Ecosystems consist of complex dynamic interactions among species and the environment, the understanding of which has implications for predicting the environmental response to changes in climate and biodiversity. Understanding the nature of functional relationships (such as prey-predator) between species is important for building predictive models. However, modelling the interactions with external stressors over time and space is also essential for ecosystem-based approaches to fisheries management. With the recent adoption of more explorative tools, like Bayesian networks, in predictive ecology, fewer assumptions can be made about the data and complex, spatially varying interactions can be recovered from collected field data and combined with existing knowledge. In this thesis, we explore Bayesian network modelling approaches, accounting for latent effects to reveal species dynamics within geographically different marine ecosystems. First, we introduce the concept of functional equivalence between different fish species and generalise trophic structure from different marine ecosystems in order to predict influence from natural and anthropogenic sources. The importance of a hidden variable in fish community change studies of this nature was acknowledged because it allows causes of change which are not purely found within the constrained model structure. Then, a functional network modelling approach was developed for the region of North Sea that takes into consideration unmeasured latent effects and spatial autocorrelation to model species interactions and associations with external factors such as climate and fisheries exploitation. The proposed model was able to produce novel insights on the ecosystem's dynamics and ecological interactions mainly because it accounts for the heterogeneous nature of the driving factors within spatially differentiated areas and their changes over time. Finally, a modified version of this dynamic Bayesian network model was used to predict the response of different ecosystem components to change in anthropogenic and environmental factors. Through the development of fisheries catch, temperature and productivity scenarios, we explore the future of different fish and zooplankton species and examine what trends of fisheries exploitation and environmental change are potentially beneficial in terms of ecological stability and resilience. Thus, we were able to provide a new data-driven modelling approach which might be beneficial to give strategic advice on potential response of the system to pressure.

Este trabalho apresenta o processo de construção de um modelo de inferência de emoções que um aluno sente em relação a outros alunos durante interação síncrona em um contexto de jogo colaborativo de aprendizagem. A inferência de emoções está psicologicamente fundamentada na abordagem da avaliação cognitiva e foram investigadas relações entre objetivos e normas comportamentais do aluno e aspectos de sua personalidade. Especificamente, foram empregados o modelo OCC de emoções e o modelo Big-Five (Cinco Grandes Fatores) de traços de personalidade para a fundamentação teórica da modelagem. O modelo afetivo representa a vergonha e orgulho apresentados pelo aluno em resposta à avaliação cognitiva de suas próprias ações e a reprovação e admiração apresentadas pelo aluno em resposta a ações de seu parceiro de jogo, a partir da avaliação do comportamento observável dos parceiros representado por suas interações no jogo colaborativo, em relação a normas comportamentais do aluno. A fim de suportar a incerteza presente na informação afetiva e cognitiva do aluno, adotou-se uma representação deste conhecimento através de Rede Bayesiana. Um refinamento qualitativo parcial e a respectiva parametrização quantitativa do modelo probabilístico foram efetuados a partir da análise de uma base de casos obtida através da condução de experimentos. A fim de prover um ambiente experimental, foi concebido e prototipado um jogo colaborativo no qual dois indivíduos conjugam esforços a fim de resolver problemas lógicos comuns à dupla, através de ações coordenadas, negociação simples e comunicação estruturada, em competição com outras duplas. / This work presents the construction of a model to infer emotions a student feels towards other students during synchronous interaction in the context of a collaborative learning game. The emotions inference is psychologically based on cognitive appraisal theory. Some relations between students’ personality and their goals and behavioral standards were also investigated. This modeling was based on OCC emotion model and Big-Five personality model. The affective model represents the student’s proud and shame as an answer to the cognitive appraisal of her/his own attributed interactions, and the student’s admiration and reproach as an answer to the cognitive appraisal of her/his partner attributed interactions, both according to the student’s behavioral standards. Bayesian Network knowledge representation was employed to better stand for the uncertainty present in the student’s cognitive and affective information. Employing a data-driven procedure, the probabilistic model was partially refined in terms of qualitative relations and quantitative parameters. Experimental data were obtained by using a game prototype implemented in order to support a collaborative dynamics of coordinated action, simple negotiation and structured communication, through which students interacted in order to solve shared problems, during synchronous competition with other students.

A representação do conhecimento de maneira mais fiel possível à realidade é uma meta histórica e não resolvida até o momento na área da Inteligência Artificial. Problemas são resolvidos e decisões são tomadas levando-se em conta diversos tipos de conhecimentos, os quais muitos são tendenciosos, inexatos, ambíguos ou ainda incompletos. A fim de tentar emular a capacidade de representação do conhecimento humano, levando-se em conta as diversas dificuldades inerentes, tem-se construído sistemas computacionais que armazenam o conhecimento das mais diversas formas. Dentro deste contexto, este trabalho propõe um experimento que utiliza duas formas distintas de representação do conhecimento: a simbólica, neste caso BDI, e a probabilística, neste caso Redes Bayesianas. Para desenvolvermos uma prova de conceito desta proposta de representação do conhecimento estamos utilizando exemplos que serão construídos através da tecnologia de programação voltada para agentes. Para tal, foi desenvolvida uma implementação de um Sistema MultiAgente, estendendo o framework Jason através da implementação de um plugin chamado COPA. Para a representação do conhecimento probabilístico, utilizamos uma ferramenta de construção de Redes Bayesianas, também adaptada a este sistema. Os estudos de caso mostraram melhorias no gerenciamento do conhecimento incerto em relação às abordagens de construções de agentes BDI clássicos, ou seja, que não utilizam conhecimento probabilístico. / Achieving faithful representation of knowledge is a historic and still unreached goal in the area of Artificial Intelligence. Problems are solved and decisions are made taking into consideration different kinds of knowledge, from which many are biased, inaccurate, ambiguous or still incomplete. Computational systems that store knowledge in many different ways have been built in order to emulate the capacity of human knowledge representation, taking into consideration the several inherent difficulties to it. Within this context, this paper proposes an experiment that utilizes two distinct ways of representing knowledge: symbolic, BDI in this case, and probabilistic, Bayesian Networks in this case. In order to develop a proof of concept of this propose of knowledge representation, examples that will be built through agent oriented programming technology will be used. For that, implementation of a MultiAgent System was developed, extending the Jason framework through the implementation of a plugin called COPA. For the representation of probabilistic knowledge, a Bayesian Network building tool, also adapted to this system, was used. The case studies showed improvement in the management of uncertain knowledge in relation to the building approaches of classic BDI agents, i.e., that do not use probabilistic knowledge.

abstract: Many methodological approaches have been utilized to predict student retention and persistence over the years, yet few have utilized a Bayesian framework. It is believed this is due in part to the absence of an established process for guiding educational researchers reared in a frequentist perspective into the realms of Bayesian analysis and educational data mining. The current study aimed to address this by providing a model-building process for developing a Bayesian network (BN) that leveraged educational data mining, Bayesian analysis, and traditional iterative model-building techniques in order to predict whether community college students will stop out at the completion of each of their first six terms. The study utilized exploratory and confirmatory techniques to reduce an initial pool of more than 50 potential predictor variables to a parsimonious final BN with only four predictor variables. The average in-sample classification accuracy rate for the model was 80% (Cohen's κ = 53%). The model was shown to be generalizable across samples with an average out-of-sample classification accuracy rate of 78% (Cohen's κ = 49%). The classification rates for the BN were also found to be superior to the classification rates produced by an analog frequentist discrete-time survival analysis model. / Dissertation/Thesis / Doctoral Dissertation Educational Psychology 2015

abstract: Understanding customer preference is crucial for new product planning and marketing decisions. This thesis explores how historical data can be leveraged to understand and predict customer preference. This thesis presents a decision support framework that provides a holistic view on customer preference by following a two-phase procedure. Phase-1 uses cluster analysis to create product profiles based on which customer profiles are derived. Phase-2 then delves deep into each of the customer profiles and investigates causality behind their preference using Bayesian networks. This thesis illustrates the working of the framework using the case of Intel Corporation, world’s largest semiconductor manufacturing company. / Dissertation/Thesis / Masters Thesis Industrial Engineering 2017

Sistemas para assistência de pessoas com sequelas de Acidente Vascular Cerebral (AVC) como, por exemplo, a Disartria apresenta interesse crescente devido ao aumento da parcela da população com esses distúrbios. Este trabalho propõe a aquisição e o processamento dos biosinais de Eletromiografia de Superficie (sEMG) no músculos do rosto ligados ao processo da fala e de Eletroencefalografia (EEG), sincronizados no tempo mediante um arquivo de áudio. Para isso realizaram-se coletas em voluntários saudáveis no Laboratório IEE e com voluntários com Disartria, previamente diagnosticados com AVC, no departamento de Fisioterapia do Hospital de Clínicas de Porto Alegre. O objetivo principal é classificar esses biosinais frente a comandos verbais estabelecidos, mediante o método computacional Support Vector Machine (SVM) para o sinal de sEMG e Naive Bayes (NB) para o sinal de EEG, visando o futuro estudo e classificação do grau de Disartria do paciente. Estes métodos foram comparados com o Linear Discriminant Analysis (LDA), que foi implementado para os sinais de sEMG e EEG. As características extraídas do sinal de sEMG foram: desvio padrão, média aritmética, skewness, kurtosis e RMS; para o sinal de EEG as características extraídas na frequência foram: Mínimo, Máximo, Média e Desvio padrão e Skewness e Kurtosis, no domínio do tempo. Como parte do pré-processamento também foi empregado o filtro espacial Common Spatial Pattern (CSP) de forma a aumentar a atividade discriminativa entre as classes de movimento no sinal de EEG. Foi avaliado através de um Projeto de Experimentos Fatorial, a natureza das coletas, o sujeito, o método computacional, o estado do sujeito e a banda de frequência filtrada para EEG. Os comandos verbais definidos: “Direita”, “Esquerda”, “Para Frente” e “Para Trás”, possibilitaram a identificação de tarefas mentais em sujeitos saudáveis e com Disartria, atingindo-se Accuracy de 77,6% - 80,8%. / Assistive technology for people with Cerebrovascular Accident (CVA) aftereffects, such as Dysarthria, is gaining interest due to the increasing proportion of the population with these disorders. This work proposes the acquisition and processing of Surface Electromyography (sEMG) signal from the speech process face muscles and Electroencephalography (EEG) signal, synchronized in time by an audio file. For that reason assays were carried out with healthy volunteers at IEE Laboratory and with dysarthric volunteers, previously diagnosed with CVA, at the physiotherapy department of the Porto Alegre University Hospital. The main objective is to classify these biosignals in front of verbal commands established, by computational method of Support Vector Machine (SVM) for the sEMG and Naive Bayes (NB) for EEG, regarding the future study and classification of pacient degree of Dysarthria. These methods were compared with Linear Discriminant Analysis (LDA), who was implemented for sEMG and EEG. The extracted features of sEMG signal were: standard deviation, arithmetic mean, skewness, kurtosis and RMS; for EEG signal extracted features in frequency domain were: minimum, maximum, average and standard deviation, skewness and kurtosis, were used for time domain extraction. As part of pre-processing, Common Spatial Pattern (CSP) filter was also employed, in order to increase the discriminating activity between motion classes in the EEG signal. Data were evaluated in a factorial experiment project, with nature of assays, subject, computational method, subject health state and specifically for EEG were evaluated frequency band filtered. Defined verbal commands, "Right", "Left", "Forward" and "Back", allowed the identification of mental tasks in healthy subjects and dysarthric subjects, reaching Accuracy of 77.6% - 80.8%.

As teorias que sustentam os modelos de precificação têm obtido resultados pouco satisfatórios ou insatisfatórios, uma vez que em cada estudo busca aproximar-se da realidade por apenas uma face, não observando o problema de todos os ângulos. Nesse sentido, percebeu-se um gap nos estudos de previsão, explorar sob outras lentes a dinâmica das variáveis do mercado que influenciam a formação do preço para o seu prévio monitoramento. Assim, o objetivo desta pesquisa foi construir uma ferramenta de apoio à decisão que pudesse prever, periodicamente, o preço futuro de uma commodity a curto e médio prazo, notadamente para o butadieno, um derivado do petróleo. Para que isto fosse possível, foi realizada a datação dos pontos de mudança do preço dessa commodity, frente aos acontecimentos históricos e, a partir daí, construído o estudo sobre três estruturas: mercado, política e econômica. A partir de então, observou-se quais seriam as variáveis mais consistentes para formar a base da pesquisa. As previsões obtidas revelam um desempenho superior às pesquisas anteriormente realizadas. Assim, a análise da previsão dos pontos de mudança constitui um instrumento informativo para sinalizar o comportamento futuro do preço da commodity do butadieno. A ferramenta utilizada para o modelo de precificação de modo a compreender a natureza das flutuações foram as Redes Bayesianas, que apresentam a capacidade de expressar as probabilidades e de um conjunto de variáveis aleatórias previamente definidas, e fazer predições adequadas. A inferência sobre o preço da commodity do butadieno, a curto e médio prazo, é realizada com o auxílio do software GeNIe 2.0. Conclui-se que investir em pesquisas que utilizem de Inteligência Artificial como métodos preditivos, como a utilização de Redes Bayesianas apresenta a vantagem de compreender a relação causa e efeito através da análise de Cenários. Assim, o objetivo de construir uma ferramenta de apoio à decisão que pudesse prever, periodicamente, o preço do butadieno a curto e médio prazo, foi alcançado. Para determinado período houve 84% de chances de acerto nas previsões. / The theories that support pricing models have obtained little satisfactory or unsatisfactory results, once each study examines only one aspect of reality, without studying the problem as a whole. In this sense its necessary to explore under other aspects the dynamics of market variables that influence the pricing for its prior monitoring. The objective of this research was to build a decision support tool capable of periodically forecast the future price of a commodity in the short and medium term, especially for butadiene, an oil derivative. To make it possible, was done the dating of turning points in the price of this commodity compared to the historical events and based on these data to build this study on three structures: market, political and economic. Then, we identified the most consistent variables to form the basis of the research. The forecasts obtained show a higher performance compared to previous investigations. Thus, the forecast analysis of turning points is an informative tool to signal the future behavior of the price of this commodity. To understand the nature of these fluctuations, the method used in the pricing model were the Bayesian networks, which are capable of expressing the probabilities of a set of random variables defined previously and make appropriate predictions. The inference on the commodity price of butadiene – in the short and medium term, was performed using the Genie 2.0 software. The conclusion was that investing in research using artificial intelligence and predictive methods such as the Bayesian networks, has the advantage of understanding the relationship of cause and effect through scenario analysis. So the objective of building a decision support tool that can predict periodically, the price of butadiene in the short and medium term, has been achieved. For certain period was 84% accurate in forecasts of chances.

abstract: Dynamic Bayesian networks (DBNs; Reye, 2004) are a promising tool for modeling student proficiency under rich measurement scenarios (Reichenberg, in press). These scenarios often present assessment conditions far more complex than what is seen with more traditional assessments and require assessment arguments and psychometric models capable of integrating those complexities. Unfortunately, DBNs remain understudied and their psychometric properties relatively unknown. If the apparent strengths of DBNs are to be leveraged, then the body of literature surrounding their properties and use needs to be expanded upon. To this end, the current work aimed at exploring the properties of DBNs under a variety of realistic psychometric conditions. A two-phase Monte Carlo simulation study was conducted in order to evaluate parameter recovery for DBNs using maximum likelihood estimation with the Netica software package. Phase 1 included a limited number of conditions and was exploratory in nature while Phase 2 included a larger and more targeted complement of conditions. Manipulated factors included sample size, measurement quality, test length, the number of measurement occasions. Results suggested that measurement quality has the most prominent impact on estimation quality with more distinct performance categories yielding better estimation. While increasing sample size tended to improve estimation, there were a limited number of conditions under which greater samples size led to more estimation bias. An exploration of this phenomenon is included. From a practical perspective, parameter recovery appeared to be sufficient with samples as low as N = 400 as long as measurement quality was not poor and at least three items were present at each measurement occasion. Tests consisting of only a single item required exceptional measurement quality in order to adequately recover model parameters. The study was somewhat limited due to potentially software-specific issues as well as a non-comprehensive collection of experimental conditions. Further research should replicate and, potentially expand the current work using other software packages including exploring alternate estimation methods (e.g., Markov chain Monte Carlo). / Dissertation/Thesis / Doctoral Dissertation Family and Human Development 2018

O Gás Natural Liquefeito (GNL) tem, aos poucos, se tornado uma importante opção para a diversificação da matriz energética brasileira. Os navios metaneiros são os responsáveis pelo transporte do GNL desde as plantas de liquefação até as de regaseificação. Dada a importância, bem como a periculosidade, das operações de transporte e de carga e descarga de navios metaneiros, torna-se necessário não só um bom plano de manutenção como também um sistema de detecção de falhas que podem ocorrer durante estes processos. Este trabalho apresenta um método de diagnose de falhas para a operação de carga e descarga de navios transportadores de GNL através da utilização de Redes Bayesianas em conjunto com técnicas de análise de confiabilidade, como a Análise de Modos e Efeitos de Falhas (FMEA) e a Análise de Árvores de Falhas (FTA). O método proposto indica, através da leitura de sensores presentes no sistema de carga e descarga, quais os componentes que mais provavelmente estão em falha. O método fornece uma abordagem bem estruturada para a construção das Redes Bayesianas utilizadas na diagnose de falhas do sistema. / Liquefied Natural Gas (LNG) has gradually become an important option for the diversification of the Brazilian energy matrix. LNG carriers are responsible for LNG transportation from the liquefaction plant to the regaseification plant. Given the importance, as well as the risk, of transportation and loading/unloading operations of LNG carriers, not only a good maintenance plan is needed, but also a failure detection system that localizes the origin of a failure that may occur during these processes. This research presents a fault diagnosis method for the loading and unloading operations of LNG carriers through the use of Bayesian networks together with reliability analysis techniques, such as Failure Modes and Effects Analysis (FMEA ) and Fault Tree Analysis (FTA). The proposed method indicates, by reading sensors present in the loading and unloading system, which components are most likely faulty. The method provides a well-structured approach for the development of Bayesian networks used in the diagnosis of system failures.

A representação do conhecimento de maneira mais fiel possível à realidade é uma meta histórica e não resolvida até o momento na área da Inteligência Artificial. Problemas são resolvidos e decisões são tomadas levando-se em conta diversos tipos de conhecimentos, os quais muitos são tendenciosos, inexatos, ambíguos ou ainda incompletos. A fim de tentar emular a capacidade de representação do conhecimento humano, levando-se em conta as diversas dificuldades inerentes, tem-se construído sistemas computacionais que armazenam o conhecimento das mais diversas formas. Dentro deste contexto, este trabalho propõe um experimento que utiliza duas formas distintas de representação do conhecimento: a simbólica, neste caso BDI, e a probabilística, neste caso Redes Bayesianas. Para desenvolvermos uma prova de conceito desta proposta de representação do conhecimento estamos utilizando exemplos que serão construídos através da tecnologia de programação voltada para agentes. Para tal, foi desenvolvida uma implementação de um Sistema MultiAgente, estendendo o framework Jason através da implementação de um plugin chamado COPA. Para a representação do conhecimento probabilístico, utilizamos uma ferramenta de construção de Redes Bayesianas, também adaptada a este sistema. Os estudos de caso mostraram melhorias no gerenciamento do conhecimento incerto em relação às abordagens de construções de agentes BDI clássicos, ou seja, que não utilizam conhecimento probabilístico. / Achieving faithful representation of knowledge is a historic and still unreached goal in the area of Artificial Intelligence. Problems are solved and decisions are made taking into consideration different kinds of knowledge, from which many are biased, inaccurate, ambiguous or still incomplete. Computational systems that store knowledge in many different ways have been built in order to emulate the capacity of human knowledge representation, taking into consideration the several inherent difficulties to it. Within this context, this paper proposes an experiment that utilizes two distinct ways of representing knowledge: symbolic, BDI in this case, and probabilistic, Bayesian Networks in this case. In order to develop a proof of concept of this propose of knowledge representation, examples that will be built through agent oriented programming technology will be used. For that, implementation of a MultiAgent System was developed, extending the Jason framework through the implementation of a plugin called COPA. For the representation of probabilistic knowledge, a Bayesian Network building tool, also adapted to this system, was used. The case studies showed improvement in the management of uncertain knowledge in relation to the building approaches of classic BDI agents, i.e., that do not use probabilistic knowledge.