Dans l'apprentissage machine, la classification est le processus d’assigner une nouvelle observation à une certaine catégorie. Les classifieurs qui mettent en œuvre des algorithmes de classification ont été largement étudié au cours des dernières décennies. Les classifieurs traditionnels sont basés sur des algorithmes tels que le SVM et les réseaux de neurones, et sont généralement exécutés par des logiciels sur CPUs qui fait que le système souffre d’un manque de performance et d’une forte consommation d'énergie. Bien que les GPUs puissent être utilisés pour accélérer le calcul de certains classifieurs, leur grande consommation de puissance empêche la technologie d'être mise en œuvre sur des appareils portables tels que les systèmes embarqués. Pour rendre le système de classification plus léger, les classifieurs devraient être capable de fonctionner sur un système matériel plus compact au lieu d'un groupe de CPUs ou GPUs, et les classifieurs eux-mêmes devraient être optimisés pour ce matériel. Dans ce mémoire, nous explorons la mise en œuvre d'un classifieur novateur sur une plate-forme matérielle à base de FPGA. Le classifieur, conçu par Alain Tapp (Université de Montréal), est basé sur une grande quantité de tables de recherche qui forment des circuits arborescents qui effectuent les tâches de classification. Le FPGA semble être un élément fait sur mesure pour mettre en œuvre ce classifieur avec ses riches ressources de tables de recherche et l'architecture à parallélisme élevé. Notre travail montre que les FPGAs peuvent implémenter plusieurs classifieurs et faire les classification sur des images haute définition à une vitesse très élevée. / In the machine learning area, classification is a process of mapping a new observation to a certain category. Classifiers which implement classification algorithms have been studied widely over the past decades. Traditional classifiers are based on algorithms such as SVM and neural nets, and are usually run by software on CPUs which cause the system to suffer low performance and high power consumption. Although GPUs can be used to accelerate the computation of some classifiers, its high power consumption prevents the technology from being implemented on portable devices such as embedded systems or wearable hardware. To make a lightweight classification system, classifiers should be able to run on a more compact hardware system instead of a group of CPUs/GPUs, and classifiers themselves should be optimized to fit that hardware. In this thesis, we explore the implementation of a novel classifier on a FPGA-based hardware platform. The classifier, devised by Alain Tapp (Université de Montréal), is based on a large amount of look-up tables that form tree-structured circuits to do classification tasks. The FPGA appears to be a tailor-made component to implement this classifier with its rich resources of look-up tables and the highly parallel architecture. Our work shows that a single FPGA can implement multiple classifiers to do classification on high definition images at a very high speed.

This master thesis investigates the possibility to create a machine vision solution for the automation of earth-moving machines. This research was done as without some type of vision system it will not be possible to create a fully autonomous earth moving machine that can safely be used around humans or other machines. Cameras were used as the primary sensors as they are cheap, provide high resolution and is the type of sensor that most closely mimic the human vision system. The purpose of this master thesis was to use existing real time object detectors together with transfer learning and examine if they can successfully be used to extract information in environments such as construction, forestry and mining. The amount of data needed to successfully train a real time object detector was also investigated. Furthermore, the thesis examines if there are specifically difficult situations for the defined object detector, how reliable the object detector is and finally how to use service-oriented architecture principles can be used to create deep learning systems. To investigate the questions formulated above, three data sets were created where different properties were varied. These properties were light conditions, ground material and dump truck orientation. The data sets were created using a toy dump truck together with a similarly sized wheel loader with a camera mounted on the roof of its cab. The first data set contained only indoor images where the dump truck was placed in different orientations but neither the light nor the ground material changed. The second data set contained images were the light source was kept constant, but the dump truck orientation and ground materials changed. The last data set contained images where all property were varied. The real time object detector YOLOv3 was used to examine how a real time object detector would perform depending on which one of the three data sets it was trained using. No matter the data set, it was possible to train a model to perform real time object detection. Using a Nvidia 980 TI the inference time of the model was around 22 ms, which is more than enough to be able to classify videos running at 30 fps. All three data sets converged to a training loss of around 0.10. The data set which contained more varied data, such as the data set where all properties were changed, performed considerably better reaching a validation loss of 0.164 compared to the indoor data set, containing the least varied data, only reached a validation loss of 0.257. The size of the data set was also a factor in the performance, however it was not as important as having varied data. The result also showed that all three data sets could reach a mAP score of around 0.98 using transfer learning.

Esta tese se concentra em aplicar os modelos de mistura de distribuições na segmentação de imagens SAR polarimétricas multi-look. Dentro deste contexto, utilizou-se o algoritmo SEM em conjunto com os estimadores obtidos pelo método dos momentos para calcular as estimativas dos parâmetros do modelo de mistura das distribuições Wishart, Kp ou G0p. Cada uma destas distribuições possui parâmetros específicos que as diferem no ajuste dos dados com graus de homogeneidade variados. A distribuição Wishart descreve bem regiões com características mais homogêneas, como cultivo. Esta distribuição é muito utilizada na análise de dados SAR polarimétricos multi-look. As distribuições Kp e G0p possuem um parâmetro de rugosidade que as permitem descrever tanto regiões mais heterogêneas, como vegetação e áreas urbanas, quanto regiões homogêneas. Além dos modelos de mistura de uma única família de distribuições, também foi analisado o caso de um dicionário contendo as três famílias. Há comparações do método SEM proposto para os diferentes modelos com os métodos da literatura k-médias e EM utilizando imagens reais da banda L. O método SEM com a mistura de distribuições G0p forneceu os melhores resultados quando os outliers da imagem são desconsiderados. A distribuição G0p foi a mais flexível ao ajuste dos diferentes tipos de alvo. A distribuição Wishart foi robusta às diferentes inicializações. O método k-médias com a distribuição Wishart é robusto à segmentação de imagens contendo outliers, mas não é muito flexível à variabilidade das regiões heterogêneas. O modelo de mistura do dicionário de famílias melhora a log-verossimilhança do método SEM, mas apresenta resultados parecidos com os do modelo de mistura G0p. Para todos os tipos de inicialização e grupos, a distribuição G0p predominou no processo de seleção das distribuições do dicionário de famílias. / The main focus of this thesis consists of the application of mixture models in multi-look polarimetric SAR image segmentation. Within this context, the SEM algorithm, together with the method of moments, were applied in the estimation of the Wishart, Kp and G0p mixture model parameters. Each one of these distributions has specific parameters that allows fitting data with different degrees of homogeneity. The Wishart distribution is suitable for modeling homogeneous regions, like crop fields for example. This distribution is widely used in multi-look polarimetric SAR data analysis. The distributions Kp and G0p have a roughness parameter that allows them to describe both heterogeneous regions, as vegetation and urban areas, and homogeneous regions. Besides adopting mixture models of a single family of distributions, the use of a dictionary with all the three family of distributions was proposed and analyzed. Also, a comparison between the performance of the proposed SEM method, considering the different models in real L-band images and two widely known techniques described in literature (k-means and EM algorithms), are shown and discussed. The proposed SEM method, considering a G0p mixture model combined with a outlier removal stage, provided the best classication results. The G0p distribution was the most flexible for fitting the different kinds of data. The Wishart distribution was robust for different initializations. The k-means algorithm with Wishart distribution is robust for segmentation of SAR images containing outliers, but it is not so flexible to variabilities in heterogeneous regions. The mixture model considering the dictionary of distributions improves the SEM method log-likelihood, but presents similar results to those of G0p mixture model. For all types of initializations and clusters, the G0p prevailed in the distribution selection process of the dictionary of distributions.

Made available in DSpace on 2016-04-26T18:15:57Z (GMT). No. of bitstreams: 1 COS - Cimara Apostolico.pdf: 2592450 bytes, checksum: 05ca79967f3a86b6bfb61627e279c7c4 (MD5) Previous issue date: 2006-09-25 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This research analyses the soap opera in its aspects related to the image presentation as hegemonic item in the audience s ability to perceive things. It is chosen to understand soap opera not in its aspects of daily narratives, but as imagery narratives created by bodies that represent themselves as mediators in the process of communication, functioning as main starting-point in the image production. In this way, the concept of body and body language is used. With it this process starts, expressing the relation of cumulativity and complementarity to media, reinforcing the soap opera appealing. It is perceived that the body is seen on the soap opera as commodities and exploiting fact. This paper/thesis selects the male image because of the visible set of public opinion in the last years. The questions of body image through history are investigated in order to understand in a broad sense its changes in relation to cultural process and trying to highlight the evidences that lead to see it as emerging bodies. The images are narrated/described from the understanding of their origin to questions that point out their symbolic aspects, which belong to the sensibility that creates links among bodies. Using Harry Pross, Martin Barbero, Esther Hamburger, Denise Bernuzzi de Sant Anna, Régis Debray as theoretical support, it can be seen that along with the soap opera several media are used as a support of it. In this sense, magazines that write about cinematographic and TV celebrities are analyzed. Being aware that there is no TV without bodies before and off cameras, for example, biological bodies and body-image, we understand that is in the relation among audience, body and image that the soap opera keeps on / A presente pesquisa analisa a telenovela em seus aspectos voltados para a apresentação da imagem como item hegemônico na captação do olhar do telespectador. Opta-se pela compreensão da telenovela não no aspecto das narrativas cotidianas, mas sim tendo como base as narrativas imagéticas geradas por meio de corpos que se configuram como mediadores no processo de comunicação, atuando como ponto de partida central na produção das imagens. Nesse sentido, é utilizado o conceito de corpo e suas linguagens. Nele iniciase esse processo, a partir do qual se expressam as relações de cumulatividade e complementaridade entre as mídias, reforçando os atrativos da telenovela. Percebese o corpo exibido na telenovela como produto mercadológico e fator de exploração. O presente trabalho faz um recorte com ênfase no masculino, pela tendência evidenciada nos últimos anos. As questões de construção de corpos ao longo da história são investigadas, compreendendo-se de maneira abrangente as etapas de suas mudanças decorrentes do processo da cultura e buscando evidências, que conduzem a percebê-los como corpos emergentes . As imagens são narradas, partindo do entendimento de sua gênese até questões que as conduzam em seus aspectos simbólicos, os quais fazem parte da sensibilidade que gera as raízes dos vínculos entre os corpos. Em diálogo e com apoio nos autores Harry Pross, Martin Barbero, Esther Hamburger, Denise Bernuzzi de Sant Anna, Régis Debray, constata-se que paralelamente à novela em si, acumulam-se e complementam-se diversas mídias de apoio. Nesse sentido, são analisadas, também revistas voltadas para as celebridades cinematográficas e televisivas. Ciente de que não há televisão sem corpos antes e depois das câmeras, ou seja, corpos biológicos e corpos-imagem, entende-se que é na cauda da relação triádica telespectador, corpo e imagem que o ambiente da telenovela se mantém

Made available in DSpace on 2014-07-29T16:27:53Z (GMT). No. of bitstreams: 1 AllexDissertacao02082012WEB.pdf: 3719508 bytes, checksum: 5ebd7cf8ae0675316ac3bcb8b80892f7 (MD5) Previous issue date: 2012-06-01 / This paper proposes an investigative reflection and (mis)reading helical tangle of lines that seeks, in the discourses and images of dadá and the avant-garde film movement dogma95 elements for performing an artistic intervention in the Rodoviaria Plano Piloto in Brasília (DF). The focus of the text is aimed at the questions that underlie the notion of looking educated in the (mis)direction of visual culture, as epistemological basis in order to ask about the different meanings articulated by the individuals who pass in the environment of the intervention in the field. By this route, the lines of escape and overflow interpretations by those subjects who admit a multiplicity of perspectives shaped, inventive and deviants, before the cultural transgressions in insurgency movements above. The research had the (dis)methodological guid Merz in the Hand, which has theoretical and historical descriptions of the movements in question, and the bases for practices with structured interviews, structured scripts of questions by e-mail, photographs, film and artifacts produced in the field. This multiplicity of assemblages unraveled reflections on the myriad of meanings from the looks of interpretations conformed to art images and connections between the subjective and cultural space-times, as well as the practices of subject positions that constitute deviant. / Este texto investigativo propõe uma reflexão e (des)leitura helicoidal, emaranhado de linhas que busca, nos discursos e nas imagens da vanguarda dadá e do movimento cinematográfico dogma95, elementos para a realização de uma intervenção artística na Rodoviária do Plano Piloto, em Brasília (DF). O foco do texto está voltado para as questões que perpassam a noção de olhar educado nos (des)caminhos da cultura visual, como base epistemológica, a fim de perguntar sobre os diferentes significados articulados pelos sujeitos que transitam no ambiente da intervenção, em campo. Por esta rota, as linhas fogem e transbordam das interpretações desses sujeitos que admitem uma multiplicidade de olhares conformados, inventivos e desviantes, perante as transgressões culturais nas insurgências dos movimentos acima. A pesquisa teve como (des)norteamento metodológico o Merz na Mão, que conta com bases teóricas e descrições históricas entre os movimentos em questão, e parte para bases práticas com entrevistas semiestruturadas, estruturadas, roteiros de perguntas por correio eletrônico, fotografias, filmagem e artefatos produzidos em campo. Essa multiplicidade de agenciamentos deslindou reflexões acerca das miríades de significados entre os olhares de interpretações conformadas para as imagens da arte e entre as conexões subjetivas e culturais dos espaços-tempos, bem como das práticas de sujeitos que configuram posturas desviantes .

Submitted by Cássia Santos (cassia.bcufg@gmail.com) on 2014-09-18T10:43:04Z No. of bitstreams: 2 Dissertacao Maria das D S de Barros.pdf: 903137 bytes, checksum: 64474d362c75a3e484576177c508756e (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2014-09-18T12:34:03Z (GMT) No. of bitstreams: 2 Dissertacao Maria das D S de Barros.pdf: 903137 bytes, checksum: 64474d362c75a3e484576177c508756e (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2014-09-18T12:34:03Z (GMT). No. of bitstreams: 2 Dissertacao Maria das D S de Barros.pdf: 903137 bytes, checksum: 64474d362c75a3e484576177c508756e (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2013-04-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Divided into three chapters, this dissertation has as its object of study the poetry of Orides Fontela. The project was conducted in order to grasp the conjuto of five books: Transposition (1969), Helianto (1973) Alba (1983) Rosacea (1986) and (1996) look at the representations of the work of Fontela, analyzing them as constituents a writing project based on the phenomenology of the gaze. At first try to locate fonteliana writing within a tradition of writers whose writing is marked by philosophical reflection order. We then present the reflections developed by Novaes, Bosi and Merleau-Ponty on the vision in Western thought. Finally, we come to the essential object of the research, the analysis of a corpus of poems that explore, in different ways and the perception of the sensible world. Using theoretical support considerations about perception, designed by phenomenology, we expect to realize and analyze the elements constituting a poetic look at the work of the author. / Dividida em três capítulos, esta dissertação tem como objeto de estudo a poesia de Orides Fontela. O projeto foi realizado no sentido de apreender, no conjunto dos cinco livros: Transposição (1969), Helianto (1973) Alba (1983) Rosácea (1986) e Teia (1996), as representações do olhar na obra de Fontela, analisando-os como constituintes de um projeto de escrita fundado na fenomenologia do olhar. Em um primeiro momento, procuramos situar a escrita fonteliana em uma tradição de escritores cuja escrita é marcada pela reflexão de ordem filosófica. Em seguida, apresentamos as reflexões desenvolvidas por Novaes, Bosi e Merleau-Ponty acerca da visão no pensamento ocidental. Por fim, chegamos ao objeto essencial da pesquisa, a análise de um corpus de poemas que exploram, por vias diversas, a percepção do mundo sensível. Usando como suporte teórico as considerações acerca da percepção, concebidas pela fenomenologia, esperamos perceber e analisar os elementos representativos de uma poética do olhar na obra da autora.

<p>Bit-parallel addition can be performed using a number of adder structures with different area and latency. However, the power consumption of different adder structures is not well studied. Further, the effect of pipelining adders to increase the throughput is not well studied. In this thesis four different adders are described, implemented in VHDL and compared after synthesis. The results give a general idea of the time-delay-power tradeoffs between the adder structures. Pipelining is shown to be a good technique for increasing the circuit speed.</p>

This thesis proposes a decision-feedback equalizer (DFE) scheme for blind ADC-based receivers to overcome the challenges introduced by blind sampling. It presents the design, simulation, and implementation of a 5Gb/s speculative DFE for a 2x blind ADC-based receiver. The complete receiver, including the ADC, the DFE, and a 2x blind clock and data recovery (CDR) circuit, is implemented in Fujitsu’s 65-nm CMOS process. Measurements of the fabricated test-chip confirm 5Gb/s data recovery with bit error rate (BER) less than 1e−12 in the presence of a test channel introducing 13.3dB of attenuation at the Nyquist frequency of 2.5GHz. The receiver tolerates 0.24UIpp of high-frequency sinusoidal jitter (SJ) in this case. Without the DFE, the BER exceeds 1e−8 even when no SJ is applied.

This thesis proposes a decision-feedback equalizer (DFE) scheme for blind ADC-based receivers to overcome the challenges introduced by blind sampling. It presents the design, simulation, and implementation of a 5Gb/s speculative DFE for a 2x blind ADC-based receiver. The complete receiver, including the ADC, the DFE, and a 2x blind clock and data recovery (CDR) circuit, is implemented in Fujitsu’s 65-nm CMOS process. Measurements of the fabricated test-chip confirm 5Gb/s data recovery with bit error rate (BER) less than 1e−12 in the presence of a test channel introducing 13.3dB of attenuation at the Nyquist frequency of 2.5GHz. The receiver tolerates 0.24UIpp of high-frequency sinusoidal jitter (SJ) in this case. Without the DFE, the BER exceeds 1e−8 even when no SJ is applied.

The objective of the research was to design and test an SRAM system which can meet the performance criteria for Memory Based Computing (MBC). This form of computing consists of a Look-Up Table (LUT) which is basically memory array mapped with a function; the computations thereafter consist of essentially read operations. An MBC framework requires very fast and low power read operations. Moreover, the cells need to be read stable as major part of the computation is done by reading the LUTs mapped in the SRAM array. Design and measurement of a prototype MBC test-chip with SRAM system optimized for read-heavy applications is presented in this thesis. For this purpose, a prototype MBC system was designed and taped out. Essential study of the write-ability of the core LUT is also presented. The core memory array for function table mapping was characterized for leakage, write-ability and power saving associated with pulsed read mode.