Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Avaliação da usabilidade de representações cartográficas em diferentes escalas para sistema de navegação e guia de rota em automóvel

Pós-graduação em Ciências Cartográficas - FCT

Serviço de referência digital: uma análise apoiada em agentes de interface

Pós-graduação em Ciência da Informação - FFC

Desenvolvimento de um sistema computacional para monitoramento de parâmetros físicos na área de irrigação, com base na plataforma labVIEW

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A machine learning approach for genome-wide prediction of morbid and druggable human genes based on systems-level data

Background: The genome-wide identification of both morbid genes, i.e., those genes whose mutations cause hereditary human diseases, and druggable genes, i.e., genes coding for proteins whose modulation by small molecules elicits phenotypic effects, requires experimental approaches that are time-consuming and laborious. Thus, a computational approach which could accurately predict such genes on a genome-wide scale would be invaluable for accelerating the pace of discovery of causal relationships between genes and diseases as well as the determination of druggability of gene products.Results: In this paper we propose a machine learning-based computational approach to predict morbid and druggable genes on a genome-wide scale. For this purpose, we constructed a decision tree-based meta-classifier and trained it on datasets containing, for each morbid and druggable gene, network topological features, tissue expression profile and subcellular localization data as learning attributes. This meta-classifier correctly recovered 65% of known morbid genes with a precision of 66% and correctly recovered 78% of known druggable genes with a precision of 75%. It was than used to assign morbidity and druggability scores to genes not known to be morbid and druggable and we showed a good match between these scores and literature data. Finally, we generated decision trees by training the J48 algorithm on the morbidity and druggability datasets to discover cellular rules for morbidity and druggability and, among the rules, we found that the number of regulating transcription factors and plasma membrane localization are the most important factors to morbidity and druggability, respectively.Conclusions: We were able to demonstrate that network topological features along with tissue expression profile and subcellular localization can reliably predict human morbid and druggable genes on a genome-wide scale. Moreover, by constructing decision trees based on these data, we could discover cellular rules governing morbidity and druggability.

Usabilidade na web: o usuário como agente-facilitador no desenvolvimento de interfaces de home pages

Pós-graduação em Design - FAAC

Agricultura familiar, multifuncionalidade da agricultura e ruralidade: interfaces de uma realidade complexa

The last decades witnessed the revitalization of the debate around family farming with the addition of discussions regarding the multiple functions of agriculture, given the fact that rural areas are longer devoted exclusively to agricultural activities. In the Brazilian context, we believed that this debate must be permeated by analyses of how differentiated processes of land distribution and economic development, and the resulting types of agriculture, generate specific ruralities with characteristics such as, in the case of family farming, the maintenance of social and work practices marked by the relations among relatives and neighbours. It is in this light that this research analyses family agriculture in a rural area of Ouro Fino-MG, its historical heritage, and its participation in the creation of a physical and human landscape that greatly contributes to the attractiveness of the region.

Meio ambiente e enfermagem: suas interfaces e inserção no ensino de graduação

A degradação ambiental vem modificando nosso cenário de forma acelerada e interferindo negativamente no processo saúde-doença de toda a comunidade. No entanto, o meio ambiente vem sendo concebido como um simples cenário, algo externo ao ser humano, não onde estamos inseridos e no qual acontecem suas interações e inter-relações. A complexidade dos problemas ambientais clama pela adoção de medidas que superem práticas assistencialistas, levando à adoção de práticas transdisciplinares que avancem na promoção da saúde. Neste artigo procura-se discutir, nesta perspectiva, a necessidade de inserção nos cursos de graduação em saúde a temática saúde e meio ambiente, adotando como exemplo um curso de enfermagem do interior paulista que inseriu uma disciplina relacionada ao tema. Analisa também o papel do enfermeiro na relação com o meio ambiente segundo a representação social dos alunos, trabalhada a partir do Discurso do Sujeito Coletivo. Nota-se que é fundamental discutir essa temática ambiental entre os profissionais da saúde, a fim de que eles se empoderem desse conhecimento e consigam identificar problemas relacionados à questão ambiental, propondo ações resolutivas e preventivas, juntamente com a comunidade, procurando amenizar os riscos ambientais a que todos estão expostos. Reforça-se a profundidade do papel dos profissionais de saúde diante dos problemas ambientais, buscando a saúde em uma perspectiva ampliada de promoção da saúde.

Adaptative techniques for the human faces detection

This paper presents results from an efficient approach to an automatic detection and extraction of human faces from images with any color, texture or objects in background, that consist in find isosceles triangles formed by the eyes and mouth.

Life with a hemodialysis machine

The aim of the present study was to describe the experience of patients undergoing haemodialysis starting from their own perception. A qualitative perspective using Merleau Ponty's Existential Phenomenology was considered to be the most appropriate methodology for this study. Fifteen patients were interviewed in a haemodialysis unit at a Brazilian teaching hospital. Interviews were based on the question 'What does the experience of living with a haemodialysis machine mean?' Convergences in speeches were grouped into three categories: the machine, improvement in quality of life, reflection on patients' experience. These findings show the existential reality patients experience. A haemodialysis machine dictates their lives: they have to accept strict rules controlled by a team of healthcare providers. They realize it has to be so and there is no way out. It is the only way to get some relief from the symptoms of the disease. The feeling is mostly acceptance of the condition. Healthcare providers' dedication is recognized. Some participants complain bout painful procedures, others deny them, others fantasize the reality. An essential piece of information is the lack of future perspectives; few patients mentioned the possibility of a transplant or the possibility of carrying out their own care. The study may contribute in outlining new perspectives for nurses to understand the needs of patients undergoing haemodialysis. An approach accepting patients' views will probably bring awareness to patients as to the possibilities of helping with their own treatment.

Comparative analysis of human and bovine teeth: Radiographic density

Since bovine teeth have been used as substitutes for human teeth in in vitro dental studies, the aim of this study was to compare the radiographic density of bovine teeth with that of human teeth to evaluate their usability for radiographic studies. Thirty bovine and twenty human teeth were cut transversally in 1 millimeter-thick slices. The slices were X-rayed using a digital radiographic system and an intraoral X-ray machine at 65 kVp and 7 mA. The exposure time (0.08 s) and the target-sensor distance (40 cm) were standardized for all the radiographs. The radiographic densities of the enamel, coronal dentin and radicular dentin of each slice were obtained separately using the histogram tool of Adobe Photoshop 7.0 software. The mean radiographic densities of the enamel, coronal dentin and radicular dentin were calculated by the arithmetic mean of the slices of each tooth. One-way ANOVA demonstrated statistically significant differences for the densities of bovine and human enamel (p < 0.05) and for bovine and human coronal dentin (p < 0.05). No statistically significant differences were found for the bovine and human radicular dentin (p > 0.05). Based on the results, the authors concluded that: a) the radiographic density of bovine enamel is significantly higher than that of human enamel; b) the radiodensity of bovine coronal dentin is statistically lower than the radiodensity of human coronal dentin; bovine radicular dentin is also less radiodense than human radicular dentin, although this difference was not statistically significant; c) bovine teeth should be used with care in radiographic in vitro studies.

Development of a support vector machine-based navigation system for driving a mobile robot through paths in plantations

The use of mobile robots turns out to be interesting in activities where the action of human specialist is difficult or dangerous. Mobile robots are often used for the exploration in areas of difficult access, such as rescue operations and space missions, to avoid human experts exposition to risky situations. Mobile robots are also used in agriculture for planting tasks as well as for keeping the application of pesticides within minimal amounts to mitigate environmental pollution. In this paper we present the development of a system to control the navigation of an autonomous mobile robot through tracks in plantations. Track images are used to control robot direction by preprocessing them to extract image features. Such features are then submitted to a support vector machine in order to find out the most appropriate route. The overall goal of the project to which this work is connected is to develop a real time robot control system to be embedded into a hardware platform. In this paper we report the software implementation of a support vector machine, which so far presented around 93% accuracy in predicting the appropriate route. © 2012 IEEE.

Effect of different methods of cutting fluid application on turning of a difficult-to-machine steel (SAE EV-8)

In this study, different methods of cutting fluid application are used in turning of a difficult-to-machine steel (SAE EV-8). Initially, a semisynthetic cutting fluid was applied using a conventional method (i.e. overhead flood cooling), minimum quantity of cutting fluid, and pulverization. A lubricant of vegetable oil (minimum quantity of lubricant) was also applied using the minimum quantity method. Thereafter, a cutting fluid jet under high pressure (3.0 MPa) was singly applied in the following regions: chip-tool interface, top surface of the chip (between workpiece and chip) and tool-workpiece contact. Moreover, two other methods were used: an interflow between conventional application and chip-tool interface jet (combined method) and, finally, three jets simultaneously applied. In order to carry out these tests, it was necessary to set up a high-pressure system using a piston pump for generating a cutting fluid jet, a venturi for fluid application (minimum quantity of cutting fluid and minimum quantity of lubricant) and a nozzle for cutting fluid pulverization. The output variables analyzed included tool life, surface roughness, cutting tool temperature, cutting force, chip form, chip compression rate and machined specimen microstructure. Among the results, it can be observed that the tool life increases and the cutting force decreases with the application of cutting fluid jet, mainly when it is directed to the chip-tool interface. Excluding the methods involving jet fluid, the conventional method seems to be more efficient than other methods of low pressure, such as minimum quantity of volume and pulverization, when considering just the cutting tool wear. © 2013 IMechE.

Different methods of cutting fluid application on turning of a difficult-to-machine steel

Different methods of cutting fluid application are used on turning of a difficult-tomachine steel (SAE EV-8). A semi-synthetic cutting fluid was applied using a conventional method, minimum quantity of cutting fluid (MQCF), and pulverization. By the minimum quantity method was also applied a lubricant of vegetable oil (MQL). Thereafter, a cutting fluid jet under high pressure (3.0 MPa) was singly applied in the following regions: chip-tool interface; top surface of the chip; and tool-workpiece contact. Two other methods were used: an interflow between conventional application and chip-tool interface jet and, finally, three jets simultaneously applied. In order to carry out these tests, it was necessary to set up a high pressure system using a piston pump for generating a cutting fluid jet, a Venturi for fluid application (MQCF and MQL), and a nozzle for cutting fluid pulverization. The output variables analyzed included tool life, surface roughness, cutting tool temperature, cutting force, chip form, chip compression rate and machined specimen microstructure. It can be observed that the tool life increases and the cutting force decreases with the application of cutting fluid jet, mainly when it is directed to the chip-tool interface. Excluding the methods involving jet fluid, the conventional method seems to be more efficient than other methods of low pressure. © (2013) Trans Tech Publications, Switzerland.

Interfaces culturais de Mallarmé à World Wide Web

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)