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

Sistema inteligente para diagnóstico de patologias na laringe utilizando máquinas de vetor de suporte

The human voice is an important communication tool and any disorder of the voice can have profound implications for social and professional life of an individual. Techniques of digital signal processing have been used by acoustic analysis of vocal disorders caused by pathologies in the larynx, due to its simplicity and noninvasive nature. This work deals with the acoustic analysis of voice signals affected by pathologies in the larynx, specifically, edema, and nodules on the vocal folds. The purpose of this work is to develop a classification system of voices to help pre-diagnosis of pathologies in the larynx, as well as monitoring pharmacological treatments and after surgery. Linear Prediction Coefficients (LPC), Mel Frequency cepstral coefficients (MFCC) and the coefficients obtained through the Wavelet Packet Transform (WPT) are applied to extract relevant characteristics of the voice signal. For the classification task is used the Support Vector Machine (SVM), which aims to build optimal hyperplanes that maximize the margin of separation between the classes involved. The hyperplane generated is determined by the support vectors, which are subsets of points in these classes. According to the database used in this work, the results showed a good performance, with a hit rate of 98.46% for classification of normal and pathological voices in general, and 98.75% in the classification of diseases together: edema and nodules

Máquina de vetores-suporte intervalar

The Support Vector Machines (SVM) has attracted increasing attention in machine learning area, particularly on classification and patterns recognition. However, in some cases it is not easy to determinate accurately the class which given pattern belongs. This thesis involves the construction of a intervalar pattern classifier using SVM in association with intervalar theory, in order to model the separation of a pattern set between distinct classes with precision, aiming to obtain an optimized separation capable to treat imprecisions contained in the initial data and generated during the computational processing. The SVM is a linear machine. In order to allow it to solve real-world problems (usually nonlinear problems), it is necessary to treat the pattern set, know as input set, transforming from nonlinear nature to linear problem. The kernel machines are responsible to do this mapping. To create the intervalar extension of SVM, both for linear and nonlinear problems, it was necessary define intervalar kernel and the Mercer s theorem (which caracterize a kernel function) to intervalar function

Predição de promotores de Bacillus subtilis usando técnicas de aprendizado de máquina

One of the most important goals of bioinformatics is the ability to identify genes in uncharacterized DNA sequences on world wide database. Gene expression on prokaryotes initiates when the RNA-polymerase enzyme interacts with DNA regions called promoters. In these regions are located the main regulatory elements of the transcription process. Despite the improvement of in vitro techniques for molecular biology analysis, characterizing and identifying a great number of promoters on a genome is a complex task. Nevertheless, the main drawback is the absence of a large set of promoters to identify conserved patterns among the species. Hence, a in silico method to predict them on any species is a challenge. Improved promoter prediction methods can be one step towards developing more reliable ab initio gene prediction methods. In this work, we present an empirical comparison of Machine Learning (ML) techniques such as Na¨ýve Bayes, Decision Trees, Support Vector Machines and Neural Networks, Voted Perceptron, PART, k-NN and and ensemble approaches (Bagging and Boosting) to the task of predicting Bacillus subtilis. In order to do so, we first built two data set of promoter and nonpromoter sequences for B. subtilis and a hybrid one. In order to evaluate of ML methods a cross-validation procedure is applied. Good results were obtained with methods of ML like SVM and Naïve Bayes using B. subtilis. However, we have not reached good results on hybrid database

Produção de grês porcelanato a partir de matérias-primas do estado da Bahia

The State Bahia, Brazil, presents different geological sites it with a very expressive variety minerals. It is situated among the very important States which produces minerals for industries, such as pointed aggregate, ornamentals stones and ceramics raw materials. Nowadays only four companies producting ceramics tiles. Porcelainized stoneware tiles is one of the noblest ceramics, depicting low water absorption (typically below of 0,5%), in addition to excellent staining resistance and mechanical strength. The present work aims at investigating the potential of local raw materials for the production of porcelainized stoneware tiles. For this purpose, these materials were characterized by X-ray fluorescence, X-ray diffraction, particle size analysis, thermal gravimetric analysis, thermal differential analysis and dilatometric analysis. Admixtures containing different compositions were prepared and fired at four temperatures, 1100 ºC, 1150 ºC, 1200 ºC and 1250 ºC with isotherm for 60 minute and heathing rate of 5 oC/min. After firing the samples, they were characterized by water absorption tests, linear retraction, analysis, apparent porosity, apparent specific mass, flexural strength, and microstructural analysis by X-ray diffraction and scanning electron microscopy . The results revealed three ceramics with porcelainized stoneware tiles characteristics and porcelain tile will be produce from raw materials originated in the State of Bahia

Biomecânica e otimização topológica com H-adaptatividade em implantes dentários nitretados a plasma em cátodo oco

In recent years there has been a significant growth in technologies that modify implant surfaces, reducing healing time and allowing their successful use in areas with low bone density. One of the most widely used techniques is plasma nitration, applied with excellent results in titanium and its alloys, with greater frequency in the manufacture of hip, ankle and shoulder implants. However, its use in dental implants is very limited due to high process temperatures (between 700 C o and 800 C o ), resulting in distortions in these geometrically complex and highly precise components. The aim of the present study is to assess osseointegration and mechanical strength of grade II nitrided titanium samples, through configuration of hollow cathode discharge. Moreover, new formulations are proposed to determine the optimum structural topology of the dental implant under study, in order to perfect its shape, make it efficient, competitive and with high definition. In the nitriding process, the samples were treated at a temperature of 450 C o and pressure of 150 Pa , during 1 hour of treatment. This condition was selected because it obtains the best wettability results in previous studies, where different pressure, temperature and time conditions were systematized. The samples were characterized by X-ray diffraction, scanning electron microscope, roughness, microhardness and wettability. Biomechanical fatigue tests were then conducted. Finally, a formulation using the three dimensional structural topology optimization method was proposed, in conjunction with an hadaptive refinement process. The results showed that plasma nitriding, using the hollow cathode discharge technique, caused changes in the surface texture of test specimens, increases surface roughness, wettability and microhardness when compared to the untreated sample. In the biomechanical fatigue test, the treated implant showed no flaws, after five million cycles, at a maximum fatigue load of 84.46 N. The results of the topological optimization process showed well-defined optimized layouts of the dental implant, with a clear distribution of material and a defined edge

Síntese de pigmentos cerâmicos inorgânicos nanométricos pela rota dos precursores poliméricos

Considering the constant evolution of technology in growth and the need for production techniques in the ceramics area to move forward together, we sought in this study, the research and development of polymeric precursor method to obtain inorganic ceramic pigments. Method that provides quality to obtain the precursor powders of oxides and pigments at the same time, offers time and cost advantages, such as reproducibility, purity and low temperature heat treatment, control of stoichiometry. This work used chromium nitrate and iron nitrate as precursors. The synthesis is based on the dissolution of citric acid as a complexing agent, addition of metal oxides, such as ion chromophores; polymerization with ethylene glycol and doping with titanium oxide. Passing through precalcination, breakdown, thermal treatments at different temperatures of calcination (700 to 1100 oC), resulting in pigments: green for chromium oxide deposited on TiO2 (CrTiO3) and orange for iron oxide deposited on TiO2 ( FeTiO3). Noticing an increase of opacity with increasing temperature. Were performed thermal analysis (TG and ATD) in order to evaluate its thermodecomposition. The powders were also characterized by techniques such as XRD, revealing the formation of crystalline phases such as iron titanate (FeTiO3) and chrome titanate (CrTiO3), SEM, demonstrating formation of rounded particles for both oxides and Spectroscopy in the UV-Visible Region, verifying the potential variation and chromaticity os pigments. Thus, the synthesized oxides were within the requirements to be applied as pigments and shown to be possible to propose its use in ceramic materials

Fresamento com ar quente: uma proposta para minimizar a formação de trincas térmicas em ferramentas de metal duro

This work presents the results, analyses and conclusions about a study carried out with objective of minimizing the thermal cracks formation on cemented carbide inserts during face milling. The main focus of investigation was based on the observation that milling process is an interrupted machining process, which imposes cyclic thermal loads to the cutting tool, causing frequent stresses changes in its superficial and sub-superficial layers. These characteristics cause the formation of perpendicular cracks from cutting edge which aid the cutting tool wear, reducing its life. Several works on this subject emphasizing the thermal cyclic behavior imposed by the milling process as the main responsible for thermal cracks formation have been published. In these cases, the phenomenon appears as a consequence of the difference in temperature experienced by the cutting tool with each rotation of the cutter, usually defined as the difference between the temperatures in the cutting tool wedge at the end of the cutting and idle periods (T factor). Thus, a technique to minimize this cyclic behavior with objective of transforming the milling in an almost-continuous process in terms of temperature was proposed. In this case, a hot air stream was applied into the idle period, during the machining process. This procedure aimed to minimize the T factor. This technique was applied using three values of temperature from the hot air stream (100, 350 e 580 oC) with no cutting fluid (dry condition) and with cutting fluid mist (wet condition) using the hot air stream at 580oC. Besides, trials at room temperature were carried out. Afterwards the inserts were analyzed using a scanning electron microscope, where the quantity of thermal cracks generated in each condition, the wear and others damages was analyzed. In a general way, it was found that the heating of the idle period was positive for reducing the number of thermal cracks during face milling with cemented carbide inserts. Further, the cutting fluid mist application was effective in reducing the wear of the cutting tools.

Medida indireta de temperatura de corpos imersos em plasma

O gradiente térmico da superfície para o interior do sólido depende da taxa de colisões das partículas e da condutividade térmica do material utilizado. Quando um sólido é imerso em plasma, a transferência de energia ocorre por radiação e colisões das partículas sobre a superfície do material. Dependendo da taxa de colisões das particulas e da condutividade térmica do sólido existirão gradientes térmicos da superfície para o interior das amostras, ocorrendo picos térmicos na superficie, ou seja, o aquecimento pontual nas regiões de colisões. A fim de estudar esse efeito, amostras de aço rápido AISI M35 cujos valores de dureza são fortemente sensíveis à temperatura de revenimento, foram utilizadas como micro sensores térmicos. Amostras foram temperadas em forno resistivo e, em seguida, parte das mesmas foram revenidas em forno resistivo e a outra parte em plasma. A partir do gráfico da dureza (Hv) em função da temperatura (T) das amostras revenidas em forno resistivo foi possível obter uma função Hv(T) para determinação indireta do perfil térmico das amostras tratadas em plasma. As amostras foram revenidas em plasma utilizando temperatura de referência igual a 550 oC. Em seguida foi obtido o perfil de dureza dessas amostras ao longo da seção transversal e, subsequentemente, o perfil de temperatura. Verificou-se que amostras tratadas em plasma, ao contrário daquelas tratadas em forno resistivo, apresentaram gradiente de temperatura da superfície para o núcleo. Além disso, verificou-se que as amostras tratadas em configuração planar apresentaram gradientes térmicos inferiores àquelas tratadas em configuração cátodo oco, variando de 20 a 120 °C, respectivamente

Estudo da incorporação de resíduo industrial polimérico ao CAP

This work presents the incorporation of an industrial polymeric waste into a petroleum asphalt cement with penetration grade 50-60 (CAP 50-60). The main goal of this research is the development of a polymer-modified asphalt, with improvements in its physical properties, in order to obtain a more resistant material to the traffic loads. Furthermore, the use of this polymeric waste will result in economic and environmental benefits. The CAP 50-60 used in this research was kindly supplied by LUBNOR Lubrificantes e Derivados de Petróleo do Nordeste (produced in Fazenda Belém Aracati - Ceará) and the industrial polymeric waste was provided by a button manufacturer industry, located in Rio Grande do Norte state. This polymeric waste represents an environmental problem due to its difficulty in recycling and disposal, being necessary the payment by the industry to a landfill. The difficulty in its reuse is for being this material a termofixed polymer, as a result, the button chips resulting from the molding process cannot be employed for the same purpose. The first step in this research was the characterization of the polymeric waste, using Differential Scanning Calorimetry (DSC) Infrared spectroscopy (IR spectroscopy), and Thermogravimetric analysis (TGA). Based on the results, the material was classified as unsaturated polyester. After, laboratory experiments were accomplished seeking to incorporate the polymeric waste into the asphalt binder according to a 23 experimental factorial design, using as main factors: the polymer content (2%, 7% and 14%), the temperature of the mixture (140 and 180 oC) and the reaction time (20 and 60 minutes). The characterization of the polymer-modified asphalt was accomplished by traditional tests, such as: penetration, ring and ball softening point, viscosity, ductility and flash point temperature. The obtained results demonstrated that the addition of the polymeric waste into the asphalt binder modified some of its physical properties. However, this addition can be considered as a feasible alternative for the use of the polymeric waste, which is a serious environmental and technological problem.

Avaliação da secagem do bagaço de cajá usando planejamento fatorial composto central

This work deals with the kinetics assay of Cajá (Spondias mombin L.) bagasse drying by an experimental design using a tray dryer. In order to add-value to this product a kinetic study has been carried out. A central composite experimental design has been carried out to evaluate the influence of the operational variables: input air temperature (55; 65 e 75ºC); the drying air velocity (3.2; 4.6 e 6.0 m/s) and the fixed bed thickness (0.8; 1.2 e 1.6 cm) and as response variable the the moisture content (dry basis). The results showed that the diffusional Fick model fitted quite well the experimental data. The best condition found has been input air temperature of 75ºC, drying air velocity of 6.0 m/s as well as fixed bed thickness of 0.8 cm. The experimental design assay showed that the main effects as well as the second ones were significant at 95% confindance level. The best operational condition according to statistical planning was 75 oC input air temperature, 6.0 m.s-1 drying air velocity and 0.8 cm fixed bed thickness. In this case, the equilibrium moisture content (1.3% dry basis) occured at 220 minutes

Montagem e operação de um secador pneumático tipo flash

In this work, a pneumatic dryer has been designed and assembled in laboratory scale in order to study and evaluate configurations more efficient for application in drying of important materials of Northeast region in Brazil. The equipment was tested with drying of corn and rice grains, in conditions of temperature and air velocity at 80 oC and 35 m/s, respectively. For this type of dryer, it is recommended to work at temperatures above 200 °C and air velocity with higher dynamic pressure. However, even under operating conditions below what it is recommended, the results obtained with the pneumatic dryer were satisfactory. In addition, experiments of drying were performed by using a cabinet dryer (batch dryer) under the same conditions used in the pneumatic dryer. Flash one curves for the corn were fitted satisfactorily by applying of the Lewis model, while a better agreement was found for rice by using the Page model. The data obtained with both drying processes allowed to compare the performance between pneumatic and batch dryers. In respect to drying rate, the pneumatic dryer presented a similar performance to the batch dryer during processing with corn and a superior performance to the last one during processing with rice. Therefore, it was possible to verify that the pneumatic dryer assembled in this preliminar study can be applied for different materials and under different operating conditions

Avaliação da capacidade de adsorção do CO2 em zeólita 12X com gases sintéticos e originados da pirólise do lodo de esgoto

This work depicts a study of the adsorption of carbon dioxide on zeolite 13X. The activities were divided into four stages: study batch adsorption capacity of the adsorbent with synthetic CO2 (4%), fixed bed dynamic evaluation with the commercial mixture of gases (4% CO2, 1.11% CO, 1 2% H2, 0.233% CH4, 0.1% C3, 0.0233% C4 argon as inert closing balance), fixed bed dynamic modeling and evaluation of the breakthrough curve of CO2 originated from the pyrolysis of sewage sludge. The sewage sludge and the adsorbent were characterized by analysis TG / DTA, SEM, XRF and BET. Adsorption studies were carried out under the following operating conditions: temperature 40 °C (for the pyrolysis of the sludge T = 600 °C), pressures of 0.55 to 5.05 bar (batch process), flow rate of the gaseous mixture between 50 - 72 ml/min and the adsorbent masses of 10, 15 and 20 g (fixed bed process). The time for the adsorption batch was 7 h and on the fixed bed was around 180 min. The results of this study showed that in batch adsorption process step with zeolite 13X is efficient and the mass of adsorbed CO2 increases with the increases pressure, decreases with temperature increases and rises due the increase of activation temperature adsorbent. In the batch process were evaluated the breakthrough curves, which were compared with adsorption isotherms represented by the models of Langmuir, Freündlich and Toth. All models well adjusted to the experimental points, but the Langmuir model was chosen in view of its use in the dynamic model does not have implications for adsorption (indeterminacy and larger number of parameters such as occurred with others) in solving the equation. In the fixed bed dynamic study with the synthetic gas mixture, 20 g of mass adsorbent showed the maximum adsorption percentage 46.7% at 40 °C temperature and 50 mL/min of flow rate. The model was satisfactorily fitted to the three breakthrough curves and the parameters were: axial dispersion coefficient (0.0165 dm2/min), effective diffusivity inside the particle (dm2/min 0.0884) and external transfer coefficient mass (0.45 dm/min). The breakthrough curve for CO2 in the process of pyrolysis of the sludge showed a fast saturation with traces of aerosols presents in the gas phase into the fixed bed under the reaction process

Estudo da influência da temperatura na degradação termoquímica da biomassa de avelós

The bio-oil obtained from the pyrolysis of biomass has appeared as inter-esting alternative to replace fossil fuels. The aim of this work is to evaluate the influence of temperature on the yield of products originating from the pyrolysis process of the powder obtained from the dried twigs of avelós (Euphorbia tirucalli), using a rotating cylinder reactor in laboratory scale. The biomass was treated and characterized by: CHNS, moisture, volatiles, fixed carbon and ashes, as well as evaluation of lignin, cellulose and hemicellulose, besides other instrumental techniques such as: FTIR, TG/DTG, DRX, FRX and MEV. The activation energy was evaluated in non-isothemichal mode with heating rates of 5 and 10 oC/min. The obtained results showed biomass as feedstock with potential for biofuel production, because presents a high organic matter content (78,3%) and fixed-carbon (7,11%). The activation energy required for the degradation of biomass ranged between 232,92 392,84 kJ/mol, in the temperature range studied and heating rate of 5 and 10°C/min. In the pyrolysis process, the influence of the reaction temperature was studied (350-520 ° C), keeping constant the other variables, such as, the flow rate of carrier gas, the centrifugal speed for the bio-oil condensationa, the biomass flow and the rotation of the reactor. The maximum yield of bio-oil was obtained in the temperature of 450°C. In this temperature, the results achieved where: content of bio-oil 8,12%; char 32,7%; non-condensed gas 35,4%; losts 23,8%; gross calorific value 3,43MJ/kg; pH 4,93 and viscosity 1,5cP. The chromatographic analysis of the bio-oil produced under these conditions shows mainly the presence of phenol (17,71%), methylciclopentenone (10,56%) and dimethylciclopentenone (7,76%)

Estudo da influência da temperatura na degradação termoquímica da biomassa de avelós (euphorbia tirucalli Linn)

The bio-oil obtained from the pyrolysis of biomass has appeared as inter-esting alternative to replace fossil fuels. The aim of this work is to evaluate the influence of temperature on the yield of products originating from the pyrolysis process of the powder obtained from the dried twigs of avelós (Euphorbia tirucalli), using a rotating cylinder reactor in laboratory scale. The biomass was treated and characterized by: CHNS, moisture, volatiles, fixed carbon and ashes, as well as evaluation of lignin, cellulose and hemicellulose, besides other instrumental techniques such as: FTIR, TG/DTG, DRX, FRX and MEV. The activation energy was evaluated in non-isothemichal mode with heating rates of 5 and 10 oC/min. The obtained results showed biomass as feedstock with potential for biofuel production, because presents a high organic matter content (78,3%) and fixed-carbon (7,11%). The activation energy required for the degradation of biomass ranged between 232,92 392,84 kJ/mol, in the temperature range studied and heating rate of 5 and 10°C/min. In the pyrolysis process, the influence of the reaction temperature was studied (350-520 ° C), keeping constant the other variables, such as, the flow rate of carrier gas, the centrifugal speed for the bio-oil condensationa, the biomass flow and the rotation of the reactor. The maximum yield of bio-oil was obtained in the temperature of 450°C. In this temperature, the results achieved where: content of bio-oil 8,12%; char 32,7%; non-condensed gas 35,4%; losts 23,8%; gross calorific value 3,43MJ/kg; pH 4,93 and viscosity 1,5cP. The chromatographic analysis of the bio-oil produced under these conditions shows mainly the presence of phenol (17,71%), methylciclopentenone (10,56%) and dimethylciclopentenone (7,76%)