In this thesis, exergy based SI engine model optimisation (EBSIEMO) is studied and evaluated. A four-stroke bi-fuel spark ignition (SI) engine is modelled for optimisation of engine performance based upon exergy analysis. An artificial neural network (ANN) is used as an emulator to speed up the optimisation processes. Constrained particle swarm optimisation (CPSO) is employed to identify parameters such as equivalence ratio and ignition time for optimising of the engine performance, based upon maximising 'total availability'. In the optimisation process, the engine exhaust gases standard emission were applied including brake specific CO (BSCO) and brake specific NOx (BSNOx) as the constraints. The engine model is developed in a two-zone model, while considering the chemical synthesis of fuel, including 10 chemical species. A computer code is developed in MATLAB software to solve the equations for the prediction of temperature and pressure of the mixture in each stage (compression stroke, combustion process and expansion stroke). In addition, Intake and exhaust processes are calculated using an approximation method. This model has the ability to simulate turbulent combustion and compared to computational fluid dynamic (CFD) models it is computationally faster and efficient. The selective outputs are cylinder temperature and pressure, heat transfer, brake work, brake thermal and volumetric efficiency, brake torque, brake power (BP), brake specific fuel consumption (BSFC), brake mean effective pressure (BMEP), concentration of CO2, brake specific CO (BSCO) and brake specific NOx (BSNOx). In this model, the effect of engine speed, equivalence ratio and ignition time on performance parameters using gasoline and CNG fuels are analysed. In addition, the model is validated by experimental data using the results obtained from bi-fuel engine tests. Therefore, this engine model was capable to predict, analyse and useful for optimisation of the engine performance parameters. The exergy based four-stroke bi-fuel (CNG and gasoline) spark ignition (SI) engine model (EBSIEM) here is used for analysis of bi-fuel SI engines. Since, the first law of thermodynamic (the FLT), alone is not able to afford an appropriate comprehension into engine operations. Therefore, this thesis concentrates on the SI engine operation investigation using the developed engine model by the second law of thermodynamic (the SLT) or exergy analysis outlook (exergy based SI engine model (EBSIEM)) In this thesis, an efficient approach is presented for the prediction of total availability, brake specific CO (BSCO), brake specific NOx (BSNOx) and brake torque for bi-fuel engine (CNG and gasoline) using an artificial neural network (ANN) model based on exergy based SI engine (EBSIEM) (ANN-EBSIEM) as an emulator to speed up the optimisation processes. In the other words, the use of a well trained an ANN is ordinarily much faster than mathematical models or conventional simulation programs for prediction. The constrained particle swarm optimisation (CPSO)-EBSIEM (EBSIEMO) was capable of optimising the model parameters for the engine performance. The optimisation results based upon availability analysis (the SLT) due to analysing availability terms, specifically availability destruction (that measured engine irreversibilties) are more regarded with higher priority compared to the FLT analysis. In this thesis, exergy based SI engine model optimisation (EBSIEMO) is studied and evaluated. A four-stroke bi-fuel spark ignition (SI) engine is modelled for optimisation of engine performance based upon exergy analysis. An artificial neural network (ANN) is used as an emulator to speed up the optimisation processes. Constrained particle swarm optimisation (CPSO) is employed to identify parameters such as equivalence ratio and ignition time for optimising of the engine performance, based upon maximising 'total availability'. In the optimisation process, the engine exhaust gases standard emission were applied including brake specific CO (BSCO) and brake specific NOx (BSNOx) as the constraints. The engine model is developed in a two-zone model, while considering the chemical synthesis of fuel, including 10 chemical species. A computer code is developed in MATLAB software to solve the equations for the prediction of temperature and pressure of the mixture in each stage (compression stroke, combustion process and expansion stroke). In addition, Intake and exhaust processes are calculated using an approximation method. This model has the ability to simulate turbulent combustion and compared to computational fluid dynamic (CFD) models it is computationally faster and efficient. The selective outputs are cylinder temperature and pressure, heat transfer, brake work, brake thermal and volumetric efficiency, brake torque, brake power (BP), brake specific fuel consumption (BSFC), brake mean effective pressure (BMEP), concentration of CO2, brake specific CO (BSCO) and brake specific NOx (BSNOx). In this model, the effect of engine speed, equivalence ratio and ignition time on performance parameters using gasoline and CNG fuels are analysed. In addition, the model is validated by experimental data using the results obtained from bi-fuel engine tests. Therefore, this engine model was capable to predict, analyse and useful for optimisation of the engine performance parameters. The exergy based four-stroke bi-fuel (CNG and gasoline) spark ignition (SI) engine model (EBSIEM) here is used for analysis of bi-fuel SI engines. Since, the first law of thermodynamic (the FLT), alone is not able to afford an appropriate comprehension into engine operations. Therefore, this thesis concentrates on the SI engine operation investigation using the developed engine model by the second law of thermodynamic (the SLT) or exergy analysis outlook (exergy based SI engine model (EBSIEM)) In this thesis, an efficient approach is presented for the prediction of total availability, brake specific CO (BSCO), brake specific NOx (BSNOx) and brake torque for bi-fuel engine (CNG and gasoline) using an artificial neural network (ANN) model based on exergy based SI engine (EBSIEM) (ANN-EBSIEM) as an emulator to speed up the optimisation processes. In the other words, the use of a well trained an ANN is ordinarily much faster than mathematical models or conventional simulation programs for prediction. The constrained particle swarm optimisation (CPSO)-EBSIEM (EBSIEMO) was capable of optimising the model parameters for the engine performance. The optimisation results based upon availability analysis (the SLT) due to analysing availability terms, specifically availability destruction (that measured engine irreversibilties) are more regarded with higher priority compared to the FLT analysis.

To support the continuously increasing number of mobile telephone users around the world, mobile communication systems have become more advanced and sophisticated in their designs. As a result of the great success with the second generation mobile radio networks, deployment of the third and development of fourth generations, the demand for higher data rates to support available services, such as internet connection, video telephony and personal navigation systems, is ever growing. To be able to meet the requirements regarding bandwidth and number of users, enhancements of existing systems and introductions of conceptually new technologies and techniques have been researched and developed. Although new proposed technologies in theory provide increased network capacity, the backbone of a successful roll-out of a mobile telephone system is inevitably the planning of the network’s cellular structure. Hence, the fundamental aspect to a reliable cellular planning is the knowledge about the physical radio channel for wide sets of different propagation scenarios. Therefore, to study radio wave propagation in typical Australian environments, the Commonwealth Scientific and Industrial Research Organisation (CSIRO) and the Australian Telecommunications Cooperative Research Centre (ATcrc) in collaboration developed a cellular code division multiple access (CDMA) pilot scanner. The pilot scanner measurement equipment enables for radio wave propagation measurements in available commercial CDMA mobile radio networks, which in Australia are usually deployed for extensive rural areas. Over time, the collected measurement data has been used to characterise many different types of mobile radio environments and some of the results are presented in this thesis. The thesis is divided into an introduction section and four parts based on peer-reviewed international research publications. The introduction section presents the reader with some relevant background on channel and propagation modelling. Also, the CDMA scanner measurement system that was developed in parallel with the research results founding this thesis is presented. The first part presents work on the evaluation and development of the different revisions of the Recommendation ITU-R P.1546 point-to-area radio wave propagation prediction model. In particular, the modified application of the terrain clearance angle (TCA) and the calculation method of the effective antenna height are scrutinized. In the second part, the correlation between the smallscale fading characteristics, described by the Ricean K-factor, and the vegetation density in the vicinity of the mobile receiving antenna is investigated. The third part presents an artificial neural network (ANN) based technique incorporated to predict path loss in rural macrocell environments. Obtained results, such as prediction accuracy and training time, are presented for different sized ANNs and different training approaches. Finally, the fourth part proposes an extension of the path loss ANN enabling the model to also predict small-scale fading characteristics.

Doctor of Philosophy / Department of Civil Engineering / Yacoub M. Najjar / Access to databases after the digital revolutions has become easier because large databases are progressively available. Knowledge discovery in these databases via intelligent data analysis technology is a relatively young and interdisciplinary field. In engineering applications, there is a demand for turning low-level data-based knowledge into a high-level type knowledge via the use of various data analysis methods. The main reason for this demand is that collecting and analyzing databases can be expensive and time consuming. In cases where experimental or empirical data are already available, prediction models can be used to characterize the desired engineering phenomena and/or eliminate unnecessary future experiments and their associated costs. Phenomena characterization, based on available databases, has been utilized via Artificial Neural Networks (ANNs) for more than two decades. However, there is a need to introduce new paradigms to improve the reliability of the available ANN models and optimize their predictions through a hybrid decision system. In this study, a new set of ANN modeling approaches/paradigms along with a new method to tackle partially missing data (Query method) are introduced for this purpose. The potential use of these methods via a hybrid decision making system is examined by utilizing seven available databases which are obtained from civil engineering applications. Overall, the new proposed approaches have shown notable prediction accuracy improvements on the seven databases in terms of quantified statistical accuracy measures. The proposed new methods are capable in effectively characterizing the general behavior of a specific engineering/scientific phenomenon and can be collectively used to optimize predictions with a reasonable degree of accuracy. The utilization of the proposed hybrid decision making system (HDMS) via an Excel-based environment can easily be utilized by the end user, to any available data-rich database, without the need for any excessive type of training.

Orientador: Norian Marranghello / Banca: Adilson Gonzaga / Banca: Rodrigo Capobianco Guido / Resumo: A presença de sistemas automatizados é cada vez mais comum para as pessoas. Seus exemplos vão desde máquinas de lavar, que executam praticamente todo o processo de lavagem e secagem de roupas, até linhas de produção em fábricas dos mais diversos produtos. Esses são exemplos de aplicações que exigem pouca interferência humana no processo, já que as etapas realizadas pelos sistemas são bem definidas e iterativas. Porém, outros tipos de processos podem exigir capacidade de discernimento daquele - ou daquilo - que os executam. Para automatizar esse tipo de processo uma das alternativas é o uso de técnicas de inteligência artificial. Esse trabalho visa realizar uma análise comparativa entre técnicas de inteligência artificial, quais sejam Redes Neurais Artificiais e Máquinas de Vetores de Suporte. Com essa análise espera-se estabelecer qual técnica é mais vantajosa para implementação em hardware de sistemas inteligentes, por meio do uso das principais métricas de projeto de circuitos digitais: tamanho do circuito gerado, consumo de energia e desempenho. Para tanto, foram realizados diversos testes com técnicas de pré-processamento e extração de características das imagens para determinar requisitos necessários para o funcionamento do sistema. A partir desses requisitos foram implementadas diversas arquiteturas de sistemas inteligentes para obter-se o classificador mais adequado para resolver o problema. Por fim, o classificador escolhido foi implementado em FPGA na forma de um módulo, o qual se integrará a um sistema maior, para interpretação de imagens digitais para detecção de ervas daninhas em plantações de soja / Abstract: Automated systems have become common for people. Examples range from washing machines, which perform almost the entire cloth washing and drying process, to the production of many products. These are examples of applications that require modest human interference, since the steps taken by the systems are well defined and iterative. However, other processes may require a capacity of judgment of the natural or artificial system performing them. An alternative to automate this kind of process is the use of artificial intelligence techniques. This study aims at a comparative analysis of artificial intelligence techniques, namely Artificial Neural Networks and Support Vector Machines. With this analysis we hope to establish which technique is more advantageous for hardware implementation of an intelligent system, through the use of key metrics for digital circuit design: circuit size, power consumption and performance. Therefore, several tests were performed with image preprocessing and feature extraction techniques to determine requirements for system operation. From these requirements, various architectures for intelligent systems were implemented to obtain the most appropriate classifier to solve the problem. Finally, the chosen classifier was implemented in FPGA as a module to fit into a larger system for digital image interpretation for the detection of weeds in crops of soybeans / Mestre

O labirinto em cruz elevado é um dos aparatos experimentais mais utilizados em avaliações neurobiológicas de ansiedade e defesa de ratos e camundongos. Estudamos aqui o uso de redes neurais artificiais otimizadas por algoritmos genéticos para investigar o comportamento de ratos nesse labirinto. Ao contrário dos demais modelos já propostos, a construção da trajetória do agente virtual independe de dados experimentais conhecidos a priori. Mostramos que, ao utilizar um agente desenvolvido a partir da otimização de uma função de avaliação inspirada no conflito de medo e ansiedade, o modelo pode simular inclusive o efeito causado pela introdução de drogas ansiolíticas e ansiogênicas em ratos (clordiazepóxido 5 mg/kg e semicarbazida 20, 40 e 80 mg/kg). Os resultados das simulações do agente virtual estão de acordo com dados experimentais, revelando que a exploração de braços abertos é reduzida em relação a dos braços fechados, especialmente sob inserção de drogas ansiogênicas, que intensificam o medo do animal. Drogas ansiolíticas, ao contrário, estimulam a exploração. Para finalizar, foi realizada uma investigação aprofundada das trajetórias e redes neurais artificiais dos melhores ratos controle virtuais (que simulam ratos sem efeito de drogas). Conforme sugerem os resultados, a função de avaliação proposta pode conter as características mais relevantes envolvidas no comportamento do rato no labirinto em cruz elevado. / The elevated plus-maze is one of the most used experimental apparatus for neurobiological evaluations of anxiety and defense of rats and mice. We investigate here the use of artificial neural networks otimized by genetic algorithms to nvestigate the behavior of rats in this maze. Unlike other proposed models, the development of the virtual agent\'s trajectory is independent of prior known experimental data. We show that, when using a agent developed from the optimization of a function inspired by the anxiety and fear conflict, the model can even simulate the effect caused by the introduction of anxiolytic and axiogenic drugs in rats (chlordiazepoxide 5 mg/kg and semicarbazide 20, 40 and 80 mg/kg). The results of simulations of the virtual agent agree with experimental data, in which the exploration of open arms is reduced compared to the exploration of enclosed arms, especially under effects of anxiogenic drugs, which enhance the animal fear. Anxiolytic drugs, on the other hand, stimulate exploration. Finally, a detailed investigation of trajectories and artificial neural networks of the best virtual control rats (that simulate rats without drugs) was performed. As the results suggest, the proposed fitness function may contain the most relevant features involved in the behavior of rats in the elevated plus-maze.

A avaliação perceptivo-auditiva tem papel fundamental no estudo e na avaliação da voz, no entanto, por ser subjetiva está sujeita a imprecisões e variações. Por outro lado, a análise acústica permite a reprodutibilidade de resultados, porém precisa ser aprimorada, pois não analisa com precisão vozes com disfonias mais intensas e com ondas caóticas. Assim, elaborar medidas que proporcionem conhecimentos confiáveis em relação à função vocal resulta de uma necessidade antiga dentro desta linha de pesquisa e atuação clínica. Neste contexto, o uso da inteligência artificial, como as redes neurais artificiais, indica ser uma abordagem promissora. Objetivo: Validar um sistema automático utilizando redes neurais artificiais para a avaliação de vozes rugosas e soprosas. Materiais e métodos: Foram selecionadas 150 vozes, desde neutras até com presença em grau intenso de rugosidade e/ou soprosidade, do banco de dados da Clínica de Fonoaudiologia da Faculdade de Odontologia de Bauru (FOB/USP). Dessas vozes, 23 foram excluídas por não responderem aos critérios de inclusão na amostra, assim utilizaram-se 123 vozes. Procedimentos: avaliação perceptivo-auditiva pela escala visual analógica de 100 mm e pela escala numérica de quatro pontos; extração de características do sinal de voz por meio da Transformada Wavelet Packet e dos parâmetros acústicos: jitter, shimmer, amplitude da derivada e amplitude do pitch; e validação do classificador por meio da parametrização, treino, teste e avaliação das redes neurais artificiais. Resultados: Na avaliação perceptivo-auditiva encontrou-se, por meio do teste Coeficiente de Correlação Intraclasse (CCI), concordâncias inter e intrajuiz excelentes, com p = 0,85 na concordância interjuízes e p variando de 0,87 a 0,93 nas concordâncias intrajuiz. Em relação ao desempenho da rede neural artificial, na discriminação da soprosidade e da rugosidade e dos seus respectivos graus, encontrou-se o melhor desempenho para a soprosidade no subconjunto composto pelo jitter, amplitude do pitch e frequência fundamental, no qual obteve-se taxa de acerto de 74%, concordância excelente com a avaliação perceptivo-auditiva da escala visual analógica (0,80 no CCI) e erro médio de 9 mm. Para a rugosidade, o melhor subconjunto foi composto pela Transformada Wavelet Packet com 1 nível de decomposição, jitter, shimmer, amplitude do pitch e frequência fundamental, no qual obteve-se 73% de acerto, concordância excelente (0,84 no CCI), e erro médio de 10 mm. Conclusão: O uso da inteligência artificial baseado em redes neurais artificiais na identificação, e graduação da rugosidade e da soprosidade, apresentou confiabilidade excelente (CCI > 0,80), com resultados semelhantes a concordância interjuízes. Dessa forma, a rede neural artificial revela-se como uma metodologia promissora de avaliação vocal, tendo sua maior vantagem a objetividade na avaliação. / The auditory-perceptual evaluation is fundamental in the study and analysis of voice. This evaluation, however, is subjective and tends to be imprecise and variable. On the other hand, acoustic analysis allows reproducing results, although these results must be refined since the analysis is not precise enough for intense dysphonia or chaotic waves. Therefore, the will to develop measurements allowing reliable knowledge related to vocal function is not new on this research and clinical actuation field. In this context, the use of artificial intelligence such as neural networks seems to be a promising research field. Objective: to validate an automatic system using artificial neural networks for evaluation of vocal roughness and breathiness. Methods: One hundred fifty (150) voices were selected from from Clínica de Fonoaudiologia da Faculdade de Odontologia de Bauru (FOB/USP) database. These voices presented variation from neutral to intense roughness and/or breathiness. Twenty-three of them were excluded since they did not match inclusion criteria. Thus, 123 voices were used for analysis. The procedures include use of auditoryperception based on two scales: visual analog scale of 100 mm and four points numerical scale. Additionally, the characteristics of voice signals were extracted by Wavelet Packet Transform and by analysis of acoustic parameters: jitter, shimmer, derivative amplitude and pitch amplitude. Validation of classifying system was carried out by parameterization, training, test and evaluation of artificial neural networks. Results: In the auditory-perceptual evaluation, excellent interrater (p=0.85) and intrarater (0.87<p<0.93) agreement were obtained by means of Intraclass Correlation Coefficient (ICC) testing. The artificial neural network performance has achieved the best results for breathiness in the subset composed by parameters jitter, pitch amplitude and fundamental frequency. In this case, the neural network obtained a rate of 74%, demonstrating excellent concordance with auditory-perceptual evaluation for visual analog scale (0.80 ICC) and mean error of 9 mm. As for roughness evaluation, the best subset is composed by Wavelet Packet Transform with 1 resolution level, jitter, shimmer, pitch amplitude and fundamental frequency. For this case, a 73% rate was achieved (0.84 ICC) and mean error of 10 mm was obtained. Conclusion: The use of artificial neural networks for roughness and breathiness evaluation present high reliability (ICC&gt;0.80), with results similar to interrater agreement. Thus, the artificial neural network reveals a promising method for vocal evaluation, bringing objective analysis as a strong advantage.

Este trabalho contempla os estudos realizados para elaboração de uma carta de eventos perigosos (hazard) de uma área de aproximadamente 45 km², no município de Ouro Preto/MG, a partir de dados geológicos e geotécnicos, gerados em trabalhos de mapeamento geotécnico, com o uso dos recursos de redes neurais artificiais e da probabilidade condicional. Os dados prévios foram tratados e um conjunto de 15 mapas e cartas elaborado, a saber: topográfico, de substrato rochoso, material inconsolidado, de uso e ocupação, de inventário dos movimentos de massa gravitacionais (escorregamentos translacionais, escorregamentos translacionais tipo de material), de declividade, de rumo da inclinação das encostas, das unidades geológico-geotécnicas, das seções típicas das unidades geológico-geotécnicas, da resistência ao cisalhamento, do contraste de permeabilidade e da superfície potencial de ruptura, associado a uma tabela com as características das unidades geológico-geotécnicas. Os modelos de redes neurais artificiais e probabilidade condicional foram desenvolvidos para o uso em MATLAB utilizando um conjunto de 11 mapas e cartas dentre os citados anteriormente. A análise dos dados prévios frente aos modelos foi desenvolvida no sentido de avaliar a sua qualidade e a sua adequação ao modelo proposto. Concluiu-se sobre a necessidade de dados específicos que nem sempre são gerados em trabalhos rotineiros, como: levantamento da atividade, velocidade, volume e data de ocorrência, entre outros para caracterização das feições de movimentos de massa gravitacionais; estudo detalhado dos parâmetros de resistência dos materiais e das descontinuidades presentes no substrato rochoso; dados de estações pluviométricas para estudos da intensidade e distribuição da chuva na região, entre outras informações. / This work shows the studies developed for elaboration of the landslide hazard map of the area of 45 km², approximately, in the municipality of Ouro Preto, in the state of Minas Gerais, Brazil, from data generated in geotechnical mapping, with the use of artificial neural networks and conditional probability methods. The previous data were processed and was elaborated a set of 15 maps and charts: topographic, lithologies, unconsolidated material, land uses, inventory (landslides, translational slides, translational inventory - type of geological material, slope, slope inclination direction, geological - geotechnical units, typical topographic profile of the geological and geotechnical units, the shear strength categories, hydraulic conductivity contrasts, potential failure surfaces and a table with characteristic of the geological and geotechnical units. The procedures of the artificial neural networks and conditional probability were developed for use in MATLAB using a set of 11 maps among the 15 elaborated. A analysis of the previous data prepared and the data necessary for models was developed to evaluate its suitability. The main conclusion is that the routine mapping and inventories do not consider important attributes, such as activity, movement rate, volume, landslide date and others aspects of the features; detailed study about shear strength of geological materials and discontinuities and rainfall data.

O estudo de inventário tem por objetivo estimar o potencial hidroelétrico de rios ou bacias, analisando várias alternativas propostas de partição de quedas, sendo que cada alternativa contém um conjunto de aproveitamentos hidroelétricos. Essas alternativas são então estudadas individualmente para definição da alternativa ótima, ou seja, a que tem melhor custo beneficio e ao mesmo tempo cause menos danos ambientais. Para essa análise necessitamos calcular a potência de cada aproveitamento específico, assim como a energia gerada, para isso então precisamos conhecer a vazão do rio em estudo, no local desses aproveitamentos. Como a vazão dos rios varia com o tempo, pois depende de variáveis como clima, geologia dos solos, desmatamento, entre outras, se recomenda usar nos cálculos séries longas de vazões médias com no mínimo 30 anos de dados, o problema é que em muitos casos não temos essas séries ou temos séries menores e incompletas, nesse caso então necessitamos estimar os valores ausentes e ruidosos utilizando os dados de estações fluviométricas próximas, para depois transportá-las para o aproveitamento em estudo, para isso utilizamos de técnicas estatísticas de correlação. A ideia nesse trabalho é de utilizarmos redes neurais artificiais ao invés das técnicas convencionais e comparar os resultados obtidos. / The inventory study aims to estimate the hydropower potential of rivers or basins, analyzing several alternative proposals for partition of falls, each of which contains a set of alternative hydroelectric developments. These alternatives are then individually analyzed to define the optimal alternative, namely that which has the best cost benefit while causing less environmental damage. For this analysis we need to calculate the power of each specific use, as well as the energy generated for that then we need to know the flow of the river under study, the location of these usages. As the river flow varies with time because it depends on variables such as climate, geology, soils, deforestation, among others, we recommend using the long series of calculations mean flow at least 30 years of data, the problem is that in many cases we do not have these series or have smaller and incomplete series, in this case then we need to estimate the missing values and noisy data using next gauged stations, and then transport them to use in the study, for this we use statistical correlation techniques. The idea is that we use work instead of the conventional Artificial Neural Network techniques and compare the results.

Este trabalho apresenta o desenvolvimento de algoritmos de adaptação do padrão de marcha com a utilização de redes neurais artificiais para uma órtese ativa para membros inferiores. Trajetórias estáveis são geradas durante o processo de otimização, considerando um gerador de trajetórias baseado no critério do ZMP (Zero Moment Point) e no modelo dinâmico do equipamento. Três redes neurais são usadas para diminuir o tempo de cálculo do modelo e da otimização do ZMP, e reproduzir o gerador de trajetórias analítico. A primeira rede aproxima a dinâmica do modelo fornecendo a variação de torque necessária para a realização do processo de otimização dos parâmetros de adaptação da marcha; a segunda rede trabalha no processo de otimização, fornecendo o parâmetro otimizado de acordo com a interação paciente-órtese; a terceira rede reproduz o gerador de trajetórias para um determinado intervalo de tempo do passo que pode ser repetido para qualquer quantidade de passos. Além disso, um controle do tipo torque calculado acrescido de um controle PD é usado para garantir que as trajetórias atuais estejam seguindo as trajetórias desejadas da órtese. O modelo dinâmico da órtese na sua configuração atual, com forças de interação incluídas, é usado para gerar resultados simulados. / This work deals with neural network-based gait-pattern adaptation algorithms for an active lower limbs orthosis. Stable trajectories are generated during the optimization process, considering a trajectory generator based on the Zero Moment Point criterion and on the dynamic model. Additionally, three neural network are used to decrease the time-consuming computation of the model and ZMP optimization and to reproduce the analitical trajectory generator. The first neural network approximates the dynamic model providing the necessary torque variation to gait adaptation parameters process; the second network works in the optimization procedure, giving the adapting parameter according to orthosis-patient interaction; and the third network replaces the trajectory generation for a stablished step time interval which can be reproduced any time during the walking. Also, a computed torque controller plus the PD controller is designed to guarantee the actual trajectories are following the orthosis desired trajectories. The dynamic model of the actual active orthosis, with interaction forces included, is used to generate simulation results.

Este trabalho apresenta um estudo de classificação de nódulos em mamograma digitalizados através de um classificador de rede neural artificial (RNA). O algoritmo de treinamento de \"backpropagation\" foi utilizado para ajustar os pesos da RNA. O objetivo principal deste trabalho foi determinar um método para analisar e selecionar a melhor configuração de atributos e topologia da RNA para classificar lesões mamárias do tipo nódulo. Foram escolhidas 118 imagens de regiões de interesse (ROI), sendo 68 benignas e 50 malignas de duas bases de imagens: uma do Hospital das Clínicas de Ribeirão Preto, da Universidade de São Paulo, e outra do MIAS-UK (Mammographic Image Analysis Society). O processo completo envolveu quatro etapas: detecção, extração e seleção de atributos, e classificação. Na etapa de detecção, as imagens foram submetidas ao processo combinado das técnicas segmentação de thresholding, morfologia matemática e crescimento de região. Foram extraídos 14 atributos de textura e 14 atributos de forma. Para selecionar os atributos mais discriminantes, foi utilizado o método de Jeffries-Matusita. Foram selecionados três grupos de atributos de forma, três de atributos de textura e três de atributos combinados. Análise pela curva ROC foram dirigidas para avaliar o desempenho do classificador de rede neural artificial (RNA). Os melhores resultados obtidos foram: para o grupo de atributos de forma com 5 unidades escondidas, a área dentro da curva ROC foi de 0.99, taxa de acerto de 98,21%, taxa de especificidade de 98,37% e taxa de sensibilidade de 98.00%; para o grupo de atributos de textura com 4 unidades escondidas, a área dentro da curva foi de 0.98, taxa de acerto de 97,08%, taxa de especificidade de 98,53% e taxa de sensibilidade de 95.11%; para o grupo de atributos combinados de textura e forma com 3 unidades escondidas, a área dentro da curva foi de 0.99, taxa de acerto de 98,21%, taxa de especificidade de 100.00% e taxa de sensibilidade de 95.78%. / This work presents a study of masses classification in digitized mammograms by means of artificial neural network (ANN). The backpropagation training algorithm was used to adjust the weights of ANN. The aim of this work was to determine a methodology to analyze and selection of the best feature subset and ANN topology to classify masses lesions. A total of 118 regions of interest images were chosen (68 benign and 50 malignant lesions) from two image databases: one from \"Hospital das Clínicas de Ribeirão Preto\", at the University of São Paulo, and other from Mammographic lmage Analysis Society (MIAS-UK). The whole process involved four steps: segmentation, feature extraction, selection, and classification. In the first step, the images were submitted to a combined process of thresholding, mathematical morphology, and region growing techniques. In the second step, fourteen texture features and fourteen shape features were extracted. The Jeffries-Matusita method was used to select the best features. The results of this stage were the selection of three shape feature sets, three texture feature sets, and three combined feature sets. The Receiver Operating Characteristic (ROC) analysis were conducted to evaluated the ANN classifier performance. The best result obtained for shape feature set was obtained using a ANN with 5 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 98.37% and sensitivity rate of 98.00%. For texture feature set, the best result was using a ANN with 4 hidden units, the area under ROC curve was of 0.98, classification rate of 97.08%, specificity rate of 98.53% and sensitivity rate of 95.11%. Finally, for the combined feature set (texture and shape) the best result obtained was using a ANN with 3 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 100.00% and sensitivity rate of 95.78%.