No description available.

No description available.

The discipline usually called `probability theory' can be seen as the theory which describes and sets standard norms to the way we reason about plausibility. From this point of view, this `plausibility theory' is a province of logic, and the following informal proportion subsists: plausibility theory is to the common notion of `plausibility', as deductive logic is to the common notion of `truth'. Some studies in plausibility theory are here offered. An alternative view and mathematical formalism for the problem of induction (the prediction of uncertain events from similar, certain ones) is presented. It is also shown how from plausibility theory one can derive a mathematical framework, based on convex geometry, for the description of the predictive properties of physical theories. Within this framework, problems like state assignment - for any physical theory - find simple and clear algorithms, numerical examples of which are given for three-level quantum systems. Plausibility theory also gives insights on various fashionable theorems, like Bell’s theorem, and various fashionable `paradoxes', like Gibbs' paradox. / QC 20100816

<p>Users of heavy trucks, as well as legislation, put increasing demands on heavy trucks. The vehicles should be more comfortable, reliable and safe. Furthermore, they should consume less fuel and be more environmentally friendly. For example, this means that faults that cause the emissions to increase must be detected early. To meet these requirements on comfort and performance, advanced sensor-based computer control-systems are used. However, the increased complexity makes the vehicles more difficult for the workshop mechanic to maintain and repair. A diagnosis system that detects and localizes faults is thus needed, both as an aid in the repair process and for detecting and isolating (localizing) faults on-board, to guarantee that safety and environmental goals are satisfied.</p><p>Reliable fault isolation is often a challenging task. Noise, disturbances and model errors can cause problems. Also, two different faults may lead to the same observed behavior of the system under diagnosis. This means that there are several faults, which could possibly explain the observed behavior of the vehicle.</p><p>In this thesis, a Bayesian approach to fault isolation is proposed. The idea is to compute the probabilities, given ``all information at hand'', that certain faults are present in the system under diagnosis. By ``all information at hand'' we mean qualitative and quantitative information about how probable different faults are, and possibly also data which is collected during test drives with the vehicle when faults are present. The information may also include knowledge about which observed behavior that is to be expected when certain faults are present.</p><p>The advantage of the Bayesian approach is the possibility to combine information of different characteristics, and also to facilitate isolation of previously unknown faults as well as faults from which only vague information is available. Furthermore, Bayesian probability theory combined with decision theory provide methods for determining the best action to perform to reduce the effects from faults.</p><p>Using the Bayesian approach to fault isolation to diagnose large and complex systems may lead to computational and complexity problems. In this thesis, these problems are solved in three different ways. First, equivalence classes are introduced for different faults with equal probability distributions. Second, by using the structure of the computations, efficient storage methods can be used. Finally, if the previous two simplifications are not sufficient, it is shown how the problem can be approximated by partitioning it into a set of sub problems, which each can be efficiently solved using the presented methods.</p><p>The Bayesian approach to fault isolation is applied to the diagnosis of the gas flow of an automotive diesel engine. Data collected from real driving situations with implemented faults, is used in the evaluation of the methods. Furthermore, the influences of important design parameters are investigated.</p><p>The experiments show that the proposed Bayesian approach has promising potentials for vehicle diagnosis, and performs well on this real problem. Compared with more classical methods, e.g. structured residuals, the Bayesian approach used here gives higher probability of detection and isolation of the true underlying fault.</p> / <p>Både användare och lagstiftare ställer idag ökande krav på prestanda hos tunga lastbilar. Fordonen ska var bekväma, tillförlitliga och säkra. Dessutom ska de ha bättre bränsleekonomi vara mer miljövänliga. Detta betyder till exempel att fel som orsakar förhöjda emissioner måste upptäckas i ett tidigt stadium.</p><p>För att möta dessa krav på komfort och prestanda används avancerade sensorbaserade reglersystem.</p><p>Emellertid leder den ökade komplexiteten till att fordonen blir mer komplicerade för en mekaniker att underhålla, felsöka och reparera.</p><p>Därför krävs det ett diagnossystem som detekterar och lokaliserar felen, både som ett hjälpmedel i reparationsprocessen, och för att kunna detektera och lokalisera (isolera) felen ombord för att garantera att säkerhetskrav och miljömål är uppfyllda.</p><p>Tillförlitlig felisolering är ofta en utmanande uppgift. Brus, störningar och modellfel kan orsaka problem. Det kan också det faktum två olika fel kan leda till samma observerade beteende hos systemet som diagnosticeras. Detta betyder att det finns flera fel som möjligen skulle kunna förklara det observerade beteendet hos fordonet.</p><p>I den här avhandlingen föreslås användandet av en Bayesianska ansats till felisolering. I metoden beräknas sannolikheten för att ett visst fel är närvarande i det diagnosticerade systemet, givet ''all tillgänglig information''. Med ''all tillgänglig information'' menas både kvalitativ och kvantitativ information om hur troliga fel är och möjligen även data som samlats in under testkörningar med fordonet, då olika fel finns närvarande. Informationen kan även innehålla kunskap om vilket beteende som kan förväntas observeras då ett särskilt fel finns närvarande.</p><p>Fördelarna med den Bayesianska metoden är möjligheten att kombinera information av olika karaktär, men också att att den möjliggör isolering av tidigare okända fel och fel från vilka det endast finns vag information tillgänglig. Vidare kan Bayesiansk sannolikhetslära kombineras med beslutsteori för att erhålla metoder för att bestämma nästa bästa åtgärd för att minska effekten från fel.</p><p>Användandet av den Bayesianska metoden kan leda till beräknings- och komplexitetsproblem. I den här avhandlingen hanteras dessa problem på tre olika sätt. För det första så introduceras ekvivalensklasser för fel med likadana sannolikhetsfördelningar. För det andra, genom att använda strukturen på beräkningarna kan effektiva lagringsmetoder användas. Slutligen, om de två tidigare förenklingarna inte är tillräckliga, visas det hur problemet kan approximeras med ett antal delproblem, som vart och ett kan lösas effektivt med de presenterade metoderna.</p><p>Den Bayesianska ansatsen till felisolering har applicerats på diagnosen av gasflödet på en dieselmotor. Data som har samlats från riktiga körsituationer med fel implementerade används i evalueringen av metoderna. Vidare har påverkan av viktiga parametrar på isoleringsprestandan undersökts.</p><p>Experimenten visar att den föreslagna Bayesianska ansatsen har god potential för fordonsdiagnos, och prestandan är bra på detta reella problem. Jämfört med mer klassiska metoder baserade på strukturerade residualer ger den Bayesianska metoden högre sannolikhet för detektion och isolering av det sanna, underliggande, felet.</p>

Users of heavy trucks, as well as legislation, put increasing demands on heavy trucks. The vehicles should be more comfortable, reliable and safe. Furthermore, they should consume less fuel and be more environmentally friendly. For example, this means that faults that cause the emissions to increase must be detected early. To meet these requirements on comfort and performance, advanced sensor-based computer control-systems are used. However, the increased complexity makes the vehicles more difficult for the workshop mechanic to maintain and repair. A diagnosis system that detects and localizes faults is thus needed, both as an aid in the repair process and for detecting and isolating (localizing) faults on-board, to guarantee that safety and environmental goals are satisfied. Reliable fault isolation is often a challenging task. Noise, disturbances and model errors can cause problems. Also, two different faults may lead to the same observed behavior of the system under diagnosis. This means that there are several faults, which could possibly explain the observed behavior of the vehicle. In this thesis, a Bayesian approach to fault isolation is proposed. The idea is to compute the probabilities, given ``all information at hand'', that certain faults are present in the system under diagnosis. By ``all information at hand'' we mean qualitative and quantitative information about how probable different faults are, and possibly also data which is collected during test drives with the vehicle when faults are present. The information may also include knowledge about which observed behavior that is to be expected when certain faults are present. The advantage of the Bayesian approach is the possibility to combine information of different characteristics, and also to facilitate isolation of previously unknown faults as well as faults from which only vague information is available. Furthermore, Bayesian probability theory combined with decision theory provide methods for determining the best action to perform to reduce the effects from faults. Using the Bayesian approach to fault isolation to diagnose large and complex systems may lead to computational and complexity problems. In this thesis, these problems are solved in three different ways. First, equivalence classes are introduced for different faults with equal probability distributions. Second, by using the structure of the computations, efficient storage methods can be used. Finally, if the previous two simplifications are not sufficient, it is shown how the problem can be approximated by partitioning it into a set of sub problems, which each can be efficiently solved using the presented methods. The Bayesian approach to fault isolation is applied to the diagnosis of the gas flow of an automotive diesel engine. Data collected from real driving situations with implemented faults, is used in the evaluation of the methods. Furthermore, the influences of important design parameters are investigated. The experiments show that the proposed Bayesian approach has promising potentials for vehicle diagnosis, and performs well on this real problem. Compared with more classical methods, e.g. structured residuals, the Bayesian approach used here gives higher probability of detection and isolation of the true underlying fault. / Både användare och lagstiftare ställer idag ökande krav på prestanda hos tunga lastbilar. Fordonen ska var bekväma, tillförlitliga och säkra. Dessutom ska de ha bättre bränsleekonomi vara mer miljövänliga. Detta betyder till exempel att fel som orsakar förhöjda emissioner måste upptäckas i ett tidigt stadium. För att möta dessa krav på komfort och prestanda används avancerade sensorbaserade reglersystem. Emellertid leder den ökade komplexiteten till att fordonen blir mer komplicerade för en mekaniker att underhålla, felsöka och reparera. Därför krävs det ett diagnossystem som detekterar och lokaliserar felen, både som ett hjälpmedel i reparationsprocessen, och för att kunna detektera och lokalisera (isolera) felen ombord för att garantera att säkerhetskrav och miljömål är uppfyllda. Tillförlitlig felisolering är ofta en utmanande uppgift. Brus, störningar och modellfel kan orsaka problem. Det kan också det faktum två olika fel kan leda till samma observerade beteende hos systemet som diagnosticeras. Detta betyder att det finns flera fel som möjligen skulle kunna förklara det observerade beteendet hos fordonet. I den här avhandlingen föreslås användandet av en Bayesianska ansats till felisolering. I metoden beräknas sannolikheten för att ett visst fel är närvarande i det diagnosticerade systemet, givet ''all tillgänglig information''. Med ''all tillgänglig information'' menas både kvalitativ och kvantitativ information om hur troliga fel är och möjligen även data som samlats in under testkörningar med fordonet, då olika fel finns närvarande. Informationen kan även innehålla kunskap om vilket beteende som kan förväntas observeras då ett särskilt fel finns närvarande. Fördelarna med den Bayesianska metoden är möjligheten att kombinera information av olika karaktär, men också att att den möjliggör isolering av tidigare okända fel och fel från vilka det endast finns vag information tillgänglig. Vidare kan Bayesiansk sannolikhetslära kombineras med beslutsteori för att erhålla metoder för att bestämma nästa bästa åtgärd för att minska effekten från fel. Användandet av den Bayesianska metoden kan leda till beräknings- och komplexitetsproblem. I den här avhandlingen hanteras dessa problem på tre olika sätt. För det första så introduceras ekvivalensklasser för fel med likadana sannolikhetsfördelningar. För det andra, genom att använda strukturen på beräkningarna kan effektiva lagringsmetoder användas. Slutligen, om de två tidigare förenklingarna inte är tillräckliga, visas det hur problemet kan approximeras med ett antal delproblem, som vart och ett kan lösas effektivt med de presenterade metoderna. Den Bayesianska ansatsen till felisolering har applicerats på diagnosen av gasflödet på en dieselmotor. Data som har samlats från riktiga körsituationer med fel implementerade används i evalueringen av metoderna. Vidare har påverkan av viktiga parametrar på isoleringsprestandan undersökts. Experimenten visar att den föreslagna Bayesianska ansatsen har god potential för fordonsdiagnos, och prestandan är bra på detta reella problem. Jämfört med mer klassiska metoder baserade på strukturerade residualer ger den Bayesianska metoden högre sannolikhet för detektion och isolering av det sanna, underliggande, felet. / QC 20101115

In this dissertation, a normative prescriptive paradigm, namely a Bayesian theory of content-dependent argument strength, was employed in order to investigate argumentation, specifically the classic fallacy of the &ldquo / argument from ignorance&rdquo / or &ldquo / argumentum ad ignorantiam&rdquo / . The study was carried out in Turkish with Turkish participants. In the Bayesian framework, argument strength is determined by the interactions between three major factors: prior belief, polarity, and evidence reliability. In addition, topic effects are considered. Three experiments were conducted. The first experiment replicated Hahn et al.&rsquo / s (2005) study in Turkish to investigate whether similar results would be obtained in a different linguistic and cultural community. We found significant main effects of three of the manipulated factors in Oaksford and Hahn (2004) and Hahn et al. (2005): prior belief, reliability and topic. With respect to the Bayesian analysis, the overall fit between the data and the model was very good. The second experiment tested the hypothesis that argument acceptance would not vary across different intelligence levels. There was no significant main effect of prior belief, polarity, topic, and intelligence. We found a main effect of reliability only. However, further analyses on significant interactions showed that more intelligent subjects were less inclined to accept negative polarity items. Finally, the third experiment investigated the hypothesis that argument acceptance would vary depending on the presence of and the kind of evidentiality markers prevalent in Turkish, indicating the certainty with which events in the past have happened, marked with overt morpho-syntactic markers (&ndash / DI or &ndash / mIs). The experiment found a significant main effect of evidentiality as well as replicating the significant main effects of the two of the manipulated factors (prior belief and reliability) in Oaksford and Hahn (2004), Hahn et al. (2005) and in our first experiment. Furthermore, reliability and evidentiality interacted, indicating separate as well as combined effects of the two. With respect to the Bayesian analysis, the overall fit between the data and the model was lower than the one in the first experiment, but still acceptable. Overall, this study supported the normative Bayesian approach to studying argumentation in an interdisciplinary perspective, combining computation, psychology, linguistics, and philosophy.

A presente tese refere-se a uma proposta de abordagem geoarqueológica voltada ao estudo de sítios arqueológicos costeiros, enfocando pressupostos teóricos e metodológicos ligados à uma aproximação entre a Arqueologia, Geociências e Ciências da Informação. Objetivou em um primeiro momento, inserir questões e problemáticas relativas a necessidade de inclusão da incerteza no raciocínio e práticas arqueológicas, vislumbrando as possibilidades de seu tratamento. Neste sentido, a percepção do \"problema da não informação\" constituiu o argumento conceitual para a elaboração de um modelo de raciocínio dialético sobre a aquisição, geração, seleção e transmissão de informações na disciplina. Nessa perspectiva, sobreveio a necessidade da interação constante entre Teorias de Formação e de Recuperação, como passo essencial ao controle das perdas e ganhos informacionais e, ao tratamento das imperfeições, incompletudes, imprecisões e ambiguidades ligadas aos fenômenos arqueológicos e seu registro científico. Um dos aspectos explorados refere-se à percepção das incertezas e vieses envolvidos na interpretação das ocupações costeiras, notadamente quanto às problemáticas de origem e migração das primeiras populações nessas áreas. Em um modelo atual dicotômico entre o interior e o litoral, onde mesmo os sítios mais antigos (somente sambaquis) acham-se dispostos sobre a superfície dos terrenos, a percepção da dinâmica e complexidade dos sistemas costeiros, fica restrita ao enquadramento desses sítios em sucessões de cenários geomórficos e paeogeográficos. Deste modo, pouca atenção é dada às conseqüências de agentes dinâmicos sobre a configuração e seleção de sítios na atual paisagem costeira, bem como, à possibilidade de ocorrência e detecção de diferentes classes de sítios, que foram preservados em profundidade por meio de processos de capeamento sedimentar. Assim, em um segundo momento, foi proposto à utilização do conceito de \"Controles Geoarquelógicos\" (CG) no estudo e explicitação dos condicionantes naturais e analíticos envolvidos em uma pesquisa de caráter regional, cujo enfoque está nas relações informacionais estabelecidas entre sítios arqueológicos e meio (natural e analítico), e cujo resultado (síntese dialética) compreenderia a noção de evento arqueológico. Diante da explicitação da variabilidade envolvida na caracterização do Registro Arqueológico Regional (RAR), bem como, dos condicionantes complexos derivados da estrutura, dinâmica e evolução da paisagem, o evento arqueológico considerado na tese, compreendeu a investigação da probabilidade de preservação de sítios costeiros antigos (teoria de formação) e do seu potencial de detecção (teoria de recuperação). Neste sentido foi utilizado o raciocínio abdutivo para gerar hipóteses sobre a preservação ou não de sítios encobertos, tendo por base os modelos sedimentares e morfoestratigraficos produzidos para a costa sul-sudeste. Por sua vez, a busca de indicadores nas planícies costeiras de Guaratuba-PR e de Caraguatatuba SP, possibilitou apontar condicionantes (variáveis) favoráveis a geração de um modelo de trapeamento de sítios (capeamento e preservação sedimentar) para a região da Baía de Guaratuba. Por fim, foi testado o raciocínio probabilístico Bayesiano e a Teoria de Evidências (Dempster-Shafer) para a inclusão e representação da incerteza na pesquisa de sambaquis, visualizando um método de tratamento das evidências e inferências geradas em sistemas baseados em conhecimento. Esses mesmos métodos também permitiram determinar os pesos para os diferentes indicadores, e as condições de necessidade, suficiência e ambigüidade das variáveis na geração de mapas aplicados à predição da favorabilidade e suscetibilidade de sítios arqueológicos enterrados na planície costeira de Guaratuba. / This thesis refers to a proposal for a geoarchaeological approach focused on the study of coastal archaeological sites, concentrating on theoretical and methodological assumptions related to a closeness between the archeology, the Information Sciences and Geosciences. It aimed in a first moment, to insert issues and problems concerning the need for inclusion of uncertainty in archaeological reasoning and practice, foreseeing the possibilities of their treatment. In this sense, the perception of the \"no information problem\" was the argument for the conceptual development of a model of dialectical thinking about the acquisition, generation, selection and transmission of information in the discipline. Accordingly, the need for constant interaction between Formation and Recovery Theories became an essential step to the control of informational losses and gains, and the treatment of imperfections, incompleteness, inaccuracies and ambiguities relating to archaeological phenomena and their scientific record. One of the aspects exploited, is the perception of slants and uncertainties involved in the interpretation of coastal activities, notably on issues of origin and migration of the first people in those areas. In a current dichotomic model between the interior and the coast, where even the oldest sites (only sambaquis) are found placed on the surface of the land, the perception of the complexity and dynamics of the coastal systems, is restricted to the framework of these sites in a succession of geomorphic and paleogeographics \"scenarios\". Thus, little attention is given to the dynamic agents consequences on the configuration and selection of sites in the coastal landscape, and the possibility of occurrence and detection of different classes of sites, which were preserved indepth by a sedimental capstone process. Therefore, in a second moment, it was proposed to use the concept of \"geoarchaeological control \" (GC) in the study and explanation of natural and analytical conditions involved in a research of regional manner, whose focus is on the informational relations established between archaeological sites and the environment (natural and analytical), whose result (dialectical synthesis) understand the concept of the archaeological event. Given the explicit characterization of the variability involved in the Regional Archaeological Record (RAR), as well as the complex condition agent derived from the structure, dynamics and evolution of the landscape, the archaeological event considered in the thesis, understand the research of the probability of preservation of ancient coastal sites (formation theory) and its potential for detection (recovery theory). In this sense abdutive reasoning was used to generate hypotheses about the preservation or not of covered sites, based on the sedimentary and morphostratigraphic models produced for the south-southeast coast. In turn, the search for indicators in the coastal plains of Guaratuba- PR and Caraguatatuba-SP, it made possible to point constraints (variables) favorable to the generation of a trap model for sites (sedimental capstone and preservation) for the region of Guaratuba Bay. Finally it was tested the probabilistic bayesian reasoning and Evidence Theory (Dempster-Shafer) for the inclusion and representation of uncertainty in the research of sambaquis foreseeing a method of treatment of the evidence and inferences generated by knowledge-based systems. These methods also allowed to determine the weights for different indicators, and the conditions of necessity, sufficiency and ambiguity of the variables in the generation of maps applied to the prediction of favorability and susceptibility of buried archaeological sites in the coastal plain of Guaratuba.

<p>This thesis is concerned with scheduling the use of resources, or allocating resources, so as to meet future demands for the entities produced by the resources. We consider applications in mobile communications such as scheduling users' transmissions so that the amount of transmitted information is maximized, and scenarios in the manufacturing industry where the task is to distribute work among production units so as to minimize the number of missed orders.</p><p>The allocation decisions are complicated by a lack of information concerning the future demand and possibly also about the capacities of the available resources. We therefore resort to using probability theory and the maximum entropy principle as a means for making rational decisions under uncertainty.</p><p>By using probabilities interpreted as a reasonable degree of belief, we find optimum decision rules for the manufacturing problem, bidding under uncertainty in a certain type of auctions, scheduling users in communications with uncertain channel qualities and uncertain arrival rates, quantization of channel information, partitioning bandwidth between interfering and non-interfering areas in cellular networks, hand-overs and admission control. Moreover, a new method for making optimum approximate Bayesian inference is introduced.</p><p>We further discuss reasonable optimization criteria for the mentioned applications, and provide an introduction to the topic of probability theory as an extension to two-valued logic. It is argued that this view unifies a wide range of resource-allocation problems, and we discuss various directions for further research.</p>

This thesis is concerned with scheduling the use of resources, or allocating resources, so as to meet future demands for the entities produced by the resources. We consider applications in mobile communications such as scheduling users' transmissions so that the amount of transmitted information is maximized, and scenarios in the manufacturing industry where the task is to distribute work among production units so as to minimize the number of missed orders. The allocation decisions are complicated by a lack of information concerning the future demand and possibly also about the capacities of the available resources. We therefore resort to using probability theory and the maximum entropy principle as a means for making rational decisions under uncertainty. By using probabilities interpreted as a reasonable degree of belief, we find optimum decision rules for the manufacturing problem, bidding under uncertainty in a certain type of auctions, scheduling users in communications with uncertain channel qualities and uncertain arrival rates, quantization of channel information, partitioning bandwidth between interfering and non-interfering areas in cellular networks, hand-overs and admission control. Moreover, a new method for making optimum approximate Bayesian inference is introduced. We further discuss reasonable optimization criteria for the mentioned applications, and provide an introduction to the topic of probability theory as an extension to two-valued logic. It is argued that this view unifies a wide range of resource-allocation problems, and we discuss various directions for further research.

A presente tese refere-se a uma proposta de abordagem geoarqueológica voltada ao estudo de sítios arqueológicos costeiros, enfocando pressupostos teóricos e metodológicos ligados à uma aproximação entre a Arqueologia, Geociências e Ciências da Informação. Objetivou em um primeiro momento, inserir questões e problemáticas relativas a necessidade de inclusão da incerteza no raciocínio e práticas arqueológicas, vislumbrando as possibilidades de seu tratamento. Neste sentido, a percepção do \"problema da não informação\" constituiu o argumento conceitual para a elaboração de um modelo de raciocínio dialético sobre a aquisição, geração, seleção e transmissão de informações na disciplina. Nessa perspectiva, sobreveio a necessidade da interação constante entre Teorias de Formação e de Recuperação, como passo essencial ao controle das perdas e ganhos informacionais e, ao tratamento das imperfeições, incompletudes, imprecisões e ambiguidades ligadas aos fenômenos arqueológicos e seu registro científico. Um dos aspectos explorados refere-se à percepção das incertezas e vieses envolvidos na interpretação das ocupações costeiras, notadamente quanto às problemáticas de origem e migração das primeiras populações nessas áreas. Em um modelo atual dicotômico entre o interior e o litoral, onde mesmo os sítios mais antigos (somente sambaquis) acham-se dispostos sobre a superfície dos terrenos, a percepção da dinâmica e complexidade dos sistemas costeiros, fica restrita ao enquadramento desses sítios em sucessões de cenários geomórficos e paeogeográficos. Deste modo, pouca atenção é dada às conseqüências de agentes dinâmicos sobre a configuração e seleção de sítios na atual paisagem costeira, bem como, à possibilidade de ocorrência e detecção de diferentes classes de sítios, que foram preservados em profundidade por meio de processos de capeamento sedimentar. Assim, em um segundo momento, foi proposto à utilização do conceito de \"Controles Geoarquelógicos\" (CG) no estudo e explicitação dos condicionantes naturais e analíticos envolvidos em uma pesquisa de caráter regional, cujo enfoque está nas relações informacionais estabelecidas entre sítios arqueológicos e meio (natural e analítico), e cujo resultado (síntese dialética) compreenderia a noção de evento arqueológico. Diante da explicitação da variabilidade envolvida na caracterização do Registro Arqueológico Regional (RAR), bem como, dos condicionantes complexos derivados da estrutura, dinâmica e evolução da paisagem, o evento arqueológico considerado na tese, compreendeu a investigação da probabilidade de preservação de sítios costeiros antigos (teoria de formação) e do seu potencial de detecção (teoria de recuperação). Neste sentido foi utilizado o raciocínio abdutivo para gerar hipóteses sobre a preservação ou não de sítios encobertos, tendo por base os modelos sedimentares e morfoestratigraficos produzidos para a costa sul-sudeste. Por sua vez, a busca de indicadores nas planícies costeiras de Guaratuba-PR e de Caraguatatuba SP, possibilitou apontar condicionantes (variáveis) favoráveis a geração de um modelo de trapeamento de sítios (capeamento e preservação sedimentar) para a região da Baía de Guaratuba. Por fim, foi testado o raciocínio probabilístico Bayesiano e a Teoria de Evidências (Dempster-Shafer) para a inclusão e representação da incerteza na pesquisa de sambaquis, visualizando um método de tratamento das evidências e inferências geradas em sistemas baseados em conhecimento. Esses mesmos métodos também permitiram determinar os pesos para os diferentes indicadores, e as condições de necessidade, suficiência e ambigüidade das variáveis na geração de mapas aplicados à predição da favorabilidade e suscetibilidade de sítios arqueológicos enterrados na planície costeira de Guaratuba. / This thesis refers to a proposal for a geoarchaeological approach focused on the study of coastal archaeological sites, concentrating on theoretical and methodological assumptions related to a closeness between the archeology, the Information Sciences and Geosciences. It aimed in a first moment, to insert issues and problems concerning the need for inclusion of uncertainty in archaeological reasoning and practice, foreseeing the possibilities of their treatment. In this sense, the perception of the \"no information problem\" was the argument for the conceptual development of a model of dialectical thinking about the acquisition, generation, selection and transmission of information in the discipline. Accordingly, the need for constant interaction between Formation and Recovery Theories became an essential step to the control of informational losses and gains, and the treatment of imperfections, incompleteness, inaccuracies and ambiguities relating to archaeological phenomena and their scientific record. One of the aspects exploited, is the perception of slants and uncertainties involved in the interpretation of coastal activities, notably on issues of origin and migration of the first people in those areas. In a current dichotomic model between the interior and the coast, where even the oldest sites (only sambaquis) are found placed on the surface of the land, the perception of the complexity and dynamics of the coastal systems, is restricted to the framework of these sites in a succession of geomorphic and paleogeographics \"scenarios\". Thus, little attention is given to the dynamic agents consequences on the configuration and selection of sites in the coastal landscape, and the possibility of occurrence and detection of different classes of sites, which were preserved indepth by a sedimental capstone process. Therefore, in a second moment, it was proposed to use the concept of \"geoarchaeological control \" (GC) in the study and explanation of natural and analytical conditions involved in a research of regional manner, whose focus is on the informational relations established between archaeological sites and the environment (natural and analytical), whose result (dialectical synthesis) understand the concept of the archaeological event. Given the explicit characterization of the variability involved in the Regional Archaeological Record (RAR), as well as the complex condition agent derived from the structure, dynamics and evolution of the landscape, the archaeological event considered in the thesis, understand the research of the probability of preservation of ancient coastal sites (formation theory) and its potential for detection (recovery theory). In this sense abdutive reasoning was used to generate hypotheses about the preservation or not of covered sites, based on the sedimentary and morphostratigraphic models produced for the south-southeast coast. In turn, the search for indicators in the coastal plains of Guaratuba- PR and Caraguatatuba-SP, it made possible to point constraints (variables) favorable to the generation of a trap model for sites (sedimental capstone and preservation) for the region of Guaratuba Bay. Finally it was tested the probabilistic bayesian reasoning and Evidence Theory (Dempster-Shafer) for the inclusion and representation of uncertainty in the research of sambaquis foreseeing a method of treatment of the evidence and inferences generated by knowledge-based systems. These methods also allowed to determine the weights for different indicators, and the conditions of necessity, sufficiency and ambiguity of the variables in the generation of maps applied to the prediction of favorability and susceptibility of buried archaeological sites in the coastal plain of Guaratuba.