Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-03T23:48:41Z No. of bitstreams: 1 EdsonJacksonDeMedeirosNeto_DISSERT.pdf: 2349422 bytes, checksum: 58dbff032ce7a77c69ab57cce418be2d (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-07T19:55:39Z (GMT) No. of bitstreams: 1 EdsonJacksonDeMedeirosNeto_DISSERT.pdf: 2349422 bytes, checksum: 58dbff032ce7a77c69ab57cce418be2d (MD5) / Made available in DSpace on 2016-06-07T19:55:39Z (GMT). No. of bitstreams: 1 EdsonJacksonDeMedeirosNeto_DISSERT.pdf: 2349422 bytes, checksum: 58dbff032ce7a77c69ab57cce418be2d (MD5) Previous issue date: 2015-11-09 / O grande volume de dados gerados como resultado da supervis?o de processos de automa??o na ind?stria gerou como consequ?ncia um vasto espa?o de armazenamento em disco, assim como dificuldade na transmiss?o destes dados por links de telecomunica??es. Os algoritmos de compress?o com perda de dados surgiram na d?cada de 90 com intuito de solucionar estes problemas, passando a serem utilizados em sistemas de supervis?o industrial para a compress?o de dados em tempo real. Para isso estes foram projetados para eliminar informa??es redundantes e indesejadas de forma simples e eficiente. No entanto, os par?metros destes algoritmos necessitam de serem configurados para cada vari?vel de processo, tornando invi?vel a configura??o manual em caso de sistemas que supervisionam milhares de vari?veis. Nesse contexto este trabalho prop?e o algoritmo Adaptive Swinging Door Trending, que consiste numa adapta??o do Swinging Door Trending, em que seus principais par?metros s?o ajustados dinamicamente atrav?s da an?lise de tend?ncias do sinal. Prop?e-se tamb?m uma an?lise comparativa de desempenho dos algoritmos de compress?o com perda de dados aplicados sobre vari?veis de processo de s?ries temporais e cartas dinamom?tricas de fundo de po?o. Os algoritmos abordados para efeito comparativos foram os lineares por partes e os de transformadas. / The great amount of data generated as the result of the automation and process supervision in industry implies in two problems: a big demand of storage in discs and the difficulty in streaming this data through a telecommunications link. The lossy data compression algorithms were born in the 90?s with the goal of solving these problems and, by consequence, industries started to use those algorithms in industrial supervision systems to compress data in real time. These algorithms were projected to eliminate redundant and undesired information in a efficient and simple way. However, those algorithms parameters must be set for each process variable, becoming impracticable to configure this parameters for each variable in case of systems that monitor thousands of them. In that context, this paper propose the algorithm Adaptive Swinging Door Trending that consists in a adaptation of the Swinging Door Trending, as this main parameters are adjusted dynamically by the analysis of the signal tendencies in real time. It?s also proposed a comparative analysis of performance in lossy data compression algorithms applied on time series process variables and dynamometer cards. The algorithms used to compare were the piecewise linear and the transforms.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-10T00:04:44Z No. of bitstreams: 1 LeandroLuttianeDaSilvaLinhares_TESE.pdf: 2400561 bytes, checksum: 3693662adcc0c23b5063f51b23d9b6c5 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-10T22:50:22Z (GMT) No. of bitstreams: 1 LeandroLuttianeDaSilvaLinhares_TESE.pdf: 2400561 bytes, checksum: 3693662adcc0c23b5063f51b23d9b6c5 (MD5) / Made available in DSpace on 2016-06-10T22:50:22Z (GMT). No. of bitstreams: 1 LeandroLuttianeDaSilvaLinhares_TESE.pdf: 2400561 bytes, checksum: 3693662adcc0c23b5063f51b23d9b6c5 (MD5) Previous issue date: 2015-09-03 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES) / O grande interesse pela identifica??o n?o linear de sistemas din?micos deve-se, principalmente, ao fato de que uma grande quantidade dos sistemas reais s?o complexos e precisam ter suas n?o linearidades consideradas para que seus modelos possam ser utilizados com sucesso em aplica??es, por exemplo, de controle, predi??o, infer?ncia, entre outros. O presente trabalho analisa a aplica??o das redes Fuzzy Wavelet Neural Network (FWNN) na identifica??o de sistemas n?o lineares sujeitos a ru?dos e outliers. Esses elementos, geralmente, influenciam no procedimento de identifica??o, ocasionando interpreta??es err?neas em rela??o ao comportamento din?mico do sistema. A FWNN combina, em uma ?nica estrutura, a capacidade de tratar incertezas da l?gica fuzzy, as caracter?sticas de multirresolu??o da teoria wavelet e as habilidades de aprendizado e generaliza??o das redes neurais artificiais. Normalmente, o aprendizado dessas redes ? realizado por algum m?todo baseado em gradiente, tendo o erro m?dio quadr?tico como fun??o de custo. Este trabalho avalia a substitui??o dessa tradicional fun??o por uma medida de similaridade da Teoria da Informa??o, denominada correntropia. Esta medida de similaridade permite que momentos estat?sticos de ordem superior possam ser considerados durante o processo de treinamento. Por esta raz?o, ela se torna mais apropriada para distribui??es de erro n?o gaussianas e faz com que o treinamento apresente menor sensibilidade ? presen?a de outliers. Para avaliar esta substitui??o, modelos FWNN s?o obtidos na identifica??o de dois estudos de caso: um sistema real n?o linear, consistindo em um tanque de m?ltiplas se??es, e um sistema simulado baseado em um modelo biomec?nico da articula??o do joelho humano. Os resultados obtidos demonstram que a utiliza??o da correntropia, como fun??o custo no algoritmo de retropropaga??o do erro, torna o procedimento de identifica??o utilizando redes FWNN mais robusto aos outliers. Entretanto, isto somente pode ser alcan?ado a partir do ajuste adequado da largura do kernel gaussiano da correntropia. / The great interest in nonlinear system identification is mainly due to the fact that a large amount of real systems are complex and need to have their nonlinearities considered so that their models can be successfully used in applications of control, prediction, inference, among others. This work evaluates the application of Fuzzy Wavelet Neural Networks (FWNN) to identify nonlinear dynamical systems subjected to noise and outliers. Generally, these elements cause negative effects on the identification procedure, resulting in erroneous interpretations regarding the dynamical behavior of the system. The FWNN combines in a single structure the ability to deal with uncertainties of fuzzy logic, the multiresolution characteristics of wavelet theory and learning and generalization abilities of the artificial neural networks. Usually, the learning procedure of these neural networks is realized by a gradient based method, which uses the mean squared error as its cost function. This work proposes the replacement of this traditional function by an Information Theoretic Learning similarity measure, called correntropy. With the use of this similarity measure, higher order statistics can be considered during the FWNN training process. For this reason, this measure is more suitable for non-Gaussian error distributions and makes the training less sensitive to the presence of outliers. In order to evaluate this replacement, FWNN models are obtained in two identification case studies: a real nonlinear system, consisting of a multisection tank, and a simulated system based on a model of the human knee joint. The results demonstrate that the application of correntropy as the error backpropagation algorithm cost function makes the identification procedure using FWNN models more robust to outliers. However, this is only achieved if the gaussian kernel width of correntropy is properly adjusted.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-14T20:06:09Z No. of bitstreams: 1 TiagoAlvesDeAlmeida_DISSERT.pdf: 4023553 bytes, checksum: 78962742727907f1310638eedf05cc38 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-15T23:24:57Z (GMT) No. of bitstreams: 1 TiagoAlvesDeAlmeida_DISSERT.pdf: 4023553 bytes, checksum: 78962742727907f1310638eedf05cc38 (MD5) / Made available in DSpace on 2016-06-15T23:24:57Z (GMT). No. of bitstreams: 1 TiagoAlvesDeAlmeida_DISSERT.pdf: 4023553 bytes, checksum: 78962742727907f1310638eedf05cc38 (MD5) Previous issue date: 2015-12-17 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES) / Agarramento em v?lvulas ? um problema muito comum em malhas de controle e geralmente ? a principal causa do mau desempenho de sistemas industriais. Os efeitos desta n?o linearidade mais comumente observados s?o oscila??es nas vari?veis de processo. Para contornar os efeitos indesej?veis, compensadores de atrito t?m sido propostos, com o objetivo de reduzir a variabilidade na sa?da. Neste trabalho ? analisada a compensa??o do atrito em v?lvulas de controle pneum?ticas por meio de uma t?cnica de lineariza??o por realimenta??o. O modelo da v?lvula utilizado inclui tanto zona morta quanto salto. Resultados de simula??o mostram que o uso desse modelo mais completo resulta em controladores com desempenho superior. O m?todo ? tamb?m comparado por meio de simula??es com o m?todo conhecido como Refor?o Constante (CR), bastante utilizado neste problema. / In control loops valve stiction is a very common problem. Generally, it is one of main causes of poor performance of industrial systems. Its most commonly observed effect is oscillation in the process variables. To circumvent the undesirable effects, friction compensators have been proposed in order to reduce the variability in the output. This work analyzes the friction compensation in pneumatic control valves by using feedback linearization technique. The valve model includes both dead zone and jump. Simulations show that the use of this more complete model results in controllers with superior performance. The method is also compared through simulations with the method known as Constant Reinforcement (CR), widely used in this problem.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-21T19:35:53Z No. of bitstreams: 1 AluisioIgorRegoFontes_TESE.pdf: 3702181 bytes, checksum: ebee4d30550394d35c706823dc2169ae (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-22T21:45:56Z (GMT) No. of bitstreams: 1 AluisioIgorRegoFontes_TESE.pdf: 3702181 bytes, checksum: ebee4d30550394d35c706823dc2169ae (MD5) / Made available in DSpace on 2016-06-22T21:45:56Z (GMT). No. of bitstreams: 1 AluisioIgorRegoFontes_TESE.pdf: 3702181 bytes, checksum: ebee4d30550394d35c706823dc2169ae (MD5) Previous issue date: 2015-09-11 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES) / A extra??o de informa??es de sinais aleat?rios ? um problema frequente e relevante em muitas aplica??es de processamento digital de sinais. Nos ?ltimos anos, diferentes m?todos t?m sido utilizados para a parametriza??o de sinais ou obten??o de descritores eficientes de suas caracter?sticas. Quando os sinais aleat?rios possuem propriedades es- tat?sticas cicloestacion?rias, as Fun??es de Autocorrela??o C?clica (CAF) e a Densidade Espectral C?clica (SCD) podem ser utilizadas na obten??o de informa??es cicloestacion?- rias de segunda ordem. Entretanto, em sinais n?o-gaussianos, as informa??es cicloestaci- on?rias de segunda ordem s?o fracas e, neste caso a an?lise cicloestacion?ria deve ocorrer sobre informa??es estat?sticas de ordem superior. Este trabalho prop?e uma nova ferra- menta matem?tica para a an?lise cicloestacion?ria de ordem superior baseada na fun??o de correntropia. Especificamente, a teoria de an?lise cicloestacion?ria ? revisitada sob um enfoque de teoria da informa??o, e as Fun??es de Correntropia C?clica (CCF) e Densidade Espectral de Correntropia C?clica (CCSD) s?o definidas. ? comprovado analiticamente que a CCF cont?m informa??es de momentos cicloestacion?rios de segunda ordem e de ordem superior, sendo uma generaliza??o da CAF. O desempenho dessas novas fun??es, na extra??o de caracter?sticas cicloestacion?rias de ordem superior, ? analisado em um cen?rio de comunica??o sem fio com ru?do n?o-gaussiano. / Information extraction is a frequent and relevant problem in digital signal processing. In the past few years, different methods have been utilized for the parameterization of signals and the achievement of efficient descriptors. When the signals possess statistical cyclostationary properties, the Cyclic Autocorrelation Function (CAF) and the Spectral Cyclic Density (SCD) can be used to extract second-order cyclostationary information. However, second-order cyclostationary information is poor in nongaussian signals, as the cyclostationary analysis in this case should comprise higher-order statistical information. This paper proposes a new mathematical tool for the higher-order cyclostationary analysis based on the correntropy function. Specifically, the cyclostationary analysis is revisited focusing on the information theory, while the Cyclic Correntropy Function (CCF) and Cyclic Correntropy Spectral Density (CCSD) are also defined. Besides, it is analytically proven that the CCF contains information regarding second- and higher-order cyclostationary moments, being a generalization of the CAF. The performance of the aforementioned new functions in the extraction of higher-order cyclostationary characteristics is analyzed in a wireless communication system where nongaussian noise exists.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-06-21T19:35:54Z No. of bitstreams: 1 JoseMacedoFirminoFilho_TESE.pdf: 7600566 bytes, checksum: 3fb49e1b33edf4c9a3905abebf0e5309 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-06-22T22:09:41Z (GMT) No. of bitstreams: 1 JoseMacedoFirminoFilho_TESE.pdf: 7600566 bytes, checksum: 3fb49e1b33edf4c9a3905abebf0e5309 (MD5) / Made available in DSpace on 2016-06-22T22:09:41Z (GMT). No. of bitstreams: 1 JoseMacedoFirminoFilho_TESE.pdf: 7600566 bytes, checksum: 3fb49e1b33edf4c9a3905abebf0e5309 (MD5) Previous issue date: 2015-12-04 / O c?ncer de pulm?o ? uma das principais causas de morte no mundo. A sua alta taxa de mortalidade est? relacionada com detec??o da patologia em est?gios avan?ados. De acordo com a literatura, a tomografia computadorizada (TC) ? a modalidade de imagem mais indicada para a detec??o precoce de n?dulos pulmonares. No entanto, ela impacta diretamente na carga de trabalho dos radiologistas. Pesquisadores propuseram v?rios sistemas automatizados para auxiliar os radiologistas na detec??o do c?ncer de pulm?o. Entretanto, a utiliza??o desses sistemas necessitava de altera??es no fluxo de trabalho cl?nico e altos custos de implanta??o. Visando solucionar estas barreiras, o presente trabalho prop?e uma nova abordagem para detec??o de n?dulos pulmonares, em exames de tomografia computadorizada (TC), baseado no descritor Histograma do Gradiente Orientada (HoG) e M?quina de Vetor de Suporte (SVM). Al?m disso, ? proposto uma aplica??o desta abordagem num sistema de telerradiologia, chamado LCD-OpenPACS, gratuito e c?digo fonte aberto. Este sistema ? uma extens?o do sistema OpenPACS que ? um sistema de comunica??o e arquivamento de imagens m?dicas que possui c?digo fonte aberto e multiplataforma desenvolvido pelo Laborat?rio de Inova??o Tecnol?gica em Sa?de (LAIS) do Hospital Universit?rio Onofre Lopes (HUOL). O m?todo proposto ? formado por cinco etapas: aquisi??o das imagens, segmenta??o, detec??o de n?dulos suspeitos, extra??o das caracter?sticas e classifica??o (elimina??o de falsos positivos). O m?todo proposto foi validado com 100 n?dulos (identificados por, pelo menos, dois radiologistas) e 101 n?o n?dulos (por exemplo, tecido, vasos sangu?neos e outras estruturas que n?o representavam n?dulos cancer?genos) e apresentou uma sensibilidade de 98,03% com 9,6 falso positivo por caso em 0,18 s. O sistema detectou n?dulos pulmonares cancer?genos (solit?rios, opacidade em vidro fosco e n?dulos justavascular) entre 3 mm e 30 mm. Entretanto, a etapa de segmenta??o do sistema ainda n?o est? apresentando resultados satisfat?rios na presen?a de n?dulos justapleurais e outras patologias graves que alteram a opacidade dos contornos pulmonares. As principais contribui??es do presente trabalho foram o desenvolvimento do novo m?todo de detec??o de n?dulos pulmonares e a proposta do sistema de telerradiologia que minimiza as altera??es do fluxo de trabalho cl?nico e o custo de implanta??o, podendo ser utilizado pelo sistema de sa?de brasileiro (SUS). Ainda s?o necess?rias mais pesquisas para aperfei?oar o sistema proposto, principalmente melhorar o processo de segmenta??o das imagens pulmonares. Como trabalhos futuros, propomos mensurar caracter?sticas dos n?dulos (por exemplo, malignidade e volume), avaliar a evolu??o do tratamento oncol?gico e seu poss?vel progn?stico. / Lung cancer is one of the most common types of cancer and has the highest mortality rate. Patient survival is highly correlated with early detection. Computed Tomography technology services the early detection of lung cancer tremendously by offering aminimally invasive medical diagnostic tool. However, the large amount of data per examination makes the interpretation difficult. This leads to omission of nodules by human radiologist. This thesis presents a development of a computer-aided diagnosis system (CADe) tool for the detection of lung nodules in Computed Tomography study. The system, called LCD-OpenPACS (Lung Cancer Detection - OpenPACS) should be integrated into the OpenPACS system and have all the requirements for use in the workflow of health facilities belonging to the SUS (Brazilian health system). The LCD-OpenPACS made use of image processing techniques (Region Growing and Watershed), feature extraction (Histogram of Gradient Oriented), dimensionality reduction (Principal Component Analysis) and classifier (Support Vector Machine). System was tested on 220 cases, totaling 296 pulmonary nodules, with sensitivity of 94.4% and 7.04 false positives per case. The total time for processing was approximately 10 minutes per case. The system has detected pulmonary nodules (solitary, juxtavascular, ground-glass opacity and juxtapleural) between 3 mm and 30 mm.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-07-20T22:02:47Z No. of bitstreams: 1 AntonioHigorFreireDeMorais_TESE.pdf: 1781383 bytes, checksum: 12a1bd589f80bcd6303ef2f9725860f1 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-07-21T20:58:48Z (GMT) No. of bitstreams: 1 AntonioHigorFreireDeMorais_TESE.pdf: 1781383 bytes, checksum: 12a1bd589f80bcd6303ef2f9725860f1 (MD5) / Made available in DSpace on 2016-07-21T20:58:48Z (GMT). No. of bitstreams: 1 AntonioHigorFreireDeMorais_TESE.pdf: 1781383 bytes, checksum: 12a1bd589f80bcd6303ef2f9725860f1 (MD5) Previous issue date: 2015-11-20 / A Esclerose Lateral Amiotr?fica (ELA) ? uma doen?a neurodegenerativa caracterizada pela fraqueza muscular progressiva que leva o paciente ? morte, geralmente devido a complica??es respirat?rias. Assim, ao passo que a doen?a progride o paciente precisar? de ventila??o n?o-invasiva (VNI) e monitoramento constante. Esta tese apresenta uma arquitetura distribu?da para monitoramento domiciliar de ventila??o noturna n?o-invasiva (VNNI) em pacientes com ELA. A implementa??o desta arquitetura utilizou um computador de placa ?nica (Single Board Computer) e dispositivos m?veis localizados na casa do paciente para mostrar mensagens de alerta para os cuidadores do paciente e um servidor web para monitoramento remoto pela equipe de sa?de. A arquitetura utilizou um software baseado em l?gica fuzzy e vis?o computacional para capturar os dados da tela do ventilador mec?nico e gerar mensagens de alerta com instru??es para os cuidadores. O experimento de monitoramento foi realizado com 29 pacientes por 7 horas cont?nuas diariamente durante 5 dias gerando um total de 126000 amostras para cada vari?vel monitorada com uma taxa de amostragem de uma amostra por segundo. A arquitetura do sistema foi avaliada com rela??o a taxa de acerto para reconhecimento de caracteres e respectiva corre??o atrav?s de um algoritmo para detec??o e corre??o de erros. Al?m disso, a equipe de sa?de avaliou o sistema com rela??o aos intervalos de tempo em as mensagens de alertas foram geradas e se as estas estavam corretas. Dessa forma, o sistema apresentou uma m?dia geral de acertos de 98,72%, e no pior caso 98,39%. Quanto ?s mensagens a serem geradas, o sistema tamb?m concordou em 100% com a avalia??o geral, tendo havido discord?ncia em apenas dois casos com um dos avaliadores. / The Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease characterized by progressive muscle weakness that leads the patient to death, usually due to respiratory complications. Thus, as the disease progresses the patient will require noninvasive ventilation (NIV) and constant monitoring. This paper presents a distributed architecture for homecare monitoring of nocturnal NIV in patients with ALS. The implementation of this architecture used single board computers and mobile devices placed in patient?s homes, to display alert messages for caregivers and a web server for remote monitoring by the healthcare staff. The architecture used a software based on fuzzy logic and computer vision to capture data from a mechanical ventilator screen and generate alert messages with instructions for caregivers. The monitoring was performed on 29 patients for 7 con-tinuous hours daily during 5 days generating a total of 126000 samples for each variable monitored at a sampling rate of one sample per second. The system was evaluated regarding the rate of hits for character recognition and its correction through an algorithm for the detection and correction of errors. Furthermore, a healthcare team evaluated regarding the time intervals at which the alert messages were generated and the correctness of such messages. Thus, the system showed an average hit rate of 98.72%, and in the worst case 98.39%. As for the message to be generated, the system also agreed 100% to the overall assessment, and there was disagreement in only 2 cases with one of the physician evaluators.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-07-22T15:28:33Z No. of bitstreams: 1 RamonAugustoSousaLins_DISSERT.pdf: 3798892 bytes, checksum: 0a5d06ff47c763499839e741148b3dcb (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-07-27T22:14:28Z (GMT) No. of bitstreams: 1 RamonAugustoSousaLins_DISSERT.pdf: 3798892 bytes, checksum: 0a5d06ff47c763499839e741148b3dcb (MD5) / Made available in DSpace on 2016-07-27T22:14:28Z (GMT). No. of bitstreams: 1 RamonAugustoSousaLins_DISSERT.pdf: 3798892 bytes, checksum: 0a5d06ff47c763499839e741148b3dcb (MD5) Previous issue date: 2015-12-04 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico (CNPq) / Neste trabalho ? proposto o desenvolvimento de um sistema inteligente capaz de segmentar, contar e classificar individualmente dentes a partir de imagens fotogr?ficas digitais intraorais oclusais.O sistema proposto faz uso combinado das t?cnicas de aprendizagem de m?quina no caso a m?quina de vetor de suporte e processamento digital de imagens. Primeiramente ? feita uma segmenta??o baseada nas cores dos dentes e n?o dentes presentes na imagem atrav?s do uso de m?quina de vetores de suporte. A partir da identifica??o das regi?es de interesse, dentes e n?o dentes, os dados s?o representados de modo que a contagem, detec??o de fronteiras e classifica??o dos dentes possa ser feita. Para contagem e detec??o de fronteiras s?o utilizadas t?cnicas baseadas em operadores morfol?gicos, eros?o e transformada watershed, respectivamente. A classifica??o quanto aos tipos de dentes ? baseada na utiliza??o dos descritores de posi??o e forma, sendo esse ?ltimo definido por descritores de Fourier. O sistema portanto ? capaz de realizar a segmenta??o, a contagem e a classifica??o de dentes presentes nas imagens. / 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.

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-08-09T22:51:26Z No. of bitstreams: 1 GilmaraLinharesDeAraujo_TESE.pdf: 11647948 bytes, checksum: 94a5e966f18f8dd6bfc6646d2519542b (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-08-10T23:44:37Z (GMT) No. of bitstreams: 1 GilmaraLinharesDeAraujo_TESE.pdf: 11647948 bytes, checksum: 94a5e966f18f8dd6bfc6646d2519542b (MD5) / Made available in DSpace on 2016-08-10T23:44:37Z (GMT). No. of bitstreams: 1 GilmaraLinharesDeAraujo_TESE.pdf: 11647948 bytes, checksum: 94a5e966f18f8dd6bfc6646d2519542b (MD5) Previous issue date: 2015-12-10 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES) / Esse trabalho apresenta uma t?cnica h?brida de projeto de superf?cies seletivas em frequ?ncia, sobre uma camada diel?trica isotr?pica, considerando diversas geometrias para os elementos das c?lulas unit?rias. Especificamente, a t?cnica h?brida usa o m?todo do circuito equivalente em conjunto com algoritmos gen?ticos, visando a s?ntese de estruturas com resposta singleband e dual-band. O m?todo do circuito equivalente permite modelar a estrutura por meio de um circuito equivalente e tamb?m a obten??o de circuitos para diferentes geometrias. A partir da obten??o dos par?metros desses circuitos, podem-se obter as caracter?sticas de transmiss?o e de reflex?o das estruturas modeladas. Para obter a otimiza??o das estruturas modeladas, de acordo com a resposta em frequ?ncia desejada, a ferramenta de otimiza??o do Matlab optimtool mostrou-se de f?cil utiliza??o, permitindo explorar resultados importantes na an?lise de otimiza??o. No trabalho, s?o apresentados resultados num?ricos e experimentais para as caracter?sticas de transmiss?o de diferentes geometrias analisadas. Foram efetuadas compara??es com resultados apresentados na literatura, tendo-se observado uma boaconcord?ncia nos casos analisados para estruturas com substratos isotr?picos. / 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.

Made available in DSpace on 2014-12-17T14:55:29Z (GMT). No. of bitstreams: 1 AnaCMLA_da_capa_ate_pag_32.pdf: 11099536 bytes, checksum: 4f9f0f481f00f3c8e66d9a39f591e6a2 (MD5) Previous issue date: 2005-02-01 / ln this work, it was deveIoped a parallel cooperative genetic algorithm with different evolution behaviors to train and to define architectures for MuItiIayer Perceptron neural networks. MuItiIayer Perceptron neural networks are very powerful tools and had their use extended vastIy due to their abiIity of providing great resuIts to a broad range of appIications. The combination of genetic algorithms and parallel processing can be very powerful when applied to the Iearning process of the neural network, as well as to the definition of its architecture since this procedure can be very slow, usually requiring a lot of computational time. AIso, research work combining and appIying evolutionary computation into the design of neural networks is very useful since most of the Iearning algorithms deveIoped to train neural networks only adjust their synaptic weights, not considering the design of the networks architecture. Furthermore, the use of cooperation in the genetic algorithm allows the interaction of different populations, avoiding local minima and helping in the search of a promising solution, acceIerating the evolutionary process. Finally, individuaIs and evolution behavior can be exclusive on each copy of the genetic algorithm running in each task enhancing the diversity of populations / Neste trabalho foi desenvolvido um algoritmo gen?tico paralelo cooperativo com diferentes comportamentos evolutivos para o treinamento e defini??o de redes neurais Perceptron de M?ltiplas Camadas. As redes neurais Perceptron de M?ltiplas Camadas s?o ferramentas poderosas e tiveram seu uso intensificado j? que s?o capazes de proporcionar bons resultados para diversas aplica??es. A combina??o de algoritmos gen?ticos e de processamento paralelo aplicados no processo de treinamento e na defini??o de redes neurais Perceptron de M?ltiplas Camadas ? interessante uma vez que o processo de aprendizagem geralmente ? lento e a maioria dos algoritmos de treinamento existente realiza apenas o ajuste dos pesos sin?pticos da rede neural. Sabe-se que, sem conhecimento pr?vio da aplica??o, ? dif?cil definir uma arquitetura ideal para a rede neural. Desta maneira, tem-se que t?cnicas para automatizar a defini??o da arquitetura de redes neurais s?o de interesse. Al?m disso, o uso de coopera??o no algoritmo gen?tico permite a explora??o de ?reas promissoras do espa?o de busca encontradas por diferentes popula??es, pode evitar m?nimos locais e possibilita a re-introdu??o nas popula??es de informa??es previamente perdidas. Por fim, atrav?s da incorpora??o de diferentes comportamentos evolutivos, intensifica-se a diversidade dos indiv?duos e, assim, a busca por uma solu??o promissora

Made available in DSpace on 2014-12-17T14:57:47Z (GMT). No. of bitstreams: 1 WilliamFQ.pdf: 3530709 bytes, checksum: e7ebfa713499f96e35732090f0094f3f (MD5) Previous issue date: 2008-08-07 / The manufacture of prostheses for lower limb amputees (transfemural and transtibial) requires the preparation of a cartridge with appropriate and custom fit to the profile of each patient. The traditional process to the patients, mainly in public hospitals in Brazil, begins with the completion of a form where types of equipment, plugins, measures, levels of amputation etc. are identified. Currently, such work is carried out manually using a common metric tape and caliper of wood to take the measures of the stump, featuring a very rudimentary, and with a high degree of uncertainty geometry of the final product. To address this problem, it was necessary to act in two simultaneously and correlated directions. Originally, it was developed an integrated tool for viewing 3D CAD for transfemoral types of prostheses and transtibial called OrtoCAD I. At the same time, it was necessary to design and build a reader Mechanical equipment (sort of three-dimensional scanner simplified) able to obtain, automatically and with accuracy, the geometric information of either of the stump or the healthy leg. The methodology includes the application of concepts of reverse engineering to computationally generate the representation of the stump and/or the reverse image of the healthy member. The materials used in the manufacturing of prostheses nor always obey to a technical scientific criteria, because, if by one way it meets the criteria of resistance, by the other, it brings serious problems mainly due to excess of weight. This causes to the user various disorders due to lack of conformity. That problem was addressed with the creation of a hybrid composite material for the manufacture of cartridges of prostheses. Using the Reader Fitter and OrtoCAD, the new composite material, which aggregates the mechanical properties of strength and rigidity on important parameters such as low weight and low cost, it can be defined in its better way. Besides, it brings a reduction of up steps in the current processes of manufacturing or even the feasibility of using new processes, in the industries, in order to obtain the prostheses. In this sense, the hybridization of the composite with the combination of natural and synthetic fibers can be a viable solution to the challenges offered above / A fabrica??o de pr?teses para amputados de membros inferiores (transfemural e transtibial) exige a confec??o de um cartucho com encaixe adequado e personalizado ao perfil de cada paciente. O processo tradicional de atendimento a pacientes, principalmente, em hospitais p?blicos no Brasil, inicia-se com o preenchimento de uma ficha onde s?o identificados os n?veis de amputa??o, tipos de equipamentos, encaixes, medidas etc. Atualmente, esse trabalho ? realizado de forma manual utilizando-se fitas m?tricas comuns e paqu?metro de madeira para tomada das medidas do coto caracterizando um trabalho bastante rudimentar, e com um alto grau de incerteza geom?trica do produto final. Para abordar esse problema foi necess?rio partir em duas dire??es simult?neas e correlatas. Inicialmente desenvolveu-se uma ferramenta integrada CAD de visualiza??o 3D para pr?teses dos tipos transfemoral e a transtibial denominado OrtoCAD I. Ao mesmo tempo em que se fez necess?rio projetar e construir um equipamento Leitor Mec?nico (esp?cie de scanner tridimensional simplificado) capaz de obter, automaticamente e com acuracidade, as informa??es geom?tricas do coto ou da perna sadia. A metodologia inclui a aplica??o de conceitos de engenharia reversa para gerar computacionalmente a representa??o do coto e/ou a imagem reversa do membro sadio. Os materiais usados na fabrica??o dessas pr?teses nem sempre obedecem a um crit?rio t?cnico cientifico, pois se por um lado atende ao crit?rio de resist?ncia por outro traz s?rios problemas devido principalmente ao excesso de peso. Isso causa diversos transtornos ao usu?rio devido ? falta de conformidade. Esse problema foi abordado com a cria??o de um material comp?sito hibrido para fabrica??o de cartuchos de pr?teses. Com o uso do Leitor Mec?nico e do OrtoCAD I o novo material comp?sito, que agrega as propriedades mec?nicas de resist?ncia e rigidez com par?metros importantes como baixo peso e baixo custo, pode ser dimensionado de forma correta. Alem disso consegue-se uma redu??o de etapas nos atuais processos de fabrica??o ou at? mesmo a viabilidade de uso de novos processos, no ?mbito industrial, na obten??o das pr?teses. Neste sentido, a hibridiza??o do comp?sito com a combina??o entre fibras sint?ticas e naturais pode ser uma solu??o vi?vel aos desafios propostos acima