Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.

Sistema inteligente para o processamento de imagens digitais intrabucais oclusais

Several are the areas in which digital images are used in solving day-to-day problems. In medicine the use of computer systems have improved the diagnosis and medical interpretations. In dentistry it’s not different, increasingly procedures assisted by computers have support dentists in their tasks. Set in this context, an area of dentistry known as public oral health is responsible for diagnosis and oral health treatment of a population. To this end, oral visual inspections are held in order to obtain oral health status information of a given population. From this collection of information, also known as epidemiological survey, the dentist can plan and evaluate taken actions for the different problems identified. This procedure has limiting factors, such as a limited number of qualified professionals to perform these tasks, different diagnoses interpretations among other factors. Given this context came the ideia of using intelligent systems techniques in supporting carrying out these tasks. Thus, it was proposed in this paper the development of an intelligent system able to segment, count and classify teeth from occlusal intraoral digital photographic images. The proposed system makes combined use of machine learning techniques and digital image processing. We first carried out a color-based segmentation on regions of interest, teeth and non teeth, in the images through the use of Support Vector Machine. After identifying these regions were used techniques based on morphological operators such as erosion and transformed watershed for counting and detecting the boundaries of the teeth, respectively. With the border detection of teeth was possible to calculate the Fourier descriptors for their shape and the position descriptors. Then the teeth were classified according to their types through the use of the SVM from the method one-against-all used in multiclass problem. The multiclass classification problem has been approached in two different ways. In the first approach we have considered three class types: molar, premolar and non teeth, while the second approach were considered five class types: molar, premolar, canine, incisor and non teeth. The system presented a satisfactory performance in the segmenting, counting and classification of teeth present in the images.

Obtenção e caracterização de um compósito de matriz polimérica com carga de resíduos vegetal proveniente do sabugo de milho

The feasibility of using the corn cob to obtain a polymer matrix composite was studied. To obtain the bran, corncob passed the drying process in a solar dryer, and was subsequently triturated in forage and to obtain the different particle sizes, by sieving. Three different grain sizes were used: fine particles (FP) size between 0,10 and 2mm; sized particles (PM) with sizes between 2,10 and 3,35 mm; large particles (PG) sizes between 3,45 and 4,10 mm. Using 20% of residue relative to the resin, the test samples were constructed for characterization of the composite, taking into account thermal and mechanical parameters. The main advantage of the proposed composite is that it has a low density, below the relative resin, about 1.06 kg / m³ for the PG. The composite showed a mechanical behavior less than of the resin to the grain sizes and for all formulations studied. Showed better results for the bending, reaching 25.3 MPa for the PG. The composite also showed be feasible for thermal applications, with thermal conductivity less than 0.21 W / m, ranking as insulation. In terms of homogeneity of the mixture, the most viable grain size is the PF, which also showed improved aesthetics and better processability. This composite can be used to make structures that do not require significant mechanical strength, such as tables, chairs, planks, and solar and wind prototypes, such as ovens and cookers and turbines blades.

Obtenção e caracterização de um compósito de matriz polimérica com carga de resíduos vegetal proveniente do sabugo de milho

The feasibility of using the corn cob to obtain a polymer matrix composite was studied. To obtain the bran, corncob passed the drying process in a solar dryer, and was subsequently triturated in forage and to obtain the different particle sizes, by sieving. Three different grain sizes were used: fine particles (FP) size between 0,10 and 2mm; sized particles (PM) with sizes between 2,10 and 3,35 mm; large particles (PG) sizes between 3,45 and 4,10 mm. Using 20% of residue relative to the resin, the test samples were constructed for characterization of the composite, taking into account thermal and mechanical parameters. The main advantage of the proposed composite is that it has a low density, below the relative resin, about 1.06 kg / m³ for the PG. The composite showed a mechanical behavior less than of the resin to the grain sizes and for all formulations studied. Showed better results for the bending, reaching 25.3 MPa for the PG. The composite also showed be feasible for thermal applications, with thermal conductivity less than 0.21 W / m, ranking as insulation. In terms of homogeneity of the mixture, the most viable grain size is the PF, which also showed improved aesthetics and better processability. This composite can be used to make structures that do not require significant mechanical strength, such as tables, chairs, planks, and solar and wind prototypes, such as ovens and cookers and turbines blades.

Estudo da incorporação de cinza e chamote gerado pela cerâmica vermelha ao próprio processo industrial

The ceramics industry generates waste at various stages of that process, defective products, waste from burning solid fuels, among others. This waste is dumped in landfills, garbage dumps or directly on roads, which has a negative environmental impact. This paper presents a study to incorporate the waste of algaroba wood and chamote (scrap pieces of ceramic already sintered), in to the ceramic material for making sealing blocks. The methodological procedures consist in the characterization of chemical and mineralogical residues, raw materials, and physical-mechanical of the formulations of mixes with clay, silt and waste. By pressing test pieces were produced using a pressure of 200 kgf/cm², varying compositions in the range of 0%, 5%, 10% and 15% by weight of residue. The sintering was performed in a muffle furnace, with the temperature levels of 850 ° C, 900 ° C, 950 ° C, 1000 ° C and 1050 ° C. The evaluated physical and mechanical properties were: Water Absorption, Linear Shrinkage Burning, Apparent Porosity, Apparent Density and Mechanical Resistance to Flexion. Analysis was carried out by Scanning Electron Microscopy on fracture surfaces of the specimens. Evaluation of linear shrinkage property drying and firing , water absorption and mechanical resistance to compression of the sealing blocks 5% wood ash residue, sintered at 900 °C hold temperature in the laboratory the products manufactured on an industrial scale. The main results, it was found on the viability of using the residues of algaroba wood and to confer refractory properties of the ceramic product. The main results, it was concluded feasibility of using the ash residues algaroba wood to impart refractory properties to the ceramic product and the residue of chamote, being derived from the own ceramic product not interfere with the properties, when used in a percentage of up to 5%.Since the residue of chamote being derived from the ceramic product itself had no effect on the properties. Studies in the laboratory have shown that the incorporation of up to 5% of these residues may be adopted as an alternative technology to reduce the environmental impact caused by the industrial sector, without compromising the final properties of the material, since the results on an industrial scale showed absorption values 11.66 and 11.74 of water and waste products respectively, within the parameters of NBR - 15,270, since the mechanical strength was 1.25 MPa and 0.94 MPa respectively for products with and without residue, lower than the minimum required by the technical standard that is 1.5 MPa.

Estudo da incorporação de cinza e chamote gerado pela cerâmica vermelha ao próprio processo industrial

The ceramics industry generates waste at various stages of that process, defective products, waste from burning solid fuels, among others. This waste is dumped in landfills, garbage dumps or directly on roads, which has a negative environmental impact. This paper presents a study to incorporate the waste of algaroba wood and chamote (scrap pieces of ceramic already sintered), in to the ceramic material for making sealing blocks. The methodological procedures consist in the characterization of chemical and mineralogical residues, raw materials, and physical-mechanical of the formulations of mixes with clay, silt and waste. By pressing test pieces were produced using a pressure of 200 kgf/cm², varying compositions in the range of 0%, 5%, 10% and 15% by weight of residue. The sintering was performed in a muffle furnace, with the temperature levels of 850 ° C, 900 ° C, 950 ° C, 1000 ° C and 1050 ° C. The evaluated physical and mechanical properties were: Water Absorption, Linear Shrinkage Burning, Apparent Porosity, Apparent Density and Mechanical Resistance to Flexion. Analysis was carried out by Scanning Electron Microscopy on fracture surfaces of the specimens. Evaluation of linear shrinkage property drying and firing , water absorption and mechanical resistance to compression of the sealing blocks 5% wood ash residue, sintered at 900 °C hold temperature in the laboratory the products manufactured on an industrial scale. The main results, it was found on the viability of using the residues of algaroba wood and to confer refractory properties of the ceramic product. The main results, it was concluded feasibility of using the ash residues algaroba wood to impart refractory properties to the ceramic product and the residue of chamote, being derived from the own ceramic product not interfere with the properties, when used in a percentage of up to 5%.Since the residue of chamote being derived from the ceramic product itself had no effect on the properties. Studies in the laboratory have shown that the incorporation of up to 5% of these residues may be adopted as an alternative technology to reduce the environmental impact caused by the industrial sector, without compromising the final properties of the material, since the results on an industrial scale showed absorption values 11.66 and 11.74 of water and waste products respectively, within the parameters of NBR - 15,270, since the mechanical strength was 1.25 MPa and 0.94 MPa respectively for products with and without residue, lower than the minimum required by the technical standard that is 1.5 MPa.

Avaliação de processo de lodos ativos por batelada seguido de tratamento terciário com ênfase na remoção de matéria orgânica e na sedimentabilidade do lodo

This paper evaluate the performance of a Wastewater Treatment Plant (WWTP) in sequential batch activated sludge modality with tertiary treatment step, located in high temperature region. It also presents the analysis of organic matter’s removal and the evaluation of sludge sedimentation conditions through reactors in bench scale, fed with different substrate’s and biomass’ concentrations, from the WWTP in study. The results showed high efficiency and stability of the treatment process using Sequential Batch Reactors for domestic sewage, even with sudden changes of organic and hydraulic load, reaching more than 90% of efficiency in the removal of biodegradable organic matter. The removal of organic matter and sedimentation tests in bench reactors showed the good performance in respect of the organic matter’s removal, however, the high concentration of micro-organism results in a lower sludge sedimentation rate, which can compromise the quality of the final effluent. The relation Food/Microorganism in the conditions of the WWTP’s current operation showed a value of 0.06 gCOD/gVSS.d. and zonal sedimentation velocity of 0.59 m/h, the great ratio of the concentration of the substrate by biomass concentration, which obtained the maximum operational efficiency, showed a value of 0.09 gCOD/gVSS.d. and zonal sedimentation velocity of 1.4 m/h.

Avaliação de processo de lodos ativos por batelada seguido de tratamento terciário com ênfase na remoção de matéria orgânica e na sedimentabilidade do lodo

This paper evaluate the performance of a Wastewater Treatment Plant (WWTP) in sequential batch activated sludge modality with tertiary treatment step, located in high temperature region. It also presents the analysis of organic matter’s removal and the evaluation of sludge sedimentation conditions through reactors in bench scale, fed with different substrate’s and biomass’ concentrations, from the WWTP in study. The results showed high efficiency and stability of the treatment process using Sequential Batch Reactors for domestic sewage, even with sudden changes of organic and hydraulic load, reaching more than 90% of efficiency in the removal of biodegradable organic matter. The removal of organic matter and sedimentation tests in bench reactors showed the good performance in respect of the organic matter’s removal, however, the high concentration of micro-organism results in a lower sludge sedimentation rate, which can compromise the quality of the final effluent. The relation Food/Microorganism in the conditions of the WWTP’s current operation showed a value of 0.06 gCOD/gVSS.d. and zonal sedimentation velocity of 0.59 m/h, the great ratio of the concentration of the substrate by biomass concentration, which obtained the maximum operational efficiency, showed a value of 0.09 gCOD/gVSS.d. and zonal sedimentation velocity of 1.4 m/h.

Controle ativo de vibração em estruturas inteligentes utilizando um controlador por modos deslizantes com compensação difusa

Smart structures and systems have the main purpose to mimic living organisms, which are essentially characterized by an autoregulatory behavior. Therefore, this kind of structure has adaptive characteristics with stimulus-response mechanisms. The term adaptive structure has been used to identify structural systems that are capable of changing their geometry or physical properties with the purpose of performing a specific task. In this work, a sliding mode controller with fuzzy inference is applied for active vibration control in an SMA two-bar truss. In order to obtain a simpler controller, a polynomial model is used in the control law, while a more sophisticated version, which presents close agreement with experimental data, is applied to describe the SMA behavior of the structural elements. This system has a rich dynamic response and can easily reach a chaotic behavior even at moderate loads and frequencies. Therefore, this approach has the advantage of not only obtaining a simpler control law, but also allows its robustness be evidenced. Numerical simulations are carried out in order to demonstrate the control system performance.

Controle ativo de vibração em estruturas inteligentes utilizando um controlador por modos deslizantes com compensação difusa

Smart structures and systems have the main purpose to mimic living organisms, which are essentially characterized by an autoregulatory behavior. Therefore, this kind of structure has adaptive characteristics with stimulus-response mechanisms. The term adaptive structure has been used to identify structural systems that are capable of changing their geometry or physical properties with the purpose of performing a specific task. In this work, a sliding mode controller with fuzzy inference is applied for active vibration control in an SMA two-bar truss. In order to obtain a simpler controller, a polynomial model is used in the control law, while a more sophisticated version, which presents close agreement with experimental data, is applied to describe the SMA behavior of the structural elements. This system has a rich dynamic response and can easily reach a chaotic behavior even at moderate loads and frequencies. Therefore, this approach has the advantage of not only obtaining a simpler control law, but also allows its robustness be evidenced. Numerical simulations are carried out in order to demonstrate the control system performance.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Implementação de conversor de polarização linear-circular para antenas de microfita usando metasuperfícies

This work aims to propose a new model of metasurface with simplified basic cell, able to convert linearly polarized signals generated by planar antenna array in circularly polarized signals, for the ISM frequency band (2.45 GHz), with good bandwidth of return loss and axial ratio. To study the behavior of the proposed structure, the metasurface is coupled to three different structures. First, initial tests are made with the metasurface coupled to a microstrip antenna in its simple configuration. Then the metasurface is coupled to an array with two elements of patch type. And later it is coupled to an optimized array, that uses a stub in its main feed, to get a better impedance matching. The structures are analyzed numerically through Ansoft HFSS™, and to validate these results, the structures are characterized experimentally. The characteristics of transmissions simulated and measures are presented. A good agreement between simulated and measured results was obtained. The structure proposed here has the advantage of meeting the desired characteristics, with a simple geometry to be built using a low-cost substrate (FR-4).

Implementação de conversor de polarização linear-circular para antenas de microfita usando metasuperfícies

This work aims to propose a new model of metasurface with simplified basic cell, able to convert linearly polarized signals generated by planar antenna array in circularly polarized signals, for the ISM frequency band (2.45 GHz), with good bandwidth of return loss and axial ratio. To study the behavior of the proposed structure, the metasurface is coupled to three different structures. First, initial tests are made with the metasurface coupled to a microstrip antenna in its simple configuration. Then the metasurface is coupled to an array with two elements of patch type. And later it is coupled to an optimized array, that uses a stub in its main feed, to get a better impedance matching. The structures are analyzed numerically through Ansoft HFSS™, and to validate these results, the structures are characterized experimentally. The characteristics of transmissions simulated and measures are presented. A good agreement between simulated and measured results was obtained. The structure proposed here has the advantage of meeting the desired characteristics, with a simple geometry to be built using a low-cost substrate (FR-4).

Método híbrido para projeto de superfícies seletivas em frequência

This thesis presents a hybrid technique of frequency selective surfaces project (FSS) on a isotropic dielectric layer, considering various geometries for the elements of the unit cell. Specifically, the hybrid technique uses the equivalent circuit method in conjunction with genetic algorithm, aiming at the synthesis of structures with response single-band and dual-band. The equivalent circuit method allows you to model the structure by using an equivalent circuit and also obtaining circuits for different geometries. From the obtaining of the parameters of these circuits, you can get the transmission and reflection characteristics of patterned structures. For the optimization of patterned structures, according to the desired frequency response, Matlab™ optimization tool named optimtool proved to be easy to use, allowing you to explore important results on the optimization analysis. In this thesis, numeric and experimental results are presented for the different characteristics of the analyzed geometries. For this, it was determined a technique to obtain the parameter N, which is based on genetic algorithms and differential geometry, to obtain the algebraic rational models that determine values of N more accurate, facilitating new projects of FSS with these geometries. The optimal results of N are grouped according to the occupancy factor of the cell and the thickness of the dielectric, for modeling of the structures by means of rational algebraic equations. Furthermore, for the proposed hybrid model was developed a fitness function for the purpose of calculating the error occurred in the definitions of FSS bandwidths with transmission features single band and dual band. This thesis deals with the construction of prototypes of FSS with frequency settings and band widths obtained with the use of this function. The FSS were initially reviewed through simulations performed with the commercial software Ansoft Designer ™, followed by simulation with the equivalent circuit method for obtaining a value of N in order to converge the resonance frequency and the bandwidth of the FSS analyzed, then the results obtained were compared. The methodology applied is validated with the construction and measurement of prototypes with different geometries of the cells of the arrays of FSS.