Thesis (M.S.) -- Mississippi State University. Department of Computer Science and Engineering. / Title from title screen. Includes bibliographical references.

Thesis (Ph. D.)--Florida State University, 2006. / Advisor: J. Joseph Cronin Jr., Florida State University, College of Business, Dept. of Marketing. Title and description from dissertation home page (viewed Sept. 27, 2006). Document formatted into pages; contains xi, 209 pages. Includes bibliographical references.

Made available in DSpace on 2014-06-11T19:23:31Z (GMT). No. of bitstreams: 0 Previous issue date: 2002-12Bitstream added on 2014-06-13T18:09:44Z : No. of bitstreams: 1 tsuchiya_i_me_prud.pdf: 799978 bytes, checksum: 9fdf1a044dc4426ea66abb64ee6b3e13 (MD5) / O presente trabalho tem como referência o Projeto de Salvamento Arqueológico de Porto Primavera, cujo objetivo foi resgatar, analisar e conservar os vestígios das antigas civilizações ribeirinhas do Rio Paraná. Uma das etapas de um projeto de salvamento é a prospecção, nela, o arqueólogo realiza a vistoria em toda a área de interesse à procura de indícios das habitações pretéritas, porém, essa etapa é demorada e onerosa. Com base na técnica de modelagem preditiva multivariada (regressão logística), aliada às ferramentas de geoprocessamento, pudemos avaliar as prováveis áreas de ocupação pretérita, reduzindo assim, a etapa de prospeção. Como resultado temos um mapa de classes, com as probabilidades de ocorrência de sítios arqueológicos utilizando o método de regressão logística. / This work has as reference the Project of Archaeological Rescue of Porto Primavera, whose objective was to rescue, to analyze and to conserve the vestiges of the old marginal civilizations of the Paraná River. One of the stages of project is the prospection, in, the archaeologist carries through the inspection in all the area of interest to the search of indications of the past habitations, however, this stage is delayed and onerous. On the basis of the technique of multivaried predictive modeling (logistic regression), allied to the tools of Geographic Information System, we could evaluate the probable areas of past occupation, thus reducing, the stage of prospection. As result we have a map of classrooms, with the probabilities of occurrence of archaeological small farms using the method of logistic regression.

In December 2009 Google had a press release, in which they stated that they would start individualize their users' search results. This is the year individualization began, according to Eli Pariser, who also coined the expression filter bubble. A filter bubble is said to occur when a user only receives individualized feeds, causing them to only consume information that align with their beliefs and excluding them from contradicting information. The main goal of this thesis is to evaluate the existence of filter bubbles and the effects of them. In order to reach the goal, an experiment on a large social media platform is conducted, as well as a qualitative literature study. The experiment consists of fourteen bots that are assigned different behaviors which are performed on a social media platform, which expresses that they use individualization of users' information feeds. The presented results from the experiment are based on data crawled from the bots' feeds. The main finding of the experiment is that no significant filter bubbles are observed and that users experience less exclusion the more of the feed they consume. The literature study consists of 24 papers that both do and do not support the theory of filter bubbles. The main effects found are that filter bubbles fosters polarization of opinions and confirmation bias. It is also said that this could lead to undermining deliberative democracy. / År 2009 talade Google om att de skulle börja anpassa sina sökresultat beroende på vem som använde deras tjänst. Detta lyftes fram av Eli Pariser år 2011, som då myntade uttrycket filterbubbla. Pariser menar att en person befinner sig i en filterbubbla om personen endast konsumerar innehåll som är anpassat efter tidigare visade intressen och därmed blir utesluten från information som utmanar personens åsikter och övertygelser. Det är omdiskuterat huruvida filter bubblor existerar eller inte och vilka effekter som kommer av att en person befinner sig i en. Detta arbete utförs med syfte att utvärdera filter bubblors existens och effekter på både individen och samhället i stort. För att uppfylla syftet genomförs ett experiment och en kvalitativ litteraturstudie. Experimentet består av fjorton nya medlemskonton på en stor social medieplattform där en automatisk mjukvara gillar specifika inlägg under sex veckors tid. Plattformen har uttryckligen framfört att de anpassar användarens flöde av inlägg efter dess beteende. Detta flöde sparas ner för samtliga fjorton konton, två gånger dagligen under sju veckors tid (en vecka extra efter att gillandet av inlägg slutat) och analyseras sedan i jakt på filterbubblor. Genom experimentet att skapa filterbubblor på en social medieplattform hittas inga bevis på att filterbubblor existerar på precis den plattformen. Den kvalitativa litteraturstudien innebär en ingående granskning av vetenskapliga artiklar och avhandlingar inom området. I de 24 arbeten som utvärderas är det åtta stycken som anser att filterbubblor existerar. Flera effekter av filterbubblor hittas i litteraturen och en av de negativa effekterna filterbubblor kan ha på individen är att förstärka behovet att bekräfta sina fördomar. Samhället kan också drabbas av effekter från filterbubblor, såsom försvagande av deliberativ demokrati. Deliberativ demokrati, även kallat samtalsdemokrati lyfter vikten av kommunikation för att utveckla och förstärka en demokrati.

Resumo: O presente trabalho tem como referência o Projeto de Salvamento Arqueológico de Porto Primavera, cujo objetivo foi resgatar, analisar e conservar os vestígios das antigas civilizações ribeirinhas do Rio Paraná. Uma das etapas de um projeto de salvamento é a prospecção, nela, o arqueólogo realiza a vistoria em toda a área de interesse à procura de indícios das habitações pretéritas, porém, essa etapa é demorada e onerosa. Com base na técnica de modelagem preditiva multivariada (regressão logística), aliada às ferramentas de geoprocessamento, pudemos avaliar as prováveis áreas de ocupação pretérita, reduzindo assim, a etapa de prospeção. Como resultado temos um mapa de classes, com as probabilidades de ocorrência de sítios arqueológicos utilizando o método de regressão logística. / Abstract: This work has as reference the Project of Archaeological Rescue of "Porto Primavera", whose objective was to rescue, to analyze and to conserve the vestiges of the old marginal civilizations of the Paraná River. One of the stages of project is the prospection, in, the archaeologist carries through the inspection in all the area of interest to the search of indications of the past habitations, however, this stage is delayed and onerous. On the basis of the technique of multivaried predictive modeling (logistic regression), allied to the tools of Geographic Information System, we could evaluate the probable areas of past occupation, thus reducing, the stage of prospection. As result we have a map of classrooms, with the probabilities of occurrence of archaeological small farms using the method of logistic regression. / Orientador: Vilma Mayumi Tachibana / Coorientador: Nilton Nobuhiro Imai / Banca: José Alberto Quintanilha / Banca: Rosângela Custódio Cortez Thomaz / Mestre

To ensure greater success in its regular projects, Abu-Dhabi Police (ADP) is working on: training their project managers, applying project management software, utilising the services of engineering consultants, etc. However, the performance and outcomes of its projects are still not fully meeting the desired expectations. Therefore, a study to understand some of the undermining factors was carried out. A critical literature review was carried out initially where it was established that project delivery and outcomes are affected in part by the three overarching factors of: project managers’ characteristics, organizational culture and project management culture. On this basis a conceptual framework was developed highlighting how these 3 compound factors affect project performance and outcome; and in particular how ADP’s values relate with the competencies of their project managers. The empirical aspects involved the use of mixed methods where the first part was a quantitative survey of the understanding and achievement of both ADP’s 5 values (part of organizational culture) and 15 competencies (part of project manager’s characteristics), as well as the impact of the former on the later. A questionnaire was administered to 157 people for data collection and 71 fully completed responses were obtained, representing a response rate of 45%. Descriptive statistics were used to evaluate the levels of achievement of ADP’s values and competencies, which were found to be high. The analysis went on to use ordered logistic regression to examine the association between the attainment of ADP’s values and competencies. The findings showed that the 5 values impact on the competencies of ADP’s project managers differently; for example, the value of ‘integrity and honesty’ impacts heavily on the 5 competencies of Integration management, Scope management, Time management, Achieving and action, and Leadership; while the value of ‘effective communication’ impacts heavily on the 3 competencies of Scope management, Cost management, and Achieving and action. An advanced training programme was subsequently developed for ADP to further increase the attainment of values and competencies by their project managers. This programme was developed in focus group discussions that involved some selected project managers who had long working experience and high understanding of ADP project schemes. A further round of focus group discussions was also used to validate this advanced training programme.

Magister Scientiae - MSc / This thesis looks at the effect that the introduction of various techniques (weighting, bootstrapping and variable selection) has on the accuracy of the modelling process when using logistic regression. The data used in the modelling process is based on the sexual activity of entering first-year students at the University of the Western Cape, therefore, by constructing logistic regression models based on this data, certain predictor variables or factors associated with the sexual activity of these students are identified. The sample weighting technique utilized in this thesis assigned a weight to a student based on gender and racial representations within a sample when compared to the population of the entering first-year. The use of a sample weighting technique is shown to produce a more effective modelling process than a modelling process without weighting. The bootstrapping procedure is shown to produce logistic regression models that are more accurate. Utilizing more than 200 bootstrap samples did not necessarily produce logistic regression models that were more accurate than using a total of 200 bootstrap samples. It is, however, concluded that a weighted bootstrap modelling procedure will result in more accurate models compared to a procedure without this intervention. The forward, backward, stepwise, Newton-Raphson and Fisher variable selection methods are used. The Newton-Raphson and Fisher methods are found not to be effective when used in a logistic modelling process, whereas the forward, backward and stepwise methods are all shown to produce very similar results. Six predictor variables or factors are identified with respect to the sexual activity of the specified students: the age of the student; whether they consume alcohol or not; their racial grouping; whether an HIV test has been taken; the importance of religion in influencing their sexual behaviour; and whether they smoke or not.i i Conclusions are reached with respect to improvements that could be made to the HIV prevention programme at UWC with reference to the sexual activity of entering first-years.

A presente dissertação tem como objetivo propor uma sistemática para a construção de modelos de previsão de risco de crédito e também comparar o desempenho de três técnicas estatísticas multivariadas utilizadas para sua construção: análise discriminante, regressão logística e redes neurais. O método proposto (denominado Modelo PRC) é composto de seis etapas: (i) delimitação da população; (ii) seleção da amostra; (iii) análise preliminar; (iv) construção do modelo; (v) escolha do modelo e (vi) passos para implantação. O Modelo PRC foi aplicado em uma amostra de 17.005 clientes de uma rede de farmácias com crediário próprio. Os resultados encontrados demonstram uma superioridade das redes neurais em relação às outras duas técnicas, o que era esperado devido a sua abordagem nãolinear na combinação das variáveis. Considerando a venda anual aos clientes da base em estudo e utilizando o modelo neural desenvolvido, estima-se um acréscimo de 65% nos lucros. / This work presents a methodology for credit risk prediction, comparing the performance of three statistical techniques used in the prediction process: discriminant analysis, logistic regression and neural networks. The proposed method (entitled PRC Model) embraces six steps: (i) population definition, (ii) sampling, (iii) preliminary analysis, (iv) model development, (v) model selection and (vi) implementation steps. The PRC Model was applied to a sample of 17,005 customers from an organization, which manages his own credit system and controls a pool of drugstores. The results show the superiority of neural networks over the other two techniques. This was expected due to the non-linear approach of the neural network when dealing with the explanatory variables. Considering the neural network model and the annual sales due to customers included on this study, the use of the proposed methodology indicates a 65% potential profits.

Através dos dispositivos e técnicas desenvolvidas na área da Instrumentação Biomédica é possível oferecer um tratamento ou de forma geral soluções que permitam uma vivência mais plena em sociedade para pessoas que possuem algum tipo de deficiência ou doença. Com o aumento da capacidade computacional nos últimos anos foi possível desenvolver muitas técnicas e dispositivos apoiados em processamento digital de sinais e há um grande interesse pelo desenvolvimento de interfaces mais naturais, como sinais biológicos para o controle de próteses e dispositivos. Este trabalho tem por objetivo apresentar o desenvolvimento de um método de Inteligência Computacional baseado em Regressão Logística capaz de classificar 17 movimentos do segmento mão-braço realizados pelos voluntários do estudo através do processamento do sinal mioelétrico (SME) adquiridos dos sujeitos em questão. Adicionalmente é realizada uma avaliação da influência de alguns dos canais, características do sinal e movimentos executados na taxa de acerto global. Para a realização do sistema foi utilizado um aparato experimental capaz de adquirir os SME através de 12 canais utilizando eletrodos não invasivos e posteriormente digitalizá-los. Logo após efetua-se a extração das três características utilizadas no trabalho, que servem de entrada para o método de Regressão Logística. Para este estudo foram processados três bancos de dados que perfazem um total de 50 voluntários. A taxa média de acerto alcançada foi de 70,1%, considerando todas as variações de testes realizados enquanto a média para os melhores casos de cada variação de entrada realizada foi de 92,5%. / Through the devices and techniques developed in the field of Biomedical Instrumentation commonly is possible to offer treatment or solutions to provide a more pleasurable experience in society for people who have a disability or illness. With increasing computing capability in recent years, it has been possible to develop many techniques and devices supported by digital signal processing, and there is a great interest in the development of more natural interfaces, such as biological signals for the control of devices and prostheses. This work aims to present the development of a computational intelligence method based on Logistic Regression able to classify 17 movements of the hand-arm segment performed by the subjects of this study through the processing of the myoelectric signal (SME) acquired from the subject in question. Additionally, an assessment of the influence of some of the combination of the channels, signal characteristics and movements performed in the overall hit rate is additionally performed. To conduct the system has built an experimental apparatus able to acquire the SME through 12 channels using non-invasive electrodes and scan them. Thereafter there is a three features extraction from the signal which serves as input to the Logistic Regression method. For this study were processed three databases that compose 50 volunteers. The average hit rate achieved was 70.1%, considering all tests variations while the average for the best cases for each input variation performed was 92,5 %.

Made available in DSpace on 2016-08-02T21:42:37Z (GMT). No. of bitstreams: 1 MariliaMartins.pdf: 1613138 bytes, checksum: f00e9ebd7187148a5be5b300624e1223 (MD5) Previous issue date: 2014-06-04 / The global market stimulates competitiveness by seeking financial return. However, in order to obtain these financial returns, companies cannot act without considering criteria of corporate sustainability, without which companies will lose competitiveness. The BM&FBOVESPA brought great contribution to companies operating in the market through the ISE (Corporate Sustainability Index). Nevertheless, it is justified to question whether the group of variables that include social responsibility investments is sufficient to better classify a company in the ISE portfolio or whether the weight the ISE sustainability concept is multifocal whose emphasis would balance for all the concepts included in the triple bottom line. In order to verify this assumption, this study sought to establish the actual weight of the social dimension within the ISE through logistic regression drawing on appropriate sampling of participating and non-participating companies in the ISE 2011 and 2012 portfolios. It was demonstrated that there are no significant differences between groups justifying the classification or not in the ISE portfolio, based only on the variables of the social dimension, as well as after adding variables representing the financial. t was noticed, thus, that the social dimension is not relevant enough to differentiate the involvement or not of a company in the ISE classification.   / O mercado global estimula a competitividade para a busca de retornos financeiros. Entretanto, para a obtenção destes retornos financeiros, as empresas não podem atuar sem considerar critérios de sustentabilidade empresarial, condição sem a qual as empresas perderão competitividade. A BM&FBOVESPA trouxe grande contribuição às empresas que operam em seu mercado através do ISE (Índice de Sustentabilidade Empresarial). No entanto é justificado o questionamento se a dimensão que contempla os investimentos relativos à responsabilidade social tem peso suficiente para classificar melhor uma empresa no ISE ou se a concepção de sustentabilidade do ISE é multifocal e cuja ênfase seja distribuída nos conceitos do triple bottom line. Para verificar tal fato, este trabalho procurou comprovar o peso real da dimensão social dentro do ISE por meio de regressão logística, valendo-se de amostragem adequada de empresas participantes ou não na carteira do ISE nos anos 2011 e 2012. Demonstrou-se que não há diferenças significativas entre os grupos que justifiquem a classificação ou não no ISE somente baseando-se nas variáveis da dimensão social, bem como das mesmas com a adição de variáveis financeiras. Nota-se, portanto, que a dimensão social não é suficientemente relevante para diferenciar a participação ou não de uma empresa na carteira do ISE.