Elaborate sexual ornaments evolve because mate choice exerts strong sexual selection favouring individuals with high levels of ornament expression. Consequently, even at evolutionary equilibrium, life history theory predicts that ornamental traits should be under directional sexual selection that opposes contrasting selection to reduce the costs associated with their maintenance. Otherwise, the resources used to maintain ornaments should be used to improve other life history functions. Elaborate female ornaments have only evolved in a few species, despite females commonly experiencing strong sexual selection. One explanation for this rarity is that male preferences for female ornaments may be self-limiting: females with higher mating success become less attractive because of the lower paternity share they provide to mates with every additional sperm competitor. The unusual species in which female ornaments do occur can provide rare insight into how selection can favour the expression of expensive characters in females despite their costs. The main goal of my thesis was to determine how sexual selection acts on exaggerated sexual ornaments, and give new insight into how these ornaments may have evolved, in spite of the self-limiting nature of selection on male preferences. To determine the strength of sexual selection acting on female ornamentation in dance flies, we developed new microsatellite markers to assess polyandry rates by genotyping stored sperm in wild female dance flies. We first used polyandry rates to determine whether ornament expression was associated with higher mating success in female Rhamphomyia longicauda, a species that has evolved two distinct and exaggerated female ornaments. Contrary to our predictions, we found no evidence that females with larger ornaments enjoy higher mating success. We then compared polyandry rates in R. longicauda to those of two other species of dance fly, one (Empis aestiva) that has i independently evolved female ornaments on its legs, and another (E. tessellata) that does not possess any discernable female ornaments. We also estimated the opportunity for sexual selection, which we found to be similar and relatively low in all three species. Moreover, the standardized sexual selection gradients for ornaments were weak and non-significant in all three species. Females with more elaborate ornaments, in both within- and cross-species comparisons, therefore did not enjoy higher mating success. Overall, these results suggested that sexual selection operates rather differently in females compared to males, potentially explaining the general rarity of female ornaments. Our amplifications of stored sperm were able to reveal more than just mate numbers. We developed new methods to study patterns of sperm storage in wild female dance flies. We investigated how the skew in sperm genotypes from mixed sperm stores changed with varying levels of polyandry. Our data suggested that sperm stores were dominated by a single male in R. longicauda, and that the proportion of sperm contributed by this dominant male was largely independent of the number of rival males’ sperm present in the spermatheca. These results were consistent with the expectation of males using sperm ‘offence strategies’ in sperm competition and that the most successful male is likely to be the female’s last partner before oviposition. As a whole, my thesis contributed new molecular resources for an understudied and fascinating group of organisms. It exploited these new resources to provide the first estimates of lifetime mating success in several related species, and suggested that the general prediction that ornament expression should covary with sexual selection intensity does not seem to hold in this group. Instead, both the unusual prevalence of ii ornaments and the inconsistent evidence for sexual selection that sustains them in dance flies may owe their existence to the confluence of two important factors. First, the conditions under which sperm competition occurs: as last male precedence is likely, males are selected to prefer the most gravid females to secure a high fraction of her offspring’s paternity as they are unlikely to mate again before oviposition. Second, potent sexually antagonistic coevolution between hungry females and discerning males: females have evolved ornaments to disguise their stage of egg maturity to receive the benefits of nuptial gifts, while males face the challenge of distinguishing between gravidity and ornamentation in females.

Cette thèse propose trois extensions de la Régression linéaire par tranches (Sliced Inverse Regression, SIR), notamment Collaborative SIR, Student SIR et Knockoff SIR.Une des faiblesses de la méthode SIR est l’impossibilité de vérifier si la Linearity Design Condition (LDC) est respectée. Il est établi que, si x suit une distribution elliptique, la condition est vraie ; dans le cas d’une composition de distributions elliptiques il n y a aucune garantie que la condition soit vérifiée globalement, pourtant, elle est respectée localement.On va donc proposer une extension sur la base de cette considération. Étant donné une variable explicative x, Collaborative SIR réalise d’abord un clustering. Pour chaque cluster, la méthode SIR est appliquée de manière indépendante.Le résultat de chaque composant contribue à créer la solution finale.Le deuxième papier, Student SIR, dérive de la nécessité de robustifier la méthode SIR.Vu que cette dernière repose sur l’estimation de la covariance et contient une étape APC, alors elle est sensible au bruit.Afin d’étendre la méthode SIR on a utilisé une stratégie fondée sur une formulation inverse du SIR, proposée par R.D. Cook.Finalement, Knockoff SIR est une extension de la méthode SIR pour la sélection des variables et la recherche d’une solution sparse, ayant son fondement dans le papier publié par R.F. Barber et E.J. Candès qui met l’accent sur le false discovery rate dans le cadre de la régression. L’idée sous-jacente à notre papier est de créer des copies de variables d’origine ayant certaines proprietés.On va montrer que la méthode SIR est robuste par rapport aux copies et on va proposer une stratégie pour utiliser les résultats dans la sélection des variables et pour générer des solutions sparse / This thesis proposes three extensions of Sliced Inverse Regression namely: Collaborative SIR, Student SIR and Knockoff SIR.One of the weak points of SIR is the impossibility to check if the Linearity Design Condition (LDC) holds. It is known that if X follows an elliptic distribution thecondition holds true, in case of a mixture of elliptic distributions there are no guaranties that the condition is satisfied globally, but locally holds. Starting from this consideration an extension is proposed. Given the predictor variable X, Collaborative SIR performs initially a clustering. In each cluster, SIR is applied independently. The result from each component collaborates to give the final solution.Our second contribution, Student SIR, comes from the need to robustify SIR. Since SIR is based on the estimation of the covariance, and contains a PCA step, it is indeed sensitive to noise. To extend SIR, an approach based on a inverse formulation of SIR proposed by R.D. Cook has been used.Finally Knockoff SIR is an extension of SIR to perform variable selection and give sparse solution that has its foundations in a recently published paper by R. F. Barber and E. J. Candès that focuses on the false discovery rate in the regression framework. The underlying idea of this paper is to construct copies of the original variables that have some properties. It is shown that SIR is robust to this copies and a strategy is proposed to use this result for variable selection and to generate sparse solutions.

abstract: Public health surveillance is a special case of the general problem where counts (or rates) of events are monitored for changes. Modern data complements event counts with many additional measurements (such as geographic, demographic, and others) that comprise high-dimensional covariates. This leads to an important challenge to detect a change that only occurs within a region, initially unspecified, defined by these covariates. Current methods are typically limited to spatial and/or temporal covariate information and often fail to use all the information available in modern data that can be paramount in unveiling these subtle changes. Additional complexities associated with modern health data that are often not accounted for by traditional methods include: covariates of mixed type, missing values, and high-order interactions among covariates. This work proposes a transform of public health surveillance to supervised learning, so that an appropriate learner can inherently address all the complexities described previously. At the same time, quantitative measures from the learner can be used to define signal criteria to detect changes in rates of events. A Feature Selection (FS) method is used to identify covariates that contribute to a model and to generate a signal. A measure of statistical significance is included to control false alarms. An alternative Percentile method identifies the specific cases that lead to changes using class probability estimates from tree-based ensembles. This second method is intended to be less computationally intensive and significantly simpler to implement. Finally, a third method labeled Rule-Based Feature Value Selection (RBFVS) is proposed for identifying the specific regions in high-dimensional space where the changes are occurring. Results on simulated examples are used to compare the FS method and the Percentile method. Note this work emphasizes the application of the proposed methods on public health surveillance. Nonetheless, these methods can easily be extended to a variety of applications where counts (or rates) of events are monitored for changes. Such problems commonly occur in domains such as manufacturing, economics, environmental systems, engineering, as well as in public health. / Dissertation/Thesis / Ph.D. Industrial Engineering 2010

O objetivo geral desta dissertação é analisar o não dito sobre os requisitos de seleção de pessoal das empresas de telefonia móvel, através de vagas encaminhadas para empresas intermediadoras de emprego. O estudo está centrado em três grandes eixos: a flexibilização, os requisitos descritos e os requisitos não descritos nas seleções realizadas por intermediadoras de emprego para as empresas de telefonia móvel. O primeiro eixo diz respeito ao contexto em que ocorrem os processos seletivos e verifica os aspectos explícitos e implícitos das relações flexíveis estabelecidas entre operadoras e empresas intermediadoras. O segundo eixo está centrado na análise dos requisitos descritos como necessários para os cargos, sendo esses critérios os anunciados para os candidatos. O terceiro eixo, por fim, analisa os requisitos não descritos, aqui nomeados como “não ditos”e não anunciados, mas praticados pelas empresas e determinantes para contratação ou exclusão de candidatos. Trata-se de uma pesquisa de abordagem qualitativo-exploratória. A coleta de dados foi realizada através de entrevistas semiestruturadas, realizadas com 14 sujeitos – gestores, selecionadores e trabalhadores – que atuam em empresas intermediadoras de emprego. O estudo constata que as vagas encaminhadas para as empresas intermediadoras são predominantemente operacionais e temporárias e que os processos seletivos realizados ocorrem mediante pressão por cumprimento de prazos e metas impostas pelas operadoras. A pesquisa revela que os requisitos de seleção de pessoal vão além dos descritos e anunciados socialmente, identificando 12 elementos que não constam no perfil formal das empresas, mas que são considerados na seleção. Com isso, questiona a negação da subjetividade e discurso de imparcialidade e neutralidade nos processos seletivos sustentados por correntes tradicionais da Administração e Psicologia. O estudo também discute a aplicação do modelo de competências no contexto de submissão e pressão por prazos em que estão inseridas as intermediadoras e conclui que o seu caráter subjetivo e ainda incipiente, em termos de ferramentas de avaliação, ajuda a mascarar os requisitos velados. / The objective of this paper in general is to analyze the untold about the requirements for personnel selection of mobile phone companies through vacancies taken to job brokerage companies. The study focuses on three main areas: flexibility, the requirements described and the requirements that are not described in the selections made by job brokerage companies to the mobile phone companies. The first axis is related to the context in which there are selective processes and it verifies the explicit and implicit aspects of flexible relations established between operators and brokerage companies. The second axis focuses on the analysis of the requirements needed for the positions described, these being the advertised criteria for applicants. The third axis, finally, discusses the requirements that are not described, here named as "untold" and not announced, but practiced by companies and fundamental to the recruitment or exclusion of applicants. This is an exploratory qualitative research approach. Data collection was conducted through semi structured interviews with 14 individuals - managers, pickers and workers - who work for job brokerage companies. The study points out that the vacancies taken to the job brokerage companies are mainly operational, temporary and the selective processes occur under pressure because of meeting deadlines and targets imposed by the operators. The research reveals that the requirements for personnel selection go beyond those described and announced socially, identifying 12 elements not found in the formal profile of the companies, but considered in the selection. Thus, it questions the denial of subjectivity and discourse of impartiality and neutrality in the selection processes supported by traditional patterns of management and psychology. The study also discusses the application of the competency model in the context of submission and pressure for deadlines in which job brokerage companies are embedded and it concludes that its subjective and still nascent nature in terms of assessment tools helps mask the hidden requirements.

abstract: During the 1960s, the long-standing idea that traits or behaviors could be explained by natural selection acting on traits that persisted "for the good of the group" prompted a series of debates about group-level selection and the effectiveness with which natural selection could act at or across multiple levels of biological organization. For some this topic remains contentious, while others consider the debate settled, even while disagreeing about when and how resolution occurred, raising the question: "Why have these debates continued?" Here I explore the biology, history, and philosophy of the possibility of natural selection operating at levels of biological organization other than the organism by focusing on debates about group-level selection that have occurred since the 1960s. In particular, I use experimental, historical, and synthetic methods to review how the debates have changed, and whether different uses of the same words and concepts can lead to different interpretations of the same experimental data. I begin with the results of a group-selection experiment I conducted using the parasitoid wasp Nasonia, and discuss how the interpretation depends on how one conceives of and defines a "group." Then I review the history of the group selection controversy and argue that this history is best interpreted as multiple, interrelated debates rather than a single continuous debate. Furthermore, I show how the aspects of these debates that have changed the most are related to theoretical content and empirical data, while disputes related to methods remain largely unchanged. Synthesizing this material, I distinguish four different "approaches" to the study of multilevel selection based on the questions and methods used by researchers, and I use the results of the Nasonia experiment to discuss how each approach can lead to different interpretations of the same experimental data. I argue that this realization can help to explain why debates about group and multilevel selection have persisted for nearly sixty years. Finally, the conclusions of this dissertation apply beyond evolutionary biology by providing an illustration of how key concepts can change over time, and how failing to appreciate this fact can lead to ongoing controversy within a scientific field. / Dissertation/Thesis / Doctoral Dissertation Biology 2014

abstract: The Modern Synthesis embodies a theory of natural selection where selection is to be fundamentally understood in terms of measures of fitness and the covariance of reproductive success and trait or character variables. Whether made explicit or left implicit, the notion that selection requires that some trait variable cause reproductive success has been deemphasized in our modern understanding of exactly what selection amounts to. The dissertation seeks to advance a theory of natural selection that is fundamentally causal. By focusing on the causal nature of natural selection (rather than on fitness or statistical formulae), certain conceptual and methodological problems are seen in a new, clarifying light and avenues toward new, interesting solutions to those problems are illustrated. First, the dissertation offers an update to explicitly causal theories of when exactly a trait counts as an adaptation upon fixation in a population and draws out theoretical and practical implications for evolutionary biology. Second, I examine a case of a novel character that evolves by niche construction and argue that it evolves by selection for it and consider implications for understanding adaptations and drift. The third contribution of the dissertation is an argument for the importance of defining group selection causally and an argument against model pluralism in the levels of selection debate. Fourth, the dissertation makes a methodological contribution. I offer the first steps toward an explicitly causal methodology for inferring the causes of selection—something often required in addition to inferring the causes of reproductive success. The concluding chapter summarizes the work and discusses potential paths for future work. / Dissertation/Thesis / Doctoral Dissertation Biology 2016

Submitted by Bruna Rodrigues (bruna92rodrigues@yahoo.com.br) on 2017-10-02T12:13:16Z No. of bitstreams: 1 DissLRR.pdf: 4462451 bytes, checksum: cd5651c604894410c0918ddc5d0b7551 (MD5) / Approved for entry into archive by Ronildo Prado (bco.producao.intelectual@gmail.com) on 2018-02-05T17:09:32Z (GMT) No. of bitstreams: 1 DissLRR.pdf: 4462451 bytes, checksum: cd5651c604894410c0918ddc5d0b7551 (MD5) / Approved for entry into archive by Ronildo Prado (bco.producao.intelectual@gmail.com) on 2018-02-05T17:09:45Z (GMT) No. of bitstreams: 1 DissLRR.pdf: 4462451 bytes, checksum: cd5651c604894410c0918ddc5d0b7551 (MD5) / Made available in DSpace on 2018-02-05T17:17:58Z (GMT). No. of bitstreams: 1 DissLRR.pdf: 4462451 bytes, checksum: cd5651c604894410c0918ddc5d0b7551 (MD5) Previous issue date: 2017-05-18 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / The issue of sustainability, which is an increasingly important consideration in the day-to-day operations of businesses, needs to be addressed in the context of supplier selection. The use of multi-criteria approaches in decisions concerning the selection of sustainable suppliers can be a valuable approach for helping to resolve the complexity of this process. A systematic review of the literature highlighted gaps in the research in this area, such as the lack of a detailed description of multi-criteria methods, as well as a scarcity of sustainability criteria that take into account the three main perspectives (Economic, Environmental, and Social). This work describes the development and real case application of a DEMATEL (Decision-Making Trial and Evaluation Laboratory) and ANP (Analytic Network Process) fuzzy modeling technique for the selection of sustainable suppliers. The methodological approach used in the research was quantitative, descriptive, and empirical. The modeling and simulations were performed using MATLAB®. Incorporation of the specificities of the process of selection of sustainable suppliers makes the model a useful tool for use by both businesses and researchers concerned with the issue of sustainability. A systematic review of the published research highlights the main state-of-art methods and criteria used for the selection of green and sustainable suppliers. The model is described in a framework highlighting each step of the application. It was subsequently applied by a major glass packaging company, where the supply chain coordinator agreed to assist in the research. The outputs of the second phase of the model showed that the Economic cluster was most important and interacted with the Environmental cluster, while the Social cluster remained practically inert, without interactions with the other clusters. For the three perspectives, the three most influential criteria were as follows: cost, compliance, and quality (Economic perspective); environmental certifications/ISO 14001, reuse/recovery, and pollution control (Environmental perspective); and stakeholder rights, respect for policies, and encouragement of the development of self-sustainable recycling programs (Social perspective). Finally, a supplier was selected using the framework presented, and the criteria that most influenced the decision were highlighted. The procedure developed here offers a tool to assist businesses searching for sustainable solutions, as well as researchers in the scientific community concerned with the development of knowledge in this area. / A temática sustentável, cada vez mais presente e atuante no cotidiano das operações das empresas precisa ser tratada no contexto da seleção de fornecedores. Aplicar abordagens de decisão multicritério para a seleção de fornecedores sustentáveis demonstra ser uma alternativa interessante a fim de lidar com a natureza complexa deste processo. Por meio de uma revisão sistemática da literatura foi possível destacar algumas lacunas de pesquisa, como a falta de uma visão detalhada dos métodos multicritérios e uma escassa abordagem de critérios sustentáveis, abordando as três perspectivas (Econômica, Ambiental e Social). Desta forma, o objetivo central da pesquisa é detalhar e aplicar em um caso real a modelagem fuzzy DEMATEL (Decision-making Trial and Evaluation Laboratory) e fuzzy ANP (Analytic Network Process) para a seleção de fornecedores sustentáveis. A abordagem metodológica empregada na pesquisa é quantitativa descritiva empírica, com aplicação de modelagem e simulação em MATLAB ®. Espera-se que o modelo possa internalizar as especificidades do processo de seleção de fornecedores sustentáveis de modo a tornar-se uma ferramenta útil às empresas e aos pesquisadores que estudam o método. A revisão sistemática da pesquisa pode destacar os principais métodos na literatura e os principais critérios utilizados pela seleção de fornecedores verdes e sustentáveis no estado da arte. O modelo foi detalhado em um framework, destacando-se cada passo da aplicação. Posteriormente foi aplicado em uma empresa de grande porte de embalagens vítreas, onde a coordenadora de Supply Chain se dispôs a auxiliar na pesquisa. Como saídas da segunda fase do modelo, o cluster Econômico revelou ser o mais importante e exerce influência sob o cluster Ambiental, já o cluster Social permanece praticamente inerte sem exercer ou receber influência. Também pode-se destacar que os três critérios mais influentes de cada perspectiva foram: ‘Custo’, ‘Compliance’ e ‘Qualidade’ na perspectiva Econômica; ‘Certificações Ambientais / ISO 14001’, Reuso / Recuperação e ‘Controle da Poluição’ na perspectiva Ambiental; e ‘Direitos dos Stakeholders’, ‘Respeito pelas políticas’ e ‘Incentivo ao desenvolvimento de programas de reciclagem auto-sustentáveis’ na perspectiva Social. Ao final, um fornecedor é escolhido com o framework apresentado, e os critérios mais influentes na decisão foram destacados. Esta discussão é válida para auxiliar empresas em busca de soluções sustentáveis e pesquisadores na área que desenvolvem o conhecimento para a comunidade científica.

O objetivo geral desta dissertação é analisar o não dito sobre os requisitos de seleção de pessoal das empresas de telefonia móvel, através de vagas encaminhadas para empresas intermediadoras de emprego. O estudo está centrado em três grandes eixos: a flexibilização, os requisitos descritos e os requisitos não descritos nas seleções realizadas por intermediadoras de emprego para as empresas de telefonia móvel. O primeiro eixo diz respeito ao contexto em que ocorrem os processos seletivos e verifica os aspectos explícitos e implícitos das relações flexíveis estabelecidas entre operadoras e empresas intermediadoras. O segundo eixo está centrado na análise dos requisitos descritos como necessários para os cargos, sendo esses critérios os anunciados para os candidatos. O terceiro eixo, por fim, analisa os requisitos não descritos, aqui nomeados como “não ditos”e não anunciados, mas praticados pelas empresas e determinantes para contratação ou exclusão de candidatos. Trata-se de uma pesquisa de abordagem qualitativo-exploratória. A coleta de dados foi realizada através de entrevistas semiestruturadas, realizadas com 14 sujeitos – gestores, selecionadores e trabalhadores – que atuam em empresas intermediadoras de emprego. O estudo constata que as vagas encaminhadas para as empresas intermediadoras são predominantemente operacionais e temporárias e que os processos seletivos realizados ocorrem mediante pressão por cumprimento de prazos e metas impostas pelas operadoras. A pesquisa revela que os requisitos de seleção de pessoal vão além dos descritos e anunciados socialmente, identificando 12 elementos que não constam no perfil formal das empresas, mas que são considerados na seleção. Com isso, questiona a negação da subjetividade e discurso de imparcialidade e neutralidade nos processos seletivos sustentados por correntes tradicionais da Administração e Psicologia. O estudo também discute a aplicação do modelo de competências no contexto de submissão e pressão por prazos em que estão inseridas as intermediadoras e conclui que o seu caráter subjetivo e ainda incipiente, em termos de ferramentas de avaliação, ajuda a mascarar os requisitos velados. / The objective of this paper in general is to analyze the untold about the requirements for personnel selection of mobile phone companies through vacancies taken to job brokerage companies. The study focuses on three main areas: flexibility, the requirements described and the requirements that are not described in the selections made by job brokerage companies to the mobile phone companies. The first axis is related to the context in which there are selective processes and it verifies the explicit and implicit aspects of flexible relations established between operators and brokerage companies. The second axis focuses on the analysis of the requirements needed for the positions described, these being the advertised criteria for applicants. The third axis, finally, discusses the requirements that are not described, here named as "untold" and not announced, but practiced by companies and fundamental to the recruitment or exclusion of applicants. This is an exploratory qualitative research approach. Data collection was conducted through semi structured interviews with 14 individuals - managers, pickers and workers - who work for job brokerage companies. The study points out that the vacancies taken to the job brokerage companies are mainly operational, temporary and the selective processes occur under pressure because of meeting deadlines and targets imposed by the operators. The research reveals that the requirements for personnel selection go beyond those described and announced socially, identifying 12 elements not found in the formal profile of the companies, but considered in the selection. Thus, it questions the denial of subjectivity and discourse of impartiality and neutrality in the selection processes supported by traditional patterns of management and psychology. The study also discusses the application of the competency model in the context of submission and pressure for deadlines in which job brokerage companies are embedded and it concludes that its subjective and still nascent nature in terms of assessment tools helps mask the hidden requirements.

abstract: Alzheimer's Disease (AD) is the most common form of dementia observed in elderly patients and has significant social-economic impact. There are many initiatives which aim to capture leading causes of AD. Several genetic, imaging, and biochemical markers are being explored to monitor progression of AD and explore treatment and detection options. The primary focus of this thesis is to identify key biomarkers to understand the pathogenesis and prognosis of Alzheimer's Disease. Feature selection is the process of finding a subset of relevant features to develop efficient and robust learning models. It is an active research topic in diverse areas such as computer vision, bioinformatics, information retrieval, chemical informatics, and computational finance. In this work, state of the art feature selection algorithms, such as Student's t-test, Relief-F, Information Gain, Gini Index, Chi-Square, Fisher Kernel Score, Kruskal-Wallis, Minimum Redundancy Maximum Relevance, and Sparse Logistic regression with Stability Selection have been extensively exploited to identify informative features for AD using data from Alzheimer's Disease Neuroimaging Initiative (ADNI). An integrative approach which uses blood plasma protein, Magnetic Resonance Imaging, and psychometric assessment scores biomarkers has been explored. This work also analyzes the techniques to handle unbalanced data and evaluate the efficacy of sampling techniques. Performance of feature selection algorithm is evaluated using the relevance of derived features and the predictive power of the algorithm using Random Forest and Support Vector Machine classifiers. Performance metrics such as Accuracy, Sensitivity and Specificity, and area under the Receiver Operating Characteristic curve (AUC) have been used for evaluation. The feature selection algorithms best suited to analyze AD proteomics data have been proposed. The key biomarkers distinguishing healthy and AD patients, Mild Cognitive Impairment (MCI) converters and non-converters, and healthy and MCI patients have been identified. / Dissertation/Thesis / M.S. Computer Science 2012

abstract: Dynamic channel selection in cognitive radio consists of two main phases. The first phase is spectrum sensing, during which the channels that are occupied by the primary users are detected. The second phase is channel selection, during which the state of the channel to be used by the secondary user is estimated. The existing cognitive radio channel selection literature assumes perfect spectrum sensing. However, this assumption becomes problematic as the noise in the channels increases, resulting in high probability of false alarm and high probability of missed detection. This thesis proposes a solution to this problem by incorporating the estimated state of channel occupancy into a selection cost function. The problem of optimal single-channel selection in cognitive radio is considered. A unique approach to the channel selection problem is proposed which consists of first using a particle filter to estimate the state of channel occupancy and then using the estimated state with a cost function to select a single channel for transmission. The selection cost function provides a means of assessing the various combinations of unoccupied channels in terms of desirability. By minimizing the expected selection cost function over all possible channel occupancy combinations, the optimal hypothesis which identifies the optimal single channel is obtained. Several variations of the proposed cost-based channel selection approach are discussed and simulated in a variety of environments, ranging from low to high number of primary user channels, low to high levels of signal-to-noise ratios, and low to high levels of primary user traffic. / Dissertation/Thesis / M.S. Electrical Engineering 2014