Classificação bibliográfica: as diversas contribuições para o tratamento da informação

PEREIRA, Edinete do Nascimento et al. Classificação bibliográfica: as diversas contribuições para o tratamento da informação. In: SEMINÁRIO DE PESQUISA DO CCSA, 15., 2009. Anais... Natal: UFRN, 2009.

Estudo e implementação de algoritmos inteligentes para detecção e classificação de falhas na medição de gás natural

This master dissertation presents the study and implementation of inteligent algorithms to monitor the measurement of sensors involved in natural gas custody transfer processes. To create these algoritmhs Artificial Neural Networks are investigated because they have some particular properties, such as: learning, adaptation, prediction. A neural predictor is developed to reproduce the sensor output dynamic behavior, in such a way that its output is compared to the real sensor output. A recurrent neural network is used for this purpose, because of its ability to deal with dynamic information. The real sensor output and the estimated predictor output work as the basis for the creation of possible sensor fault detection and diagnosis strategies. Two competitive neural network architectures are investigated and their capabilities are used to classify different kinds of faults. The prediction algorithm and the fault detection classification strategies, as well as the obtained results, are presented

Seleção de categorias da Classificação Internacional de Funcionalidade, Incapacidade e Saúde para avaliação do paciente com acidente vascular cerebral em reabilitação

Stroke represents the first cause of disabilities among adults. Although different professions work together in treatment of stroke patients, all they use different terminologies for the description of the patients problems and it can constitute an impediment in the communication between the staff members. Thus, the multidisciplinary and interdisciplinary work would be facilitated if using a reference common tool, as the new International Classification of Functioning, Disability and Health (ICF). However, the ICF is very extensive and complex and due to its complexity, it has been evidenced the necessity to select its categories to become it more practical. The aim of the study was to investigate which categories of the ICF are more suitable to evaluate and to describe the stroke patient in the view of teachers and municipal public health professionals. It was a descriptive research, which involved 5 professors and 11 professionals of Physiotherapy that have worked at the health public area in Natal / RN. It was used the Delphi Technique in 3 rounds and the Likert Scale to select the categories among the ICF components. As result, from the 362 IFC categories, 94 were selected. The selected categories correspond to rehabilitative characteristics of Stroke patients in the universe of the Physiotherapy performance. The methodology applied was suitable to the studied object emphasizing the necessity of future studies for validation of the chosen categories

Estado nutricional antropométrico, composição corporal e pressão arterial em adolescentes

Os objetivos deste trabalho foram: (1) estimar as prevalências de excesso de peso e de gordura corporal, obesidade central e pressão arterial elevada (PAE) em adolescentes beneficiários do Programa Nacional de Alimentação Escolar (PNAE) da rede municipal de ensino de Natal-RN; (2) verificar a associação entre variáveis antropométricas e de composição corporal com a pressão arterial, a maturação sexual e a história familiar positiva de fatores de risco para doença cardiovascular (FRDCV); (3) comparar dois padrões de referência para classificação do excesso de peso em adolescentes; e (4) propor equações preditivas de massa gorda (MG) e massa livre de gordura (MLG) baseadas nos perímetros corporais. Trata-se de um estudo transversal, com 526 adolescentes beneficiários do PNAE, em Natal, Brasil. O tamanho da população de estudo foi definido por amostragem aleatória, em dois estágios, e ponderada segundo número de alunos de cada escola. No primeiro estudo, o excesso de peso foi determinado por Índice de Massa Corporal (IMC), a gordura corporal estimada por dobras cutâneas e a obesidade central por perímetro abdominal. A pressão arterial elevada foi classificada conforme a American Academy of Pediatrics. As prevalências foram apresentadas em valores relativos e efeito do desenho. Realizou-se uma análise fatorial para sintetizar o conjunto de variáveis antropométricas visando identificar fatores comuns. Extraíram-se dois fatores: (1) padrão excesso de adiposidade e (2) padrão adiposidade central elevada. Para avaliar a associação entre os padrões de adiposidade corporal com pressão arterial elevada, faixa etária, maturação sexual e história familiar de FRDCV utilizou-se a Razão de Chances e respectivo intervalo de confiança de 95% e regressão logística. No segundo estudo, calculou-se a sensibilidade e a especificidade do excesso de peso classificado segundo o IOTF e a World Health Organization WHO em relação ao excesso de adiposidade corporal; e a estatística Kappa para medir a concordância entre os dois padrões de referência. No terceiro estudo, foram elaborados modelos preditivos de MG e MLG com base em nove perímetros corporais, utilizando a bioimpedância Byodinamics 450 como padrão de referência. Para tanto foram selecionados 218 adolescentes eutróficos, segundo o IMC a partir do estudo transversal. As equações foram estimadas por regressão linear múltipla, considerando a idade e os perímetros corporais. Os resultados apontaram que 14,1% dos meninos e 15,7% das meninas tinham excesso de peso; 15,3% dos meninos e 11,6% das meninas tinham excesso de gordura corporal e dentre os meninos 14,3% tinham pressão arterial elevada e as meninas, 21,4%. Todos os efeitos do desenho foram inferiores a 2,5%. Nos meninos, o padrão excesso de adiposidade foi associado à história familiar positiva de FRDCV (ORajust=2,60; 1,09-6,22), maturação sexual (ORajust=2,92; 1,04-8,22) e PAE (ORajust=3,66; 1,34-9,94). Os meninos com 12 anos e mais apresentaram 6,1 vezes mais chance de apresentar padrão adiposidade central elevada do que os adolescentes com 10 a 11 anos (IC95% 2,32-16,04), assim como os púberes apresentaram 3,2 vezes este mesmo padrão em relação aos pré-púberes (IC95%1,14-8,85). A partir da comparação entre os dois padrões de referencia de classificação do excesso de peso por meio do IMC, observou-se que a sensibilidade foi de 79,3% para o critério IOTF e de 88,9% para WHO e a especificidade foi de 94,7% e 89,9%, respectivamente. O nível de concordância foi maior para o critério IOTF (Kappa=0,70 x Kappa=0,64). Em relação à construção das equações preditivas de gordura corporal, do total de 106 meninos e 112 meninas, foram desenvolvidas duas equações para estimar MG e duas para MLG, considerando o sexo. No sexo masculino, a equação para estimar a MG incluiu as variáveis idade, punho, quadril e perímetro abdominal (R2=0,552; AIC=416,04) e MLG, idade, punho e antebraço (R2=0,869; AIC=578,24). Enquanto que no feminino, MG foi estimada pelas variáveis punho, perímetro do abdômen, do quadril, da coxa proximal e da panturrilha (R2=0,838; AIC=415,36); e a MLG por idade, punho, perímetro do abdômen, do quadril e da panturrilha (R2=0,878; AIC=512,48). Conclui-se que os adolescentes tinham elevada prevalência de excesso de adiposidade corporal e de pressão arterial elevada. Tanto o padrão excesso de adiposidade quanto adiposidade central elevada constituem-se em padrões de risco. O padrão excesso de adiposidade foi associado à pressão arterial, história familiar positiva de FRDCV e maturação sexual em meninos. O critério IOTF mostrou-se menos sensível, mais específico, com maior nível de concordância e maior probabilidade de identificar corretamente o excesso de gordura corporal nos adolescentes avaliados. Quatro equações foram desenvolvidas para a estimativa da MG e MLG em adolescentes. As equações desenvolvidas para estimar a MG no sexo feminino e MLG para ambos os sexos apresentaram valores elevados de coeficiente de determinação ajustados e, portanto, são as preferenciais. Este estudo foi realizado com a participação de equipe multidisciplinar composta por professores da área de Nutrição, Endocrinologia Pediátrica, Estatística, Educação Física, discentes do Curso de Graduação em Nutrição e residentes em Pediatria

Determinação dos fatores neuroepidemiológicos das crises convulsivas em recém nascidos internados em unidades de terapia intensiva

O objetivo do nosso projeto foi determinar as características dos recém nascidos com crises convulsivas internados em unidades de terapia intensiva. Foi realizada uma pesquisa multicêntrica, observacional, prospectiva, cuja população alvo foi os recém nascidos com crises convulsivas internados em unidades de terapia intensiva, envolvendo equipe multidisciplinar constituída por neurologista infantil, neonatologistas, intensivistas pediátricos, enfermeiros, técnicos de enfermagem e fisioterapêutas. As crises foram definidas pelo critério clínico, com classificação de Volpe. Variáveis relacionadas à gestação, ao parto, características dos recém nascidos, aspectos das crises convulsivas e mortalidade foram analisadas. Estatística: descritiva (freqüências, medidas de tendência central e dispersão) e análise (teste de probabilidade, teste de risco e de acurácia). Comparamos as crises clínicas entre os recém nascidos de termo e pretermo e observamos diferenças com significância estatística na idade de início das crises, mais tardia nos prematuros, na etiologia predominante: hemorragia peri-intraventricular no prematuro e encefalopatia hipóxico-isquêmica no termo e tipo clínico de crise, clônica no pretermo e sutil no termo. Os testes de acurácia utilizados para determinar se o tipo clínico de crise convulsiva é predictor da etiologia da mesma não revelaram resultados positivos. Quanto às características associadas à mortalidade de prematuros com crise convulsiva, observamos associação entre ventilação mecânica e pneumonia com a mortalidade. Existem diferenças clínicas quando comparamos os recém nascidos pretermo e de termo com crises convulsivas, confirmando dados da literatura

Testes bioquímicos para avaliação do vigor em sementes de Mimosa caesalpiniaefolia Benth

Mimosa caesalpiniaefolia Benth. is a forest species of the Mimosaceae family, recommended for recovery of degraded areas. The evaluation of vigor by biochemical tests have been an important tool in the control of seed quality programs, and the electrical conductivity and potassium leaching the most efficient in the verifying the physiological potential. The objective, therefore, to adjust the methodology of the electrical conductivity test for seeds of M. caesalpiniaefolia, for then compare the efficiency of this test with the potassium in the evaluation of seed vigor of different lots of seeds M. caesalpiniaefolia. To test the adequacy of the electrical conductivity were used different combinations of temperatures , 25 °C and 30 ºC, number of seeds , 25 and 50, periods of imbibition , 4 , 8 , 12 , 16 and 24 hours , and volumes deionized water, 50 mL and 75mL. For potassium leaching test, which was conducted from the results achieved by the methodology of the adequacy of the electrical conductivity test, to compare the efficiency of both tests , in the classification of seeds at different levels of vigor, and the period 4 hours also evaluated because the potassium leaching test can be more efficient in the shortest time . The best combination obtained in experiment of electrical conductivity is 25 seeds soaked in 50 mL deionized or distilled water for 8 hours at a temperature of 30 ° C. Data were subjected to analysis of variance, the means were compared with each other by F tests and Tukey at 5 % probability, and when necessary polynomial regression analysis was performed. The electrical conductivity test performed at period eight hour proved to be more efficient in the separation of seed lots M. caesalpiniaefolia at different levels of vigor compared to the potassium test

Integridade tissular de pacientes com úlceras venosas: um estudo baseado na Classificação dos Resultados de Enfermagem

The venous ulcer is an epidemiological problem of high prevalence, causing disability and dependence. Assess the tissue impairment level of patients with venous lesions, within a nursing referential, is relevant for the implementation of a directed assistance to specific clientele. Thus, this work aims to characterize the health status regarding the integrity the lower limbs skin of patients with venous ulcers, according to the of tissue integrity outcome indicators from the Nursing Outcomes Classification. A cross-sectional study conducted in a university hospital in Natal - Rio Grande do Norte. The sample consisted of 50 participants, selected through consecutive sampling. Data collection occurred through a interview and physical examination form and a operational definitions tool for indicators of the nursing Tissue Integrity outcome directed to patients with venous ulcer, applied from February to June 2012. Data analysis was done by descriptive statistics and nonparametric tests (Spearman, Kruskal-Wallis and Mann-Whitney tests). The project was approved by the Research Ethics Committee with protocol 608/11 and Presentation Certificate to Ethical Consideration No. 0038.0.294.000-11. The results were presented using three scientific articles derivatives of research. It was found that the indicators show moderate impairment, light and not impaired, as the median. The respondents had an average of 59.72 years, 66% female, 50% were retired, 60% with a partner, 44% had arterial hypertension, 26% allergies, 20% diabetes mellitus, 96% were sedentary, 14% drank alcohol and 6% were smokers. There was a statistically significant correlation of low intensity between age and hydration (p=0.032; rs=-0.304) and skin desquamation (p=0.026; rs=-0.316), family income and necrosis (p=0.012; rs=-0.353); Ankle Brachial Index and tissue perfusion (p=0,044; rs=-0,329); Diabetes Mellitus and texture (p=0.015) and tissue perfusion (p=0.026); allergy and texture (p=0.034), physical activity and hydration (p=0.034), smoking and thickness (p=0.018), and alcohol consumption and exudate (p=0.045). We conclude that the patients had light to moderate impairment, indicating a good state of health on the integrity of the skin of the lower limbs, according to the indicators of the outcome of tissue integrity Classification Nursing Outcomes valued in the present study. It is believed that the evaluation of impairment tissue using a self-nursing system and its relation with socioeconomic, clinical and risk factors are unique tools in the care planning and in the wound healing

Modelo de classificação para pequenas empresas supermercadistas quanto ao uso de técnicas de prevenção de perdas: um estudo de caso

The objective of this work is to draw attention to the importance of use of techniques of loss prevention in small retail organization, analyzing and creating a classification model related to the use of these in companies. This work identifies the fragilities and virtues of companies and classifies them relating the use of techniques of loss prevention. The used methodology is based in a revision of the available literature on measurements and techniques of loss prevention, analyzing the processes that techniques needed to be adopted to reduce losses, approaching the "pillars" of loss prevention, the cycle life of products in retail and cycles of continues improvement in business. Based on the objectives of this work and on the light of researched techniques, was defined the case study, developed from a questionnaire application and the researcher's observation on a net of 16 small supermarkets. From those studies a model of classification of companies was created. The practical implications of this work are useful to point mistakes in retail administration that can become losses, reducing the profitability of companies or even making them impracticable. The academic contribution of this study is a proposal of an unpublished model of classification for small supermarkets based on the use of techniques of loss prevention. As a result of the research, 14 companies were classified as Companies with Minimum Use of Loss Prevention Techniques - CMULPT, and 02 companies were classified as Companies with Deficient Use of Loss Prevention Techniques - CDULPT. The result of the research concludes that on average the group was classified as being Companies with Minimum Use of Techniques of Prevention of Losses EUMTPP, and that the companies should adopt a program of loss prevention focusing in the identification and quantification of losses and in a implantation of a culture of loss prevention

Sistema de gestão da qualidade na hotelaria :um estudo comparativo da ISO 9000 com os modelos de classificação no Brasil

Este trabalho tem como objetivo estudar os sistemas de Classificações existentes para a garantia da gestão da qualidade no setor hoteleiro, tendo como foco principal a Matriz de Classificação para os Meios de Hospedagem da EMBRATUR e a ISO 9000, observando os benefícios que esses sistemas e/ou processos de gestão poderão vir a proporcionar para o setor hoteleiro no que se refere à qualidade de seus serviços. Para a obtenção dessas informações foi realizada uma análise comparativa dos sistemas de gestão da qualidade através de pesquisas bibliográficas e de questionários enviados para empreendimentos hoteleiros certificados e classificados, onde os principais resultados fornecidos pela pesquisa foram trabalhados de forma a apresentar, de maneira clara, a superioridade de um sistema em relação ao outro

Classificação de imagens de ambientes coralinos: uma abordagem empregando uma combinação de classificadores e máquina de vetor de suporte

The use of the maps obtained from remote sensing orbital images submitted to digital processing became fundamental to optimize conservation and monitoring actions of the coral reefs. However, the accuracy reached in the mapping of submerged areas is limited by variation of the water column that degrades the signal received by the orbital sensor and introduces errors in the final result of the classification. The limited capacity of the traditional methods based on conventional statistical techniques to solve the problems related to the inter-classes took the search of alternative strategies in the area of the Computational Intelligence. In this work an ensemble classifiers was built based on the combination of Support Vector Machines and Minimum Distance Classifier with the objective of classifying remotely sensed images of coral reefs ecosystem. The system is composed by three stages, through which the progressive refinement of the classification process happens. The patterns that received an ambiguous classification in a certain stage of the process were revalued in the subsequent stage. The prediction non ambiguous for all the data happened through the reduction or elimination of the false positive. The images were classified into five bottom-types: deep water; under-water corals; inter-tidal corals; algal and sandy bottom. The highest overall accuracy (89%) was obtained from SVM with polynomial kernel. The accuracy of the classified image was compared through the use of error matrix to the results obtained by the application of other classification methods based on a single classifier (neural network and the k-means algorithm). In the final, the comparison of results achieved demonstrated the potential of the ensemble classifiers as a tool of classification of images from submerged areas subject to the noise caused by atmospheric effects and the water column

Análise e classificação de imagens de lesões da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte

The skin cancer is the most common of all cancers and the increase of its incidence must, in part, caused by the behavior of the people in relation to the exposition to the sun. In Brazil, the non-melanoma skin cancer is the most incident in the majority of the regions. The dermatoscopy and videodermatoscopy are the main types of examinations for the diagnosis of dermatological illnesses of the skin. The field that involves the use of computational tools to help or follow medical diagnosis in dermatological injuries is seen as very recent. Some methods had been proposed for automatic classification of pathology of the skin using images. The present work has the objective to present a new intelligent methodology for analysis and classification of skin cancer images, based on the techniques of digital processing of images for extraction of color characteristics, forms and texture, using Wavelet Packet Transform (WPT) and learning techniques called Support Vector Machine (SVM). The Wavelet Packet Transform is applied for extraction of texture characteristics in the images. The WPT consists of a set of base functions that represents the image in different bands of frequency, each one with distinct resolutions corresponding to each scale. Moreover, the characteristics of color of the injury are also computed that are dependants of a visual context, influenced for the existing colors in its surround, and the attributes of form through the Fourier describers. The Support Vector Machine is used for the classification task, which is based on the minimization principles of the structural risk, coming from the statistical learning theory. The SVM has the objective to construct optimum hyperplanes that represent the separation between classes. The generated hyperplane is determined by a subset of the classes, called support vectors. For the used database in this work, the results had revealed a good performance getting a global rightness of 92,73% for melanoma, and 86% for non-melanoma and benign injuries. The extracted describers and the SVM classifier became a method capable to recognize and to classify the analyzed skin injuries

Classificação de distúrbios na rede elétrica usando redes neurais e wavelets

Post dispatch analysis of signals obtained from digital disturbances registers provide important information to identify and classify disturbances in systems, looking for a more efficient management of the supply. In order to enhance the task of identifying and classifying the disturbances - providing an automatic assessment - techniques of digital signal processing can be helpful. The Wavelet Transform has become a very efficient tool for the analysis of voltage or current signals, obtained immediately after disturbance s occurrences in the network. This work presents a methodology based on the Discrete Wavelet Transform to implement this process. It uses a comparison between distribution curves of signals energy, with and without disturbance. This is done for different resolution levels of its decomposition in order to obtain descriptors that permit its classification, using artificial neural networks

Detecção e classificação de modos de operação do bombeio mecânico via cartas dinamométricas

The precision and the fast identification of abnormalities of bottom hole are essential to prevent damage and increase production in the oil industry. This work presents a study about a new automatic approach to the detection and the classification of operation mode in the Sucker-rod Pumping through dynamometric cards of bottom hole. The main idea is the recognition of the well production status through the image processing of the bottom s hole dynamometric card (Boundary Descriptors) and statistics and similarity mathematics tools, like Fourier Descriptor, Principal Components Analysis (PCA) and Euclidean Distance. In order to validate the proposal, the Sucker-Rod Pumping system real data are used

Um sistema inteligente de classificação de sinais de EEG para Interface Cérebro-Computador

The Brain-Computer Interfaces (BCI) have as main purpose to establish a communication path with the central nervous system (CNS) independently from the standard pathway (nervous, muscles), aiming to control a device. The main objective of the current research is to develop an off-line BCI that separates the different EEG patterns resulting from strictly mental tasks performed by an experimental subject, comparing the effectiveness of different signal-preprocessing approaches. We also tested different classification approaches: all versus all, one versus one and a hierarchic classification approach. No preprocessing techniques were found able to improve the system performance. Furthermore, the hierarchic approach proved to be capable to produce results above the expected by literature

Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification