Segmentação de uma imagem é um processo de extrema importância em processamento de imagens e consiste em subdividir a imagem em partes constituintes correspondentes a objetos de interesse no domínio de aplicação. Objetos de interesse podem apresentar cores que se caracterizam numa imagem por um conjunto de pixels, que por sua vez possuem um número muito grande de valores cromáticos. Estes conjuntos podem ser denominados por relativamente poucos rótulos lingüísticos atribuídos por seres humanos, caracterizando as cores, representadas por classes. Entretanto, a fronteira entre estas classes é vaga, pois os valores cromáticos que definem a transição de uma cor para outra dependem de diversos fatores do domínio. Esta tese visa contribuir no processo de segmentação de imagens através da proposta de um classificador de pixels exclusivamente por meio do atributo cor. Para lidar com o problema da vagueza entre as classes de cores, emprega-se a teoria dos conjuntos nebulosos. Assim, propõe-se um aprendizado híbrido e incremental de modelos nebulosos de classes de cores constituintes do classificador. O aprendizado híbrido combina os paradigmas de aprendizado supervisionado e não-supervisionado, transferindo a rotulação individual das instâncias (muito custosa) para a rotulação dos grupos de instâncias similares, pelo agente supervisor. Estes grupos são combinados por meio da aplicação de operadores de agregação adequados, que possibilitam uma forma de aprendizado incremental, onde os modelos das classes existentes podem ser revisados ou novas classes, obtidas com a continuidade do treinamento, podem ser incorporadas aos modelos. Propõe-se, ainda, um processo de generalização do modelo, visando sua completude. O classificador proposto foi testado na modelagem da cor da pele humana em imagens adquiridas em condições ambientais controladas e em condições variadas. Os resultados obtidos mostram a eficácia do classificador proposto, obtendo uma detecção robusta e acurada da cor da pele em imagens digitais coloridas. / Image segmentation is a very important process, which aims at subdividing an image in parts that correspond to objects of interest in the application domain. Objects may depict few colors that are represented in an image by a set of pixels presenting a very large range of chromatic values. A relatively small number of human-defined linguistic labels can be assigned to these sets, and these labels characterize colors represented by classes. However, the borders among these classes are fuzzy, since the chromatic values that define the transition from a class to another depend on different domain factors. This thesis contributes in the image segmentation process by proposing a pixel classifier based exclusively on the color attribute. Fuzzy sets theory is used to deal with the problem of fuzziness among color classes. This thesis proposes a hybrid and incremental scheme for learning fuzzy models of color classes included in the classifier. The hybrid-learning scheme combines unsupervised and supervised learning paradigms, transferring the labeling by a supervisor from individual instances (a very computationally costly task) to groups of similar instances. These groups are combined by application of adequate aggregation operators, providing an incremental learning scheme to the classifier, so that models can be revised and new classes can be incorporated into the models. In order to provide completeness to the models, a generalization process is also proposed. The classifier was tested in the human skin color-modeling problem, by using digital color-images captured under controlled and uncontrolled conditions. Experimental results assess its effectiveness, providing a robust and accurate detection of skin color in digital color-images.

by Wai-chuen Tso. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1995. / Includes bibliographical references (leaves 90-94). / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Prior Information --- p.5 / Chapter 2.1 --- Prior Distribution --- p.6 / Chapter 2.2 --- Quantification of Prior Belief --- p.10 / Chapter 2.2.1 --- Prior Belief --- p.10 / Chapter 2.2.2 --- Some Basic Concepts of Fuzzy Set Theory --- p.12 / Chapter 2.2.3 --- Quantification --- p.16 / Chapter 2.3 --- Specification and Determination of Model Parameters --- p.20 / Chapter 2.3.1 --- A Questionnaire --- p.21 / Chapter 2.3.2 --- Parameter Value --- p.22 / Chapter 2.3.3 --- Determination of Degree of Fuzziness --- p.23 / Chapter 2.4 --- Comments --- p.26 / Chapter 2.4.1 --- Interpretation of Time Length of Poisson Process --- p.26 / Chapter 2.4.2 --- Likelihood Interpretation of Membership Value --- p.28 / Chapter 2.4.3 --- Comparison with Existing Modeling --- p.30 / Chapter 2.4.4 --- Conclusion of Prior Information --- p.31 / Chapter 3 --- Posterior Analysis --- p.33 / Chapter 3.1 --- Posterior Analysis by Monte Carlo Method --- p.34 / Chapter 3.1.1 --- Monte Carlo Method --- p.34 / Chapter 3.1.2 --- Estimation of Posterior Mean and Posterior Variance of Log-odds Ratio --- p.35 / Chapter 3.1.3 --- Construction of Credible Region of Log-odds Ratio --- p.38 / Chapter 3.1.4 --- Estimation of Posterior Mean of Cell Probability --- p.41 / Chapter 3.2 --- Sampling of Prior Cell Frequency Vector by Gibbs Sampler --- p.42 / Chapter 3.2.1 --- Gibbs Sampler --- p.42 / Chapter 3.2.2 --- Two Sampling Algorithms --- p.45 / Chapter 3.2.3 --- Acceptance-Rejection Algorithm --- p.50 / Chapter 3.3 --- Some Practical Problems --- p.51 / Chapter 3.3.1 --- Number of Iterations in Gibbs Sampler --- p.51 / Chapter 3.3.2 --- Sample Size of Gibbs Sample --- p.53 / Chapter 4 --- Simulation Study --- p.58 / Chapter 4.1 --- Multinomial Model --- p.59 / Chapter 4.1.1 --- Determination of Number of Iterations --- p.61 / Chapter 4.1.2 --- Determination of Sample Size --- p.62 / Chapter 4.1.3 --- Posterior Estimation --- p.63 / Chapter 4.1.4 --- Sensitivity Analysis --- p.64 / Chapter 4.2 --- Poisson Model --- p.71 / Chapter 4.2.1 --- Determination of Number of Iterations --- p.72 / Chapter 4.2.2 --- Determination of Sample Size --- p.73 / Chapter 4.2.3 --- Posterior Estimation --- p.74 / Chapter 4.2.4 --- Sensitivity Analysis --- p.75 / Chapter 4.3 --- Conclusion --- p.82 / Chapter 5 --- Conclusions and Discussions --- p.85 / References --- p.90

Neste trabalho é proposto um novo modelo para análise empírica de sobre-reação e sub-reação no mercado de ações. O modelo proposto é baseado em uma técnica de classificação de padrão fuzzy, que permite estabelecer uma relação com as heurísticas de representatividade e ancoramento, oriundas da teoria de finanças comportamentais. O modelo é usado para classificar ações com base nos índices financeiros de companhias abertas. Resultados numéricos ilustram o procedimento de análise para ações do setor de petróleo/petroquímica e do setor têxtil do mercado brasileiro, com indicadores financeiros relativos ao período de 1994 a 2005. / In this work a new model for empirical analysis of stock market overreaction and underreaction is proposed. Such model is based on a fuzzy pattern classification technique, which is strongly connected to the representativeness and anchoring heuristics from behavioral finance. The proposed model is used for stock classification by exploring financial ratios of public companies. Numerical results illustrate the analysis procedure in the cases of the petroleum/petrochemical and textile stocks from the Brazilian market, with financial ratios ranging from 1994 to 2005.

Orientador: Rodney Carlos Bassanezi / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-09-11T21:18:32Z (GMT). No. of bitstreams: 1 Leite_JeffersonCruzdosSantos_D.pdf: 39583926 bytes, checksum: ac69c5a564ed32a9d1eb58ac0e71c1fd (MD5) Previous issue date: 2011 / Resumo: Neste trabalho definiremos solução fuzzy para problemas que envolvam difusão e exploraremos algumas propriedades importantes como unicidade e estabilidade dessas soluções. Basicamente estamos interessados em considerar algumas características importantes desses problemas difusivos como incertos, para isso, usaremos o conceito de numero fuzzy. Termos como coeficiente de difusão e condição inicial serão considerados como incertos e através da extensão de Zadeh aplicado a solução da equação determinística associada ao problema teremos a solução fuzzy. Serão obtidas também soluções via base de regras, utilizando sistemas dinâmicos pfuzzy, garantindo assim, uma maneira eficiente e prática de obtermos, boas respostas para os problemas, sem necessariamente termos as soluções explícitas. Aplicações desses resultados também serão apresentados / Abstract: This work will define fuzzy solution for problems involving di_usion and explore some important properties such as uniqueness and stability of these solutions. Basically we are interested in considering some important features of these diffusion problems as uncertain and, we use the concept of fuzzy numbers for this. Terms such as diffusion coefficient and initial condition are considered as uncertain and by the extension of Zadeh's solution applied to deterministic equation associated with the problem we have the fuzzy solution. Solutions for rule-base situations are also obtained, using p-fuzzy dynamic systems, thus guaranteeing an, efficient and practical way of obtaining adequate answers to the problems, not necessarily under the explicit solutions. Applications of these results will also be discussed / Doutorado / Matematica Aplicada / Doutor em Matemática Aplicada

Excessive high-frequency jitter or low-frequency wander can create problems within synchronous transmission systems and must be kept within limits to ensure reliable network operation. The emerging Synchronous Optical NETwork (SONET) introduces additional challenges for jitter and wander attenuation equipment (called desynchronizers) when used to carry payloads from the existing Plesiochronous Digital Hierarchy (PDH), such as the DS3. The difficulty is primarily due to the large phase transients resulting from the pointer-based justification technique employed by SONET (called Pointer Justification Events or PJEs). While some previous desynchronization techniques consider the buffer level in their control actions, none has explicitly considered wander generation. Instead, compliance with jitter, wander, and buffer-size constraints have typically been met implicitly--through testing and tuning of the Phase Locked Loop (PLL) controller. We investigated a fuzzy/rule-based solution to this desynchronization/constraint-satisfaction problem. But rather than mapping the input state to an action, as is done in standard fuzzy logic, our controller maps a state and a candidate action to a desired result. In other words, this control paradigm employs prediction to evaluate which of a set of candidate actions would result in the "best" predicted performance. Before the controller could predict an action's affect on buffer and wander levels, appropriate models were required. The model of the buffer is simply the integral of the frequency difference between the input and output of the PLL, and a novel MTIE Constraint Envelope technique was developed to evaluate future wander performance. We show that a predictive knowledge-based controller is capable of achieving the following three objectives: (1) Reduce jitter implicitly by avoiding unnecessary frequency changes such that the jitter limits specified in relevant standards are met, (2) Explicitly satisfy both buffer-level and wander (MTIE) constraints by trading off performance in one to meet the hard limit of the other, (3) When both buffer-level and wander constraints are in danger of violation and cannot be satisfied simultaneously, maintain the preferred constraint by sacrificing the other. We also show that the computation required for this control algorithm is easily within the reach of modern microprocessors.

The body motion of patients, during magnetic resonance (MR) imaging causes significant artifacts in the reconstructed image. Artifacts are manifested as a motion induced blur and ghost repetitions of the moving structures. which obscure vital anatomical and pathological detail. The techniques that have been proposed for suppressing motion artifacts fall into two major categories. Real-time techniques attempt to prevent the motion from corrupting the data by restricting the data acquisition times or motion of the patients, whereas the post-processing techniques use the information embedded in the corrupted data to restore the image. Most methods currently in widespread use belong to the real-time techniques, however with the advent of fast computing platforms and sophisticated signal processing algorithms, the emergence of post-processing techniques is clearly evident. The post-processing techniques usually demand an appropriate model of the motion. The restoration of the image requires that the motion parameters be determined in order to invert the data degradation process. Methods for the correction of translational motion have been studied extensively in the past. The subject of this thesis encompasses the rotational motion model and the effect of rotational motion on the collected MR data in the spatial frequency space (k-space), which is in general, more complicated than the translational model. Rotational motion artifacts are notably prevalent in MR images of head, brain and limbs. Post-processing techniques for the correction of rotational motion artifacts often involve interpolation and re-gridding of the acquired data in the k-space. These methods create significant data overlap and void regions. Therefore, in the past, proposed corrective techniques have been limited to suppression of artifacts caused by small angle rotations. This thesis presents a method of managing overlap regions, using weighted averaging of redundant data, in order to correct for large angle rotations. An iterative estimation technique for filling the data void regions has also been developed by the use of iterated application of projection operators onto constraint sets. These constraint sets are derived from the k-space data generated by the MR imager, and available a priori knowledge. It is shown that the iterative algorithm diverges at times from the required image, due to inconsistency among the constraint sets. It is also shown that this can be overcome by using soft. constraint sets and fuzzy projections. One of the constraints applied in the iterative algorithm is the finite support of the imaged object, marked by the outer boundary of the region of interest (ROI). However, object boundary extraction directly from the motion affected MR image can be difficult, specially if the motion function of the object is unknown. This thesis presents a new ROI extraction scheme based on entropy minimization in the image background. The object rotation function is usually unknown or unable to be measured with sufficient accuracy. The motion estimation algorithm proposed in this thesis is based on maximizing the similarity among the k-space data subjected to angular overlap. This method is different to the typically applied parameter estimation technique based on minimization of pixel energy outside the ROI, and has higher efficiency and ability to estimate rotational motion parameters in the midst of concurrent translational motion. The algorithms for ROI extraction, rotation estimation and data correction have been tested with both phantom images and spin echo MR images producing encouraging results.

No description available.

A neutrosophic set is a part of neutrosophy that studies the origin, nature, and scope of neutralities, as well as their interactions with different ideational spectra. The neutrosophic set is a powerful general formal framework that has been recently proposed. However, the neutrosophic set needs to be specified from a technical point of view. Here, we define the set-theoretic operators on an instance of a neutrosophic set, and call it an Interval Neutrosophic Set (INS). We prove various properties of INS, which are connected to operations and relations over INS. We also introduce a new logic system based on interval neutrosophic sets. We study the interval neutrosophic propositional calculus and interval neutrosophic predicate calculus. We also create a neutrosophic logic inference system based on interval neutrosophic logic. Under the framework of the interval neutrosophic set, we propose a data model based on the special case of the interval neutrosophic sets called Neutrosophic Data Model. This data model is the extension of fuzzy data model and paraconsistent data model. We generalize the set-theoretic operators and relation-theoretic operators of fuzzy relations and paraconsistent relations to neutrosophic relations. We propose the generalized SQL query constructs and tuple-relational calculus for Neutrosophic Data Model. We also design an architecture of Semantic Web Services agent based on the interval neutrosophic logic and do the simulation study.

Fonaments de la Matemàtica per al tractament de la Incertesa. Noves aportacions a l’estudi de les Equacions Borroses i de les Equacions Diferencials Borroses. Aplicacions de la Matemàtica de la Incertesa al comportament de models de la teoria econòmica.

Construction industry is a one of the most risky sectors due to high level of uncertainties included in the nature of the construction projects. Although there are many reasons, the deficiency of cash is one of the main factors threatening the success of the construction projects and causing business failures. Therefore, an appropriate cash planning technique is necessary for adequate cost control and efficient cash management while considering the risks and uncertainties of the construction projects. The main objective of this thesis is to develop a realistic, reliable and cost-schedule integrated cash flow modeling technique by using fuzzy set theory for including the uncertainties in project cost and schedule resulting from complex and ambiguous nature of construction works. The linguistic expressions are used for utilizing from human judgment and approximate reasoning ability of users for reflecting their experience into the model to create cash flow scenarios. The uncertain cost and duration estimates gathered from experts are inserted in the model as fuzzy numbers. The model provides the user different net cash flow scenarios with fuzzy formats that are beneficial for foreseeing possible cost and schedule threats to the project during the tender stage. The model is generated in Microsoft Excel 2007 using Visual Basic for applications and the model is applied to a case example.