Orientadores: Victor Hugo Lachos Dávila, Filidor Edilfonso Vilca Labra / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-16T04:06:26Z (GMT). No. of bitstreams: 1 MedinaGaray_AldoWilliam_M.pdf: 1389516 bytes, checksum: 2763869ea52e11ede3c860714ea0e75e (MD5) Previous issue date: 2010 / Resumo: Neste trabalho estudamos alguns aspectos de estimação e diagnóstico de influência global e local de modelos não lineares sob a classe de distribuição misturas da escala skew-normal, baseado na metodologia proposta por Cook (1986) e Poon & Poon (1999). Os modelos não lineares heteroscedásticos também são discutidos. Esta nova classe de modelos constitui uma generalização robusta dos modelos de regressão não linear simétricos, que têm como membros particulares distribuições com caudas pesadas, tais como skew-t, skew-slash, skew-normal contaminada, entre outras. A estimação dos parâmetros será obtida via o algoritmo EM proposto por Dempster et al. (1977). Estudos de testes de hipóteses são considerados utilizando as estatísticas de escore e da razão de verossimilhança, para testar a homogeneidade do parâmetro de escala. Propriedades das estatísticas do teste são investigadas através de simulações de Monte Carlo. Exemplos numéricos considerando dados reais e simulados são apresentados para ilustrar a metodologia desenvolvida / Abstrac: In this work, we studied some aspects of estimation and diagnostics on the global and local influence in nonlinear models under the class of scale mixtures of the skewnormal (SMSN) distribution, based on the methodology proposed by Cook (1986) e Poon & Poon (1999). Heteroscedastic nonlinear models are also discussed. This new class of models are a robust generalization of non-linear regression symmetrical models, which have as members individual distributions with heavy tails, such as skew-t, skew-slash, and skew-contaminated normal, among others. The parameter estimation will be obtained with the EM algorithm proposed by Dempster et al. (1977). Studies testing hypotheses are considered using the score statistics and the likelihood ratio test to test the homogeneity of scale parameter. Properties of test statistics are investigated through Monte Carlo simulations. Numerical examples considering real and simulated data are presented to illustrate the methodology / Mestrado / Métodos Estatísticos / Mestre em Estatística

Submitted by Thiago Costa Belisario (thiagobelisario@yahoo.com.br) on 2018-10-29T17:39:41Z No. of bitstreams: 1 TA_Thiago_Belisario_final.pdf: 1087607 bytes, checksum: 7b7579a36ab0b10900527b26ba2aacec (MD5) / Rejected by Simone de Andrade Lopes Pires (simone.lopes@fgv.br), reason: Prezado Thiago, Recebemos seu trabalho na biblioteca digital, mas será necessário fazer alguns ajustes, que encaminharei por e-mail. Por favor, faça as alterações e submeta novamente o trabalho na biblioteca digital. Atenciosamente, Simone on 2018-10-30T00:09:37Z (GMT) / Submitted by Thiago Costa Belisario (thiagobelisario@yahoo.com.br) on 2018-10-30T00:29:27Z No. of bitstreams: 1 TA_Thiago_Belisario_final.pdf: 1086621 bytes, checksum: a82d2dec931e745334372b498047389c (MD5) / Approved for entry into archive by Simone de Andrade Lopes Pires (simone.lopes@fgv.br) on 2018-10-30T17:11:12Z (GMT) No. of bitstreams: 1 TA_Thiago_Belisario_final.pdf: 1086621 bytes, checksum: a82d2dec931e745334372b498047389c (MD5) / Approved for entry into archive by Suzane Guimarães (suzane.guimaraes@fgv.br) on 2018-10-30T18:00:20Z (GMT) No. of bitstreams: 1 TA_Thiago_Belisario_final.pdf: 1086621 bytes, checksum: a82d2dec931e745334372b498047389c (MD5) / Made available in DSpace on 2018-10-30T18:00:20Z (GMT). No. of bitstreams: 1 TA_Thiago_Belisario_final.pdf: 1086621 bytes, checksum: a82d2dec931e745334372b498047389c (MD5) Previous issue date: 2018-09-24 / Hoje em dia o consumidor se depara com uma enxurrada de opções de escolha durante o processo decisório de compra. Empresas do mundo inteiro não medem esforços para disponibilizar um sortimento cada vez mais amplo aos seus clientes, acreditando que, quanto maior o número de alternativas apresentadas, maior a chance de sucesso do negócio. Algumas teorias, entretanto, contrapõem essa perspectiva, assumindo que existe um efeito negativo na amplitude de opções a partir de um certo ponto. Sendo assim, o presente estudo procurou investigar qual quantidade de opções de calçados esportivos oferecidos a 294 clientes em uma loja especializada gera maior conversão de vendas, receita média por cliente atendido, e ainda, média de itens por cliente atendido. Além disso, o trabalho também buscou entender a relação entre a quantidade de alternativas apresentadas ao consumidor comprador e seus níveis de maximização e envolvimento com o produto calçado esportivo. Os resultados apontam uma tendência de aumento na efetivação das vendas na medida em que a quantidade de opções apresentadas aumenta, bem como uma redução de conversão quando a oferta chega a determinado ponto, apesar desta não ser tão significativa. A receita média e a quantidade média de itens por cliente atendido demonstram resultado similar, contudo, com uma redução mais expressiva quando do aumento na quantidade de opções apresentadas. Ademais, constatou-se que, aqueles consumidores que compram com mais opções apresentam maiores níveis de maximização e envolvimento com o produto calçado esportivo. / Nowadays the consumer is faced with a flood of choices during the purchasing decision process. Companies around the world are struggling to deliver an ever-increasing assortment to their customers, believing that the greater the number of alternatives presented, the greater the chance of business success. Some theories, however, counterpose this perspective, assuming that there is a negative effect on the range of options from a certain point. Thus, the present study sought to investigate how many sports shoes options offered to 294 customers in a specialized store generated higher sales conversion, average revenue per customer served, and average items per customer served. In addition, the study also sought to understand the relationship between the amount of alternatives presented to the consumer buyer and their levels of maximization and involvement with the product sports shoes. The results indicate a tendency to increase sales as the number of options presented increases, as well as a reduction of the conversion when the offer reaches a certain point, although this is not so significant. The average revenue and the average number of items per customer served show a similar result, however, with a more significant reduction when the number of options presented increases. In addition, it was verified that, those consumers who buy with more options present higher levels of maximization and involvement with the product sports footwear.

Orientadores: Filidor E. Vilca Labra, Victor Hugo Lachos Davila / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica / Made available in DSpace on 2018-08-14T22:06:24Z (GMT). No. of bitstreams: 1 Zeller_CamilaBorelli_D.pdf: 2738820 bytes, checksum: d40d3df77a4b5d44de0f48a8f8afed01 (MD5) Previous issue date: 2009 / Resumo: Neste trabalho, estudamos alguns aspectos de estimação e diagnóstico de influência local (Cook, 1986) em modelos lineares, especificamente no modelo de regressão linear, no modelo linear misto e no modelo de Grubbs sob a classe de distribuições assimétricas misturas de escala skew-normal (SMSN) (Branco & Dey, 2001). Esta família de distribuições tem como membros particulares as versões simétrica e assimétrica das distribuições t-Student, slash e normal contaminada, todas com caudas mais pesadas que a distribuição normal, A estimação dos parâmetros será via o algoritmo EM (Dempster et al, 1977) e a análise de diagnóstico será baseada na técnica de dados aumentados que usa a esperança condicional da função log-verossimilhança dos dados aumentados (função-Q) proveniente do algoritmo EM, como proposta por Zhu & Lee (2001) e Lee & Xu (2004). Assim, pretendemos contribuir positivamente para desenvolvimento da área dos modelos lineares, estendendo alguns resultados encontrados na literatura, por exemplo, Pinheiro et al (2001), Arellano-Valle et aí (2005), Osório (2006), Montenegro et al (2009a), Montenegro et al (2009b), Osório et al (2009), Lachos et aí (2010), entre outros. / Abstract: In this work, we study some aspects of the estimation and the diagnostics based on the local influence (Cook, 1986) in linear models under the class of scale mixtures of the skew-normal (SMSN) distribution, as proposed by Branco & Dey (2001). Specifically, we consider the linear regression model, the linear mixed model and the Grubbs' measurement error model. The SMSN class of distributions provides a useful generalization of the normal and the skew-normal distributions since it covers both the asymmetric and heavy-tailed distributions such as the skew-t, the skew-slash, the skew-contaminated normal, among others. The local influence analysis will be based on the conditional expectation of the complete-data log-likelihood function (function-Q) from the EM algorithm (Dempster et al, 1977) ), as proposed by Zhu & Lee (2001) and Lee & Xu (2004). We believe that the results of our work have contributed positively to the development of this area of linear models, since we have extended some results from the works of Pinheiro et al. (2001), Arellano-Valle et al. (2005), Osorio (2006), Montenegro et al. (2009a), Montenegro et al. (2009b), Osorio et al. (2009), Lachos et al. (2010), among others. / Doutorado / Método Estatístico / Doutor em Estatística

Esta dissertação tem por objetivo principal analisar e responder ao questionamento acerca da relação entre desempenho social corporativo e desempenho financeiro de empresas brasileiras. De forma mais específica, a dissertação investiga a seqüência causal e a direção (positiva ou negativa) do relacionamento entre as variáveis que representam as duas concepções de desempenho. Para tanto, foram utilizadas duas variáveis para representar o desempenho financeiro a valores de mercado, três variáveis para representar o desempenho financeiro a valores contábeis, e o Indicador de Desempenho Social Corporativo, construído nesta dissertação para representar o desempenho social das empresas e baseado nos Balanços Sociais publicados segundo modelo do Instituto Brasileiro de Análises Sociais e Econômicas (IBASE). Além dessas variáveis, duas variáveis de controle consideradas relevantes pela teoria, o Tamanho da Empresa e o Setor de Atuação, também constituíram o modelo estatístico. O período de análise (2000 a 2002) do relacionamento entre as variáveis e a amostra da pesquisa foi relativamente pequeno, devido principalmente à fragilidade do banco de dados referente ao desempenho social corporativo e à incipiência do próprio tema na administração brasileira. As análises foram realizadas em períodos anuais, sem e com defasagem temporal de um ano, a fim de que seis hipóteses alternativas propostas por modelo já existente pudessem ser testadas. A análise estatística foi realizada através de matriz de correlações, de modelos de regressão linear múltipla pelo método dos mínimos quadrados ordinários, de regressão a erros padrão robustos a heterocedasticidade e de regressão robusta. Os resultados, em sua maioria, não foram capazes de rejeitar a hipótese nula do modelo, isto é, de que não há relação estatisticamente significante entre o desempenho social e o desempenho financeiro corporativos. Entretanto, as regressões que utilizaram indicadores contábeis de desempenho financeiro apresentaram resultados que indicariam, em alguns períodos de análise, a existência de uma relação positiva entre as duas formas de desempenho, corroborando, em parte, com a idéia de que a administração dos stakeholders acarretaria desempenho financeiro superior às empresas. Porém, a seqüência causal do relacionamento não foi clara, dado que tanto um melhor ou pior desempenho social corporativo foi causa de um melhor ou pior desempenho financeiro, como também o segundo foi causa do primeiro. Por sua vez, a relação entre os indicadores de mercado do desempenho financeiro das empresas e o indicador de desempenho social corporativo apresentou-se bastante contraditória, o que corrobora com resultados alcançados em pesquisas e trabalhos anteriores sobre o tema. Finalmente, a variável de controle de Tamanho da Empresa mostrou-se não significante para o modelo, enquanto a variável de controle de Setor de Atuação apresentou resultados bastante diversos. Dessa forma, os resultados mostraram-se pouco conclusivos, fato explicado pela literatura existente que identifica as limitações conceituais, como a indefinição de conceitos-chave, e empíricas, como a ausência de banco de dados ou deficiências dos existentes, que permeiam a maioria das pesquisas existentes sobre o tema e que se agravam na realidade brasileira. Para as novas pesquisas, recomenda-se atenção especial à representação do desempenho social corporativo, tornando-o mais abrangente e robusto, bem como a utilização de diferentes janelas temporais para o modelo estatístico que permitam o alcance de resultados mais conclusivos. É importante observar que iniciativas recentes de instituições no país vêm ao encontro do atendimento das necessidades dos pesquisadores que se interessam sobre o tema, o que estimula e favorece o desenvolvimento de pesquisas futuras. / The major objective of this here dissertation consists in analyzing the relation between social and financial performances of Brazilian enterprises and in responding to the related inquiries. More specifically, this text investigates the causal sequence and the direction (positive or negative) taken by the relation between the variables that represent the two performance concepts. For that purpose, two variables have been used to represent the financial performance at market values, three variables have been used to represent the financial performance at book values and the Corporate Social Performance Indicator has been here constructed to represent the social performance of enterprises, based on the Social Balance Sheets published according to the Instituto Brasileiro de Análises Sociais e Econômicas (IBASE). Besides these variables, two control variables have been considered relevant in the theory: the size of the company and its industry. Both have framed the statistic model. The analysis period (from 2000 to 2002) of the relation between the variables and the research sample has been somewhat short, mostly due to the fragility of the corporate social performance database and to the embryonic condition of the issue in Administration in Brazil. The analyses have been accomplished in yearly periods, with and without one-year temporal gaps, so that six alternative hypotheses proposed for already existing model could be tested. The statistic analysis was developed through a correlations matrix, models of multiple linear regression processed by the ordinary least squares method, models of heteroskedasticity-consistent standard error and covariance regression and of robust regression. Most of the results have not been able to reject the null hypothesis of the model, which means that there is no statistically meaningful relation between corporate social and financial performances. However, some of the results provided by the regressions that adopted book value measurement of financial performance denote, at some analysis periods, the existence of a positive relation between the two performances, which somehow reinforces the idea that the administration of stakeholders may provide an improved financial performance. Nevertheless, the causal sequence of the relation has not been clear, considering that either a better or worse corporate social performance has caused a better or worse financial performance; and that the latter may have caused the former. On the other hand, the relation between the variables of corporate financial performance at market values and the corporate social performance indicator has proven quite contradictory, which enhances the results accomplished in previous researches and articles on the subject. Finally, the control variable of enterprise size has proven meaningless for the model, while the control variable of industry has presented quite diverse results. Thus, the results are inconclusive, according to the existing literature, which identifies the conceptual limitations, such as lack of definition of key-concepts; and the empirical limitations, like lack or inadequacy of database, which permeates most of the researches on the subject and deteriorates in the Brazilian reality. For new researches, special attention should be paid to the representation of corporate social performance, making it more extensive and robust; likewise, the usage of different temporal windows for the statistic model, which would allow the accomplishment of more conclusive results. It is important to notice that recent institutional initiatives in the country have met with the needs of researchers interested in the subject, which stimulates and favors the development of future investigations.

Orientador: Filidor Edilfonso Vilca Labra / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-25T19:08:47Z (GMT). No. of bitstreams: 1 HuairaContreras_CarlosAlberto_M.pdf: 2748699 bytes, checksum: fc8d02e2b19e638936faea1dec0b8ddc (MD5) Previous issue date: 2014 / Resumo: Modelos lineares são frequentemente usados em estatística para descrever a relação entre uma variável resposta e uma ou mais variáveis explicativas, onde geralmente os erros são assumidos como normalmente distribuídos. Além disso, em modelos de regressão linear assume-se que o mesmo modelo linear é válido para todo o conjunto de dados. O modelo pode mudar após um ponto específico e assim um modelo linear com um ponto de mudança poderá ser apropriado para o conjunto de dados. O principal objetivo deste trabalho é estudar alguns aspectos de estimação e análise de diagnóstico em modelos de regressão linear com ponto de mudança sob distribuições de mistura de escala normal. A análise de diagnóstico é baseada nos trabalhos de Cook (1986) e Zhu & Lee (2001). Os resultados obtidos representam uma extensão de alguns resultados apresentados na literatura, ver por exemplo Chen (1998) e Osorio & Galea (2005). Finalmente, estudos de simulação através de simulações Monte Carlo são realizados e exemplos numéricos são apresentados para ilustrar os resultados propostos / Abstract: Linear models are widely used in statistics to describe the relationship between a response variable and one or more explanatory variables, where usually it is assumed the errors are normally distributed. Moreover, in linear regression model is assumed that the same linear model holds for the whole data set, but this is not always valid. The model may change after a specific point, and so a linear model with a change point would be appropriate for data set. The main objective of work is to study some aspect of estimation and analysis of diagnostics in the regression linear with change point model under scale mixture of normal distributions. The analysis of diagnostics is based on the works of Cook (1986) and Zhu & Lee (2001). The results obtained represent a extension of some results obtained in the literature; see for example Chen (1998) and Osorio & Galea (2005). Finally, simulation studies are investigated through Monte Carlo simulations and numerical examples are presented to illustrate the proposed results / Mestrado / Estatistica / Mestre em Estatística

This thesis presents two new routing problems, both with objective functions focused on relative positioning of teams during the routing horizon. The relative positioning results in temporal and spatial dependencies among routes and is quantified with a nonlinear dispersion metric, designed to evaluate the instantaneous distances among teams over a time interval. This metric allows the design of objective functions to approximate teams during routes execution, when minimized, or disperse them, when maximized. Both approximation and dispersion are important routing characteristics in some practical applications, and two new optimization problems are proposed with these opposite objectives. The first one is a variation of the Multiple Traveling Salesman Problem, and its goal is to find a set of tours where the salesmen travel close to each other, minimizing dispersion. A Local Search Genetic Algorithm is proposed to solve the problem. It includes specialized genetic operators and neighborhoods. A new set of benchmark instances is proposed, adapted for the new problem from literature instances. Computational results show that the proposed approach provides solutions with the desired characteristics of minimal dispersion. The second problem is a bi-objective arc routing problem in which routes must be constructed in order to maximize collected profit and dispersion of teams. The maximization of the dispersion metric fosters the scattering of the teams during routing procedure. Usually, profit and dispersion objectives are conflicting, and by using a bi-objective approach the decision maker is able to choose a trade-off between collecting profits and scattering teams. Two solution methods are proposed, a Multi-objective Genetic Algorithm and a Multi-objective Genetic Local Search Algorithm, both specialized in order to exploit the characteristics of the problem. It is demonstrated, by means of computational experiments on a new set of benchmark instances, that the proposed approach provides approximation sets with the desired characteristics. / Esta tese apresenta dois novos problemas de roteamento, ambos com funções objetivo voltadas para o posicionamento relativo das equipes durante o horizonte de roteamento. O posicionamento relativo resulta em uma dependência temporal e espacial entre rotas e é quantificado com uma métrica de dispersão não-linear, projetada para avaliar as distâncias instantâneas entre as equipes ao longo de um intervalo de tempo. Esta métrica permite a concepção de funções objetivo para aproximar as equipes durante a execução das rotas, quando minimizada, ou para dispersá-las, quando maximizada. Tanto a aproximação quanto a dispersão são características importantes de roteamento em algumas aplicações práticas, e dois novos problemas de otimização são propostos com esses objetivos opostos. O primeiro é uma variação do Problema de Múltiplos Caixeiros Viajantes, e seu objetivo é encontrar um conjunto de rotas em que os caixeiros viajam próximos uns dos outros, minimizando a dispersão. Um Algoritmo Genético com Busca Local é proposto para resolver o problema. Ele inclui operadores genéticos e vizinhanças especializados. Um novo conjunto de instâncias é proposto, adaptado para o novo problema de instâncias da literatura. Resultados computacionais mostram que a abordagem proposta proporciona soluções com as características desejadas de dispersão mínima. O segundo problema é um problema de roteamento de arcos biobjetivo em que as rotas devem ser construídas de modo a maximizar o lucro recolhido e o distanciamento entre as equipes. A maximização da métrica promove a dispersão das equipes durante a execução das rotas. Normalmente, os objetivos de lucro e dispersão são conflitantes, e com uma abordagem biobjetivo o tomador de decisão é capaz de avaliar a troca entre a coleta de lucros e a dispersão de equipes. Dois métodos de solução são propostos, um Algoritmo Genético Multiobjetivo e um Algoritmo Genético Multiobjetivo com Busca Local, ambos especializados para explorar as características do problema. É demonstrado, por meio de experimentos computacionais sobre um novo conjunto de instâncias, que a abordagem proposta fornece conjuntos de aproximação com as características desejadas.

Abstract This thesis concentrates on the design and evaluation of spatial user multiplexing methods via linear transmit-receive processing for wireless cellular multi-user multiple-input multiple-output (MIMO) communication systems operating in the time-division duplexing (TDD) mode. The main focus is on the acquisition of effective channel state information (CSI) that facilitates decentralized processing so that the network nodes – base stations (BS) and user terminals (UT), each employing an arbitrary number of antenna elements – are able to locally participate in the network adaptation. The proposed methods rely on the uplink-downlink channel reciprocity and spatially precoded over-the-air pilot signaling. Considering (single-cell) multi-user MIMO systems, coordinated zero-forcing transmit-receive processing schemes for the uplink (UL) are proposed. The BS computes the transmission parameters in a centralized manner and employs downlink (DL) pilot signals to convey the information of the beamformers to be used by the UTs. When coexisting with the DL zero-forcing, the precoded DL demodulation pilots can be reused for UL beam allocation, and the precoded UL demodulation pilots are reused in turn for partial channel sounding (CS). As a result, only the precoded pilot symbols are needed in both UL and DL. Moreover, a concept for reducing the number of the required orthogonal UL CS pilot resources is presented. Based on their DL channel knowledge, the multi-antenna UTs form fewer pilot beams by spatial precoding than conventionally needed when transmitting antenna-specific pilots. In the context of DL zero-forcing, when taking into account the CSI estimation error at the BS, the overhead reduction turns out to improve robustness and increase the average system capacity. Considering multi-cell multi-user MIMO systems, decentralized coordinated DL beamforming strategies based on weighted sum rate (WSR) maximization are proposed. An optimization framework where the WSR maximization is carried out via weighted sum mean-squared-error minimization is utilized, and the approach is generalized by employing antenna-specific transmit power constraints. The iterative processing consists of optimization steps that are run locally by the BSs. In one novel strategy, the coordinating cells update their transmit precoders and receivers one cell at a time, which guarantees monotonic convergence of the network-wide problem. The strategy employs separate uplink CS and busy burst pilot signaling to reveal the effective channels of the UTs to the neighboring BSs. In another novel strategy, the monotonic convergence is sacrificed to devise a faster scheme where the BSs are allowed to optimize their variables in parallel based on just the CS responses and additional low-rate backhaul information exchange. The numerical results demonstrate that WSR maximization has the desirable property that spatial user scheduling is carried out implicitly. Finally, methods for UL CS overhead reduction are presented, and the effect of CSI uncertainty is addressed. / Tiivistelmä Tämä väitöskirja keskittyy lineaarisella lähetys- ja vastaanottoprosessoinnilla toteutettavien tilajakomonikäyttömenetelmien suunnitteluun ja arviointiin langattomissa moniantennisissa solukkoverkoissa, jotka hyödyntävät aikajakodupleksointia (TDD). Erityisesti tarkastellaan efektiivisen kanavatiedon hankintaa, joka mahdollistaa hajautetun prosessoinnin siten että verkkoelementit – tukiasemat ja terminaalit, jotka kukin hyödyntävät useaa antennielementtiä – voivat osallistua paikallisesti verkon adaptaatioon. Esitetyt menetelmät perustuvat ylä- ja alalinkin kanavien resiprookkisuuteen ja tilatasossa esikoodattuun opetus- eli pilottisignalointiin ilmarajapinnan yli. Yksisoluisille monikäyttäjä- ja moniantennijärjestelmille esitetään ylälinkin koordinoituja nollaanpakottavia lähetys- ja vastaanottomenetelmiä. Tukiasema laskee lähetysparametrit keskitetysti ja käyttää pilottisignaaleja kertomaan millaista lähetyskeilanmuodostusta terminaalien tulee käyttää. Alalinkin nollaanpakotuksen yhteydessä esikoodattuja demodulaatiopilotteja voidaan uudelleenkäyttää ylälinkin lähetyskeilojen allokointiin, ja esikoodattuja ylälinkin demodulaatiopilotteja uudelleenkäytetään puolestaan osittaiseen kanavan luotaukseen (sounding). Näin ollen molempiin suuntiin tarvitaan vain esikoodatut pilotit. Lisäksi työssä esitetään menetelmä ylälinkin luotauspilottiresurssitarpeen vähentämiseksi. Kanavatietoon perustuen moniantenniset terminaalit muodostavat tilatasossa esikoodattuja pilottilähetyskeiloja, joita tarvitaan vähemmän kuin perinteisiä antennikohtaisia pilotteja. Kun otetaan huomioon kanavanestimointivirhe tukiasemassa, resurssiensäästömenetelmä parantaa häiriösietoisuutta ja nostaa järjestelmän keskimääräistä kapasiteettia alalinkin nollaanpakotuksen yhteydessä. Monisoluisille monikäyttäjä- ja moniantennijärjestelmille esitetään hajautettuja koordinoituja alalinkin keilanmuodostusstrategioita, jotka perustuvat painotetun summadatanopeuden (WSR) maksimointiin. Valitussa optimointikehyksessä WSR:n maksimointi toteutetaan painotetun summaneliövirheen minimoinnin kautta, ja työssä menettelytapa yleistetään antennikohtaisten lähetystehorajoitusten tapaukseen. Iteratiivinen prosessointi koostuu optimointiaskelista, jotka tukiasemat paikallisesti suorittavat. Yhdessä esitetyssä strategiassa yhteistoiminnalliset solut päivittävät lähettimensä ja vastaanottimensa yksi solu kerrallaan, mikä takaa verkonlaajuisen ongelmanratkaisun monotonisen konvergenssin. Tämä strategia käyttää erillisiä ylälinkin luotaussignaaleja sekä varattu-signaaleja ilmaistakseen terminaalien efektiiviset kanavat naapuritukiasemille. Toisessa strategiassa monotoninen konvergenssi uhrataan ja kehitetään nopeammin adaptoituva menetelmä, jossa tukiasemat saavat optimoida muuttujansa rinnakkain, perustuen vain luotaussignaaleihin ja tukiasemien väliseen informaationvaihtoon. Numeeriset tulokset osoittavat, että WSR:n maksimointi toteuttaa aktiivisten käyttäjien valinnan tilatasossa implisiittisesti. Lopuksi esitetään menetelmiä luotauspilottiresurssitarpeen vähentämiseksi ja käsitellään kanavatiedon epävarmuuden vaikutusta.

No description available.

Speech is by far the most natural form of communication between human beings. It is intuitive, expressive and contains information at several cognitive levels. We as humans, are perceptive to several of these cognitive levels of information, as we can gather the information pertaining to the identity of the speaker, the speaker's gender, emotion, location, the language, and so on, in addition to the content of what is being spoken. This makes speech based human machine interaction (HMI), both desirable and challenging for the same set of reasons. For HMI to be natural for humans, it is imperative that a machine understands information present in speech, at least at the level of speaker identity, language, location in space, and the summary of what is being spoken. Although one can draw parallels between the human-human interaction and HMI, the two differ in their purpose. We, as humans, interact with a machine, mostly in the context of getting a task done more efficiently, than is possible without the machine. Thus, typically in HMI, controlling the machine in a specific manner is the primary goal. In this context, it can be argued that, HMI, with a limited vocabulary containing specific commands, would suffice for a more efficient use of the machine. In this thesis, we address the problem of ``Who spoke what and where", in the context of a machine understanding the information pertaining to identities of the speakers, their locations in space and the keywords they spoke, thus considering three levels of information - speaker identity (who), location (where) and keywords (what). This can be addressed with the help of multiple sensors like microphones, video camera, proximity sensors, motion detectors, etc., and combining all these modalities. However, we explore the use of only microphones to address this issue. In practical scenarios, often there are times, wherein, multiple people are talking at the same time. Thus, the goal of this thesis is to detect all the speakers, their keywords, and their locations in mixture signals containing speech from simultaneous speakers. Addressing this problem of ``Who spoke what and where" using only microphone signals, forms a part of acoustic scene analysis (ASA) of speech based acoustic events. We divide the problem of ``who spoke what and where" into two sub-problems: ``Who spoke what?" and ``Who spoke where". Each of these problems is cast in a generic latent variable (LV) framework to capture information in speech at different levels. We associate a LV to represent each of these levels and model the relationship between the levels using conditional dependency. The sub-problem of ``who spoke what" is addressed using single channel microphone signal, by modeling the mixture signal in terms of LV mass functions of speaker identity, the conditional mass function of the keyword spoken given the speaker identity, and a speaker-specific-keyword model. The LV mass functions are estimated in a Maximum likelihood (ML) framework using the Expectation Maximization (EM) algorithm using Student's-t Mixture Model (tMM) as speaker-specific-keyword models. Motivated by HMI in a home environment, we have created our own database. In mixture signals, containing two speakers uttering the keywords simultaneously, the proposed framework achieves an accuracy of 82 % for detecting both the speakers and their respective keywords. The other sub-problem of ``who spoke where?" is addressed in two stages. In the first stage, the enclosure is discretized into sectors. The speakers and the sectors in which they are located are detected in an approach similar to the one employed for ``who spoke what" using signals collected from a Uniform Circular Array (UCA). However, in place of speaker-specific-keyword models, we use tMM based speaker models trained on clean speech, along with a simple Delay and Sum Beamformer (DSB). In the second stage, the speakers are localized within the active sectors using a novel region constrained localization technique based on time difference of arrival (TDOA). Since the problem being addressed is a multi-label classification task, we use the average Hamming score (accuracy) as the performance metric. Although the proposed approach yields an accuracy of 100 % in an anechoic setting for detecting both the speakers and their corresponding sectors in two-speaker mixture signals, the performance degrades to an accuracy of 67 % in a reverberant setting, with a $60$ dB reverberation time (RT60) of 300 ms. To improve the performance under reverberation, prior knowledge of the location of multiple sources is derived using a novel technique derived from geometrical insights into TDOA estimation. With this prior knowledge, the accuracy of the proposed approach improves to 91 %. It is worthwhile to note that, the accuracies are computed for mixture signals containing more than 90 % overlap of competing speakers. The proposed LV framework offers a convenient methodology to represent information at broad levels. In this thesis, we have shown its use with three different levels. This can be extended to several such levels to be applicable for a generic analysis of the acoustic scene consisting of broad levels of events. It will turn out that not all levels are dependent on each other and hence the LV dependencies can be minimized by independence assumption, which will lead to solving several smaller sub-problems, as we have shown above. The LV framework is also attractive to incorporate prior knowledge about the acoustic setting, which is combined with the evidence from the data to derive the information about the presence of an acoustic event. The performance of the framework, is dependent on the choice of stochastic models, which model the likelihood function of the data given the presence of acoustic events. However, it provides an access to compare and contrast the use of different stochastic models for representing the likelihood function.

The migratory birds stop at different stopover sites during migration. The presence of resources in these stopover sites is essential to regain the energy of these birds. This thesis aims to compare the resource abundance and intake at the two stopover sites: Reda and Wisla river estuaries. How a bird's mass changes during its stay at an estuary is considered as a proxy for the resource abundance of a site. The comparison is made on different subsets, including those which has incomplete data, i.e. next day is not exactly one day after the previous capture. Multiple linear regression, Generalized additive model and Linear mixed effect model are used for analysis. Expectation maximization and an iterative predictive process are implemented to deal with incomplete data. We found that Reda has higher resource abundance and intake as compared to that of Wisla river estuary.