Submitted by Celso Magalhaes (celsomagalhaes@ufrrj.br) on 2017-07-28T16:35:42Z No. of bitstreams: 1 2016 - Rupila Rami da Silva Goda.pdf: 2862869 bytes, checksum: 8c9a253d8a926ba04221e5ffb1311b81 (MD5) / Made available in DSpace on 2017-07-28T16:35:42Z (GMT). No. of bitstreams: 1 2016 - Rupila Rami da Silva Goda.pdf: 2862869 bytes, checksum: 8c9a253d8a926ba04221e5ffb1311b81 (MD5) Previous issue date: 2016-08-30 / Breast cancer is the second most common cancer worldwide. According to the National Cancer Institute (INCA) in 2014 were diagnosed 52,680 new cases in Brazil, a number that corresponds to a 22% increase over the year 2013. Being responsible for approximately 39% of women's deaths cancer patients. Despite the high incidence rate, mortality from this cancer has declined since the late eighties, thanks to advances in research on methods for early diagnosis. However, correctly diagnosing cancer is a complex and difficult process as a result of the different variables involved. For an accurate diagnosis, a lot of experience and especially it is required, that the classification of clinical staging of tumor (cancer stage) is correct. The conditions used traditional classification systems are complex and often offer limitations. As is the case of mammography technique, widely used, it is not as effective for women with dense breasts, surgically altered, or under 40 years. Thus, it becomes necessary to develop integrated systems that combined with the professionals in the field experience, allows performing accurate diagnosis in detecting breast cancer. The objective of this study is to apply the technique SVM (Support Vector Machine), so as to assist in the diagnostic interpretation of microcalcifications detected on screening mammography. The data set used consisted of 961 samples of mammograms, obtained from the Radiology Institute of the University of Erlangen Nuremberg. In this set we have information on the age of the patient, BI-RADS (Breast Imaging Reporting and Data System), shape, mass, density and severity (benign | malignant) of microcalcifications. The SVM was developed implemented using the R software (R Development Core Team; http: // www.R-project.org/). The data were divided into two groups: the training set consisting of 80% of the samples of mammographic, used to estimate the model parameters and the independent test set, with 20% of the remaining samples, used to measure the performance of SVM . To evaluate the performance of proposed computational model we used the value of the Total Precision or Accuracy (ACC), sensitivity (S) and specificity (E). The results presented by SVM in identifying malignant lesions in patients with calcifications remained between 72.7% and 100%, which shows that they achieved a satisfactory level in relation to other literatures applied / O c?ncer de mama ? a segunda neoplasia mais frequente no mundo. Segundo dados do Instituto Nacional de C?ncer (INCA), no ano de 2014 foram diagnosticados 52.680 novos casos no Brasil, n?mero este que corresponde a um aumento de 22% em rela??o ao ano de 2013. Sendo respons?vel por aproximadamente 39% dos ?bitos das mulheres portadores de c?ncer. Apesar da elevada taxa de incid?ncia, a mortalidade causada por esta neoplasia tem diminu?do desde o final dos anos oitenta, gra?as ao avan?o das pesquisas em m?todos para o diagn?stico precoce. No entanto, diagnosticar corretamente o c?ncer ? um processo complexo e muito dif?cil em consequ?ncia das diversas vari?veis envolvidas. Para um diagn?stico preciso, exige-se muita experi?ncia e, principalmente, que a classifica??o do estadiamento cl?nico do tumor (est?gio do c?ncer) esteja correta. Os tradicionais sistemas de classifica??o de patologias utilizados s?o complexos e em muitas vezes oferecem limita??es. Como ? o caso da t?cnica de mamografia, que amplamente utilizada, n?o ? t?o eficaz para mulheres com mamas densas, cirurgicamente alteradas ou com menos de 40 anos. Desta forma, torna-se necess?rio o desenvolvimento de sistemas integrados que combinados com a experi?ncia dos profissionais da ?rea, possibilite realizar o diagn?stico preciso na detec??o do c?ncer de mama. O objetivo do presente trabalho ? aplicar a t?cnica SVM (M?quina de Vetor de Suporte), de sorte a auxiliar na interpreta??o diagn?stica das microcalcifica??es detectadas em mamografia de rastreamento. O conjunto de dados utilizado consistiu de 961 amostras de exames mamogr?ficos, obtidos junto ao Instituto de Radiologia da Universidade de Erlangen- Nuremberg. Neste conjunto possu?mos informa??es referentes a idade da paciente, classifica??o BI-RADS ( Breast Imaging Reporting and Data System), forma, massa, densidade e severidade (benigno|maligno) das microcalcifica??o. A SVM desenvolvida foi implementada utilizando-se o software R (R Development Core Team; http:// www.R-project.org/ ) . Os dados foram divididos em dois grupos: o conjunto de treinamento composto por 80% das amostras de exames mamogr?ficos, usado para estimar os par?metros do modelo e o conjunto de teste independente, com 20% das amostras restantes, utilizado para mensurar a performance da SVM. Para avaliar o desempenho do modelo computacional proposto foram utilizados o valor da Precis?o Total ou Acur?cia (ACC), Sensibilidade (S) e Especificidade(E). Os resultados apresentados pela SVM na identifica??o das les?es malignas em pacientes portadores de microcalcifica??es se mantiveram entre 72,7% e 100% o que demonstram que os mesmos alcan?aram um grau satisfat?rio em rela??o com outras literaturas aplicadas

Road traffic signs provide instructions, warning information, to regulate driver behavior. In addition, these signs provide a reliable guarantee for safe and convenient driving. The Traffic Sign Detection and Recognition (TSDR) system is one of the primary applications for Advanced Driver Assistance Systems (ADAS). TSDR has obtained a great deal of attention over the recent years. But, it is still a challenging field of image processing. In this thesis, we first created our own dataset for North American Traffic Signs, which is still being updated. We then decided to choose Histogram Orientation Gradients (HOG) and Support Vector Machines (SVMs) to build our system after comparing them with some other techniques. For better results, we tested different HOG parameters to find the best combination. After this, we developed a TSDR system using HOG, SVM and our new color information extraction algorithm. To reduce time-consumption, we used the Maximally Stable Extremal Region (MSER) to replace the HOG and SVM detection stage. In addition, we developed a new approach based on Global Positioning System (GPS) information other than image processing. At last, we tested these three systems; the results show that all of them can recognize traffic signs with a good accuracy rate. The MSER based system is faster than the one using only HOG and SVM; and, the GPS based system is even faster than the MSER based system.

This masters thesis deals with algorithms for learning SVM classifiers on hardware systems and their implementation in FPGA. There are basics about classifiers and learning. Two learning algorithms are introduced SMO algorithm and one hardware-friendly algorithm.

Due to the rapid progress and advancements in deep learning and neural networks, manyapproaches and state-of-the-art researches have been conducted in these fields which cause developing various learning-based attacks leading to vulnerability of websites and portals. This kind of attacks decrease the security of the websites which results in releasing the sensitive and important personal information. These days, preserving the security of the websites is one of the most challenging tasks. CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) is kind of test which are developed by designers and are available in various websites to distinguish and differentiate humans from robots in order to protect the websites from possible attacks. In this dissertation, we proposed a CNN based approach to attack and break text-based CAPTCHAs. The proposed method has been compared with several state-of-the-art approaches in terms of recognition accuracy (RA). Based on the results, the developed method can break and recognize CAPTCHAs at high accuracy. Additionally, we wanted to check how to make these CAPTCHAs hard to be broken, so we employed five types of distortions in these CAPTCHAs. The recognition accuracy in presence of these noises has been calculated. The results indicate that adversarial noise can make CAPTCHAs much difficult to be broken. The results have been compared with some state-of-the-art approaches. This analysis can be helpful for CAPTCHA developers to consider these noises in their developed CAPTCHAs. This dissertation also presents a hybrid model based on CNN-SVM to solve text-based CAPTCHAs. The developed method contains four main steps, namely: segmentation, feature extraction, feature selection, and recognition. For segmentation, we suggested using histogram and k-means clustering. For feature extraction, we developed a new CNN structure. The extracted features are passed through the mRMR algorithm to select the most efficient features. These selected features are fed into SVM for further classification and recognition. The results have been compared with several state-of-the-art methods to show the superiority of the developed approach. In general, this dissertation presented deep learning-based methods to solve text-based CAPTCHAs. The efficiency and effectiveness of the developed methods have been compared with various state-of-the-art methods. The developed techniques can break CAPTCHAs at high accuracy and also in a short time. We utilized Peak Signal to Noise Ratio (PSNR), ROC, accuracy, sensitivity, specificity, and precision to evaluate and measure the performance analysis of different methods. The results indicate the superiority of the developed methods.

No description available.

Dans le cadre du projet Européen X-Media, de nombreuses contributions ont été apportées aux problèmes de classification d'image et de recherche d'images par le contenu dans des contextes industriels hétérogènes. Ainsi, après avoir établi un état de l'art des descripteurs d'image les plus courant, nous nous sommes dans un premier temps intéressé a des méthodes globales, c'est à dire basée sur la description totale de l'image par des descripteurs. Puis, nous nous sommes attachés a une analyse plus fine du contenu des images afin d'en extraire des informations locales, sur la présence et la localisation d'objets d'intérêt. Enfin, nous avons proposé une méthode hybride de recherche d'image basée sur le contenu qui s'appuie sur la description locale des régions de l'image afin d'en tirer une signature pouvant être utilisée pour des requêtes globales et locales. / The explosive development of affordable, high quality image acquisition deviceshas made available a tremendous amount of digital content. Large industrial companies arein need of efficient methods to exploit this content and transform it into valuable knowledge.This PhD has been accomplished in the context of the X-MEDIA project, a large Europeanproject with two major industrial partners, FIAT for the automotive industry andRolls-Royce plc. for the aircraft industry. The project has been the trigger for research linkedwith strong industrial requirements. Although those user requirements can be very specific,they covered more generic research topics. Hence, we bring several contributions in thegeneral context of Content-Based Image Retrieval (CBIR), Indexing and Classification.In the first part of the manuscript we propose contributions based on the extraction ofglobal image descriptors. We rely on well known descriptors from the literature to proposemodels for the indexing of image databases, and the approximation of a user defined categorisation.Additionally, we propose a new descriptor for a CBIR system which has toprocess a very specific image modality, for which traditional descriptors are irrelevant. Inthe second part of the manuscript, we focus on the task of image classification. Industrialrequirements on this topic go beyond the task of global image classification. We developedtwo methods to localize and classify the local content of images, i.e. image regions, usingsupervised machine learning algorithms (Support Vector Machines). In the last part of themanuscript, we propose a model for Content-Based Image Retrieval based on the constructionof a visual dictionary of image regions. We extensively experiment the model in orderto identify the most influential parameters in the retrieval efficiency.

La mesure de la hauteur des océans, des vents de surface (fortement liés aux températures des océans), ou encore de la hauteur des vagues sont un ensemble de paramètres nécessaires à l'étude des océans mais aussi au suivi de leurs évolutions : l'altimétrie spatiale est l'une des disciplines le permettant. Une forme d'onde altimétrique est le résultat de l'émission d'une onde radar haute fréquence sur une surface donnée (classiquement océanique) et de la mesure de la réflexion de cette onde. Il existe actuellement une méthode d'estimation non optimale des formes d'onde altimétriques ainsi que des outils de classifications permettant d'identifier les différents types de surfaces observées. Nous proposons dans cette étude d'appliquer la méthode d'estimation bayésienne aux formes d'onde altimétriques ainsi que de nouvelles approches de classification. Nous proposons enfin la mise en place d'un algorithme spécifique permettant l'étude de la topographie en milieu côtier, étude qui est actuellement très peu développée dans le domaine de l'altimétrie. / After having scanned the ocean levels during thirteen years, the french/american satelliteTopex-Poséidon disappeared in 2005. Topex-Poséidon was replaced by Jason-1 in december 2001 and a new satellit Jason-2 is waited for 2008. Several estimation methods have been developed for signals resulting from these satellites. In particular, estimators of the sea height and wave height have shown very good performance when they are applied on waveforms backscattered from ocean surfaces. However, it is a more challenging problem to extract relevant information from signals backscattered from non-oceanic surfaces such as inland waters, deserts or ices. This PhD thesis is divided into two parts : A first direction consists of developing classification methods for altimetric signals in order to recognize the type of surface affected by the radar waveform. In particular, a specific attention will be devoted to support vector machines (SVMs) and functional data analysis for this problem. The second part of this thesis consists of developing estimation algorithms appropriate to altimetric signals obtained after reflexion on non-oceanic surfaces. Bayesian algorithms are currently under investigation for this estimation problem. This PhD is co-supervised by the french society CLS (Collect Localisation Satellite) (seehttp://www.cls.fr/ for more details) which will in particular provide the real altimetric data necessary for this study.

<div> <div> <div> <p>Support Vector Machines (SVMs) have generally been effective in detecting instances of network intrusion. However, from a practical point of view, a standard SVM is not able to handle large-scale data efficiently due to the computation complexity of the algorithm and extensive memory requirements. To cope with the limitation, this study presents an incremental SVM method combined with a k-nearest neighbors (KNN) based candidate support vectors (CSV) selection strategy in order to speed up training and test process. The proposed incremental SVM method constructs or updates the pattern classes by incrementally incorporating new signatures without having to load and access the entire previous dataset in order to cope with evolving DoS and DDoS attacks. Performance of the proposed method is evaluated with experiments and compared with the standard SVM method and the simple incremental SVM method in terms of precision, recall, F1-score, and training and test duration.<br></p> </div> </div> </div>

A biometria é a ciência que estuda a mensuração dos seres vivos. Muitos trabalhos exploram as características dos seres humanos tais como, impressão digital, íris e face, a fim de desenvolver sistemas biométricos, utilizados em diversas aplicações (monitoramento de segurança, computação ubíqua, robótica). O reconhecimento de faces é uma das técnicas biométricas mais investigadas, por ser bastante intuitiva e menos invasiva que as demais. Alguns trabalhos envolvendo essa técnica se preocupam apenas em localizar a face de um indivíduo (fazer a contagem de pessoas), enquanto outros tentam identificá-lo a partir de uma imagem. Este trabalho propõe uma abordagem capaz de identificar faces a partir de quadros de vídeo e, posteriormente, reconhecê-las por meio de técnicas de análise de imagens. Pode-se dividir o trabalho em dois módulos principais: (1) - Localização e rastreamento de faces em uma seqüência de imagens ( frames), além de separar a região rastreada da imagem; (2) - Reconhecimento de faces, identificando a qual pessoa pertence. Para a primeira etapa foi implementado um sistema de análise de movimento (baseado em subtração de quadros) que possibilitou localizar, rastrear e captar imagens da face de um indivíduo usando uma câmera de vídeo. Para a segunda etapa foram implementados os módulos de redução de informações (técnica Principal Component Analysis - PCA), de extração de características (transformada wavelet de Gabor), e o de classificação e identificação de face (distância Euclidiana e Support Vector Machine - SVM). Utilizando-se duas bases de dados de faces (FERET e uma própria - Própria), foram realizados testes para avaliar o sistema de reconhecimento implementado. Os resultados encontrados foram satisfatórios, atingindo 91,92% e 100,00% de taxa de acertos para as bases FERET e Própria, respectivamente. / Biometry is the science of measuring and analyzing biomedical data. Many works in this field have explored the characteristics of human beings, such as digital fingerprints, iris, and face to develop biometric systems, employed in various aplications (security monitoring, ubiquitous computation, robotic). Face identification and recognition are very apealing biometric techniques, as it it intuitive and less invasive than others. Many works in this field are only concerned with locating the face of an individual (for counting purposes), while others try to identify people from faces. The objective of this work is to develop a biometric system that could identify and recognize faces. The work can be divided into two major stages: (1) Locate and track in a sequence of images (frames), as well as separating the tracked region from the image; (2) Recognize a face as belonging to a certain individual. In the former, faces are captured from frames of a video camera by a motion analysis system (based on substraction of frames), capable of finding, tracking and croping faces from images of individuals. The later, consists of elements for data reductions (Principal Component Analysis - PCA), feature extraction (Gabor wavelets) and face classification (Euclidean distance and Support Vector Machine - SVM). Two faces databases have been used: FERET and a \"home-made\" one. Tests have been undertaken so as to assess the system\'s recognition capabilities. The experiments have shown that the technique exhibited a satisfactory performance, with success rates of 91.97% and 100% for the FERET and the \"home-made\" databases, respectively.

O objetivo dessa tese é detectar e classificar problemas de medição de nível por princípio de radar de propagação de onda livre por meio de RNA (redes neurais artificiais) e SVM (support vector machines) aliados à tratamentos estatísticos. Um primeiro cenário com ambiente controlado foi montado para a obtenção de dados preliminares. Na sequência, outros três cenários empregaram dados industriais reais. Para tanto, algumas topologias de redes neurais em quatro cenários diferentes foram testadas e foi possível demonstrar o funcionamento eficiente da RNA com acertos de 100% para o primeiro cenário, 93,51% para o segundo, 99,75% para o terceiro e de 99,94% para o quarto cenário. Para esses mesmos quatro cenários, os resultados de classificação do SVM foram de 100%, 84,41%, 93,74% e de 96,40%. Os resultados obtidos demonstram que a técnica desenvolvida pode ser aplicada à cenários reais de medição de nível. Após a classificação dos problemas pela RNA ou SVM é recomendada a utilização de alguns dos ícones baseados na norma internacional NAMUR NE107 para reportar as diferentes classificações de problemas resultantes da aplicação das técnicas dessa tese. Propõe-se que essas técnicas sejam embarcadas em aplicativos computacionais de gerenciamento de ativos para melhorar a confiabilidade da medição, antecipar rotinas de manutenção dos instrumentos e aumentar a segurança da planta industrial através de reportes adequados aos usuários dos problemas de medição de nível e do mapeamento das fases do processo. / The aim of this Thesis is to detect and classify level measurement problems by free wave propagation radars using ANN (artificial neural network) and SVM (support vector machines) with statistical pre-processing data. In the first scenario, a controlled environment was build in order to get the preliminary data. In addition, three other scenarios with real industry data was considered. Therefore, some topologies of neural networks and SVM in four different scenarios were tested and it was demonstrated the efficiency of ANN to reach an accuracy rate of 100% for the first scenario, 93.51% for the second, 99.75% for third and 99.94% for the fourth scenario. For these same four scenarios, the results of SVM classification were 100%, 84.41%, 93.74% and 96.40%. After classifying the problems by ANN or SVM, it is recommended to use some of the icons following the international standard NAMUR NE107 to report the different classifications of problems within this thesis. It is proposed that these techniques be embedded in asset management environment to improve the reliability of level measurement, antecipate maintenance routines and improve plant safety through adequately reporting the classified problems and mapping stage of the process to the users.