for identification of abdominal obesity and lipodystrophy. According to BMI, most of the individuals were eutrophic, followed by 30.9% overweight and 6.4% malnourished. By using the PB classification, the frequency of malnourished increased (22.3%). The analysis of the PB classification in relation to BMI indicated that the former presented high sensitivity and good specificity for malnutrition diagnosis, namely 100% and 83%, respectively. The prevalence of abdominal obesity was 7.44% according to WC, and a higher prevalence (38.3%) was observed when taking W/HR into account. There was significant positive association between nutritional diagnosis according to PB and T CD4(+) lymphocyte. The results support the use of PB classification for malnutrition detection as well as that of BMI and W/HR for overweight and fat redistribution.
Resumo:
OBJETIVO: comparar duas metodologias para o cálculo do volume placentário em gestações normais de termo: a do princípio de Arquimedes e a do volume do cilindro, para estimar a densidade absoluta da placenta. Definir a metodologia mais adequada para o cálculo do volume e densidade placentários, que se relacione com o peso e classificação do recém-nascido. MÉTODOS: foram estudadas 50 placentas provenientes de gestações de termo sem complicações e calculados o volume e a densidade absoluta placentários: a) pelo princípio de Arquimedes e b) na suposição de que a placenta seria uma secção de cilindro com duas alturas diferentes do bolo placentário: com a altura média e com a altura da média aritmética do centro e extremidades. As densidades absolutas placentárias foram calculadas pelo quociente entre o peso ao ar da placenta e os diferentes volumes. RESULTADOS: a maioria das gestantes eram multíparas, idade média de 25,4 anos, volume placentário médio entre 547,8 e 610 cm³ e densidade média entre 0,94 e 1,14 g/cm³, dependendo da metodologia empregada. CONCLUSÕES: a metodologia mais adequada para estimar o volume placentário no termo foi a do princípio de Arquimedes, pela melhor correlação com o peso dos recém-nascidos, o índice placentário e a classificação do peso dos recém-nascidos em relação à idade gestacional.
Resumo:
Objective. To describe the clinical and laboratory features of macrophage activation syndrome as a complication of juvenile systemic lupus erythematosus (SLE).Methods. Cases of juvenile SLE-associated macrophage activation syndrome were provided by investigators belonging to 3 pediatric rheumatology networks or were found in the literature. Patients who had evidence of macrophage hemophagocytosis on bone marrow aspiration were considered to have definite macrophage activation syndrome, and those who did not have such evidence were considered to have probable macrophage activation syndrome. Clinical and laboratory findings in patients with macrophage activation syndrome were contrasted with those of 2 control groups composed of patients with active juvenile SLE without macrophage activation syndrome. The ability of each feature to discriminate macrophage activation syndrome from active disease was evaluated by calculating sensitivity, specificity, and area under the receiver operating characteristic curve.Results. The study included 38 patients (20 with definite macrophage activation syndrome and 18 with probable macrophage activation syndrome). Patients with definite and probable macrophage activation syndrome were comparable with regard to all clinical and laboratory features of the syndrome, except for a greater frequency of lymphadenopathy, leukopenia, and thrombocytopenia in patients with definite macrophage activation syndrome. Overall, clinical features had better specificity than sensitivity, except for fever, which was highly sensitive but had low specificity. Among laboratory features, the best sensitivity and specificity was achieved using hyperferritinemia, followed by increased levels of lactate dehydrogenase, hypertriglyceridemia, and hypofibrinogenemia. Based on the results of statistical analysis, preliminary diagnostic guidelines for macrophage activation syndrome in juvenile SLE were developed.Conclusion. Our findings indicate that the occurrence of unexplained fever and cytopenia, when associated with hyperferritinemia, in a patient with juvenile SLE should raise the suspicion of macrophage activation syndrome. We propose preliminary guidelines for this syndrome in juvenile SLE to facilitate timely diagnosis and correct classification of patients.