Orientador: Renato Vicentini dos Santos / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Biologia / Made available in DSpace on 2018-08-23T02:31:35Z (GMT). No. of bitstreams: 1 Murad_NataliaFaraj_M.pdf: 15243579 bytes, checksum: a5e50145fbdf4bddfb2ea99313b17991 (MD5) Previous issue date: 2013 / Resumo: A cana-de-açúcar é uma das mais importantes plantas cultivadas no Brasil, que é o maior produtor e exportador mundial. Seu valor econômico é devido principalmente a sua capacidade de estocar sacarose nos colmos. Os padrões de expressão gênica podem regular processos de desenvolvimento da planta e influenciar no acúmulo de sacarose em tecidos de reserva. A regulação desses padrões ocorre através de complexos sistemas de interações entre muitos genes e seus produtos, resultando em uma complexa rede de regulação gênica. Modelos gráficos probabilísticos têm sido amplamente utilizados para inferência e representação dessas redes. Dentre eles, as redes bayesianas são o principal por ser considerado o método mais flexível e também requererem um número reduzido de parâmetros para a descrição do modelo. Sendo assim, este estudo utilizou a metodologia de redes bayesianas para inferência de interações regulatórias entre genes de metabolismo e sinalização de sacarose a partir de dados de expressão gênica, obtidos através de microarrays, disponíveis no Gene Expression Omnibus (GEO). As redes foram obtidas através de softwares para inferência de redes e então analisadas quanto aos genes que as compõem e padrões de expressão. Os genes foram agrupados em clusters considerando-se seus padrões de coexpressão. Os genes mais representados no cluster da enzima sacarose fosfato sintase (SPS) em cana são genes de relacionados à tradução, ligação ao DNA e genes de função desconhecida, enquanto os menos representados são de fotossíntese, resposta a hormônios, e outros eventos metabólicos. A rede do cluster da SPS apresentou sete genes principais (hubs) que aparentam ter um importante papel dentro do cluster. Foi obtida também uma rede considerando genes selecionados em estudos com experimentos de microarrays previamente publicados. Uma dessas redes possui 136 genes e apresentou 6 genes principais, sendo que a maioria deles é de fotossíntese. Na rede considerando genes diferencialmente expressos nesses experimentos (265 genes), genes que pertencem à mesma categoria funcional tenderam a sofrer regulação por um único gene em comum, formando grupos de funções semelhantes em cada hub / Abstract: Sugarcane is one of the most important plants cultivated in Brazil which is the world's largest producer and exporter. Its economic yield is mainly due to its high sucrose content. The patterns of gene expression may regulate processes of plant development and influence the accumulation of sucrose by storage tissues. The regulation of these patterns occurs through complex systems of interactions between many genes and their products, resulting in a complex gene regulatory network. Probabilistic graphical models have been widely used for inference and representation of these networks. Among them, Bayesian networks are the main for being considered to be the most flexible method and also requiring a reduced number of parameters to the model description. Then, this work has used the Bayesian network methodology for inference of regulatory interactions between signaling and sucrose metabolism genes from gene expression data, obtained from microarrays, available on Gene Expression Omnibus (GEO). Networks were generated by networks inference softwares, and then analyzed observing their composing genes and expression patterns. The genes were grouped considering their coexpression patterns. The most represented genes in the sacarose phosphate syntase (SPS) cluster are related with translation, DNA biding and unknown function genes while the least represented are of photosynthesis, hormone response and other metabolic events. The SPS cluster network presented 7 main hubs that seem to play an important role in the cluster. It was also obtained a network considering genes selected from studies with microarray experiments previously published. One of these gene networks has 136 genes and it presented 6 main genes, being the most of them are from photosynthesis. In the network considering differential expressed in this experiments, genes that are from the same functional category tended to suffer regulation for one unique common gene, forming groups of genes with similar function on each hub / Mestrado / Genetica Vegetal e Melhoramento / Mestra em Genética e Biologia Molecular

The maritime industry is experiencing one of its longest and fastest periods of growth. Hence, the global maritime surveillance capacity is in a great need of growth as well. The detection of vessel activity is an important objective of the civil security domain. Detecting vessel activity may become problematic if audit data is uncertain. This thesis aims to investigate if Bayesian networks acquired from expert knowledge can detect activities with a signature-based detection approach. For this, a maritime pilot-boat scenario has been identified with a domain expert. Each of the scenario’s activities has been divided up into signatures where each signature relates to a specific Bayesian network information node. The signatures were implemented to find evidences for the Bayesian network information nodes. AIS-data with real world observations have been used for testing, which have shown that it is possible to detect the maritime pilot-boat scenario based on the taken approach.

This thesis explores and compares different methods of optimizing queries in Bayesian networks. Bayesian networks are graph-structured models that model probabilistic variables and their influences on each other; a query poses the question of what probabilities certain variables assume, given observed values on certain other variables. Bayesian inference (calculating these probabilities) is known to be NP-hard in general, but good algorithms exist in practice. Inference optimization traditionally concerns itself with finding and tweaking efficient algorithms, and leaves the choice of algorithms' parameters, as well as the construction of inference-friendly Bayesian network models, as an exercise to the end user. This thesis aims towards a more systematic approach to these topics: We try to optimize the structure of a given Bayesian network for inference, also taking into consideration what is known about the kind of queries that are posed. First, we implement several automatic model modifications that should help to make a model more suitable for inference. Examples of these are the conversion of definitions of conditional probability distributions from table form to noisy gates, and divorcing parents in the graph. Second, we introduce the concepts of usage profiles and query interfaces on Bayesian networks and try to take advantage of them. Finally, we conduct performance measurements of the different options available in the used library for Bayesian networks, to compare the effects of different options on speedup and stability, and to answer the question of which options and parameters represent the optimal choice to perform fast queries in the end product. The thesis gives an overview of what issues are important to consider when trying to optimize an application's query performance in Bayesian networks, and when trying to optimize Bayesian networks for queries. The project uses the SMILE library for Bayesian networks by the University of Pittsburgh, and includes a case study on script-generated Bayesian networks for troubleshooting by Scania AB.

After a huge amount of success within the military, the benefits of the use of unmanned aerial systems over manned aircraft is obvious. They are becoming cheaper and their functions advancing to such a point that there is now a large drive for their use by civilian operators. However there are a number of significant challenges that are slowing their inevitable integration into the national airspace systems of countries. A large array of emergency situations will need to be dealt with autonomously by contingency management systems to prevent potentially deadly incidences. One such emergency situation that will need autonomous intervention, is the total loss of thrust from engine failure. The complex multi faceted task of landing the stricken aircraft at a potentially unprepared site is called a forced landing. This thesis presents methods to address a number of critical parts of a forced landing system for use by an unmanned aerial system. In order for an emergency landing site to be considered, it needs to be within glide range. In order to find a landing site s reachability from the point of engine failure the aircraft s glide performance and a glide path must be known. A method by which to calculate the glide performance, both from aircraft parameters or experiments is shown. These are based on a number of steady state assumptions to make them generic and quick to compute. Despite the assumptions, these are shown to have reasonable accuracy. A minimum height loss path to the landing site is defined, which takes account of a steady uniform wind. While this path is not the path to be flown it enables a measure of how reachable a landing site is, as any extra height the aircraft has once it gets to the site makes a site more reachable. It is shown that this method is fast enough to be run online and is generic enough for use on a range of aircraft. Based on identified factors that make a landing site more suitable, a multi criteria decision making Bayesian network is developed to decide upon which site a unmanned aircraft should land in. It can handle uncertainty and non-complete information while guaranteeing a fast reasonable decision, which is critical in this time sensitive situation. A high fidelity simulation environment and flight test platform are developed in order to test the performance of the developed algorithms. The test environments developed enable rapid prototyping of algorithms not just within the scope of this thesis, but on a range of vehicle types. In simulation the minimum height loss paths show good accuracy, for two completely different types of aircraft. The decision making algorithms show that they are capable of being ran online in a flight test. They make a reasonable decision and are capable of quickly reacting to changing conditions, enabling redirection to a more suitable landing site.

Implementation of EU Water Framework Directive has led to an increased demand for cost-benefit analysis in water management. The directive introduces a good status, which is required on all water bodies by 2027. Excessive phosphorus inflows are one of the main reasons for not meeting the criteria in the Czech Republic. If achieving of the good status is not cost-proportionate, exemption can be applied. Many different methodologies were created across different states, including Czech official methodology by Slavíková et al. (2015). However, this methodology does not deal with uncertainty of measures effectiveness. This thesis describes how to implement the uncertainty into calculations using Bayesian networks. A case study of Stanovice water reservoir demonstrates the approach practically. Results of the Bayesian network show, that selected measures with available data eliminate desired amount of phosphorus in 70% of all cases. This reduction is most likely sufficient, because it holds for the upper estimate of required abatement (60 to 200 kg). Based on comparison of benefits and costs, it seems net benefits are generated by implementing suggested measures. Therefore, policy recommendation is to implement the selected measures.

The failure analysis and resolution in cloud-computing environments are a a highly important issue, being their primary motivation the mitigation of the impact of such failures on applications hosted in these environments. Although there are advances in the case of immediate detection of failures, there is a lack of research in root cause analysis of failures in cloud computing. In this process, failures are tracked to analyze their causal factor. This practice allows cloud operators to act on a more effective process in preventing failures, resulting in the number of recurring failures reduction. Although this practice is commonly performed through human intervention, based on the expertise of professionals, the complexity of cloud-computing environments, coupled with the large volume of data generated from log records generated in these environments and the wide interdependence between system components, has turned manual analysis impractical. Therefore, scalable solutions are needed to automate the root cause analysis process in cloud computing environments, allowing the analysis of large data sets with satisfactory performance. Based on these requirements, this thesis presents a data-driven solution for root cause analysis in cloud-computing environments. The proposed solution includes the required functionalities for the collection, processing and analysis of data, as well as a method based on Bayesian Networks for the automatic identification of root causes. The validation of the proposal is accomplished through a proof of concept using OpenStack, a framework for cloud-computing infrastructure, and Hadoop, a framework for distributed processing of large data volumes. The tests presented satisfactory performance, and the developed model correctly classified the root causes with low rate of false positives. / A análise e reparação de falhas em ambientes de computação em nuvem é uma questão amplamente pesquisada, tendo como principal motivação minimizar o impacto que tais falhas podem causar nas aplicações hospedadas nesses ambientes. Embora exista um avanço na área de detecção imediata de falhas, ainda há percalços para realizar a análise de sua causa raiz. Nesse processo, as falhas são rastreadas a fim de analisar o seu fator causal ou seus fatores causais. Essa prática permite que operadores da nuvem possam atuar de modo mais efetivo na prevenção de falhas, reduzindo-se o número de falhas recorrentes. Embora essa prática seja comumente realizada por meio de intervenção humana, com base no expertise dos profissionais, a complexidade dos ambientes de computação em nuvem, somada ao grande volume de dados oriundos de registros de log gerados nesses ambientes e à ampla inter-dependência entre os componentes do sistema tem tornado a análise manual inviável. Por esse motivo, torna-se necessário soluções que permitam automatizar o processo de análise de causa raiz de uma falha ou conjunto de falhas em ambientes de computação em nuvem, e que sejam escaláveis, viabilizando a análise de grande volume de dados com desempenho satisfatório. Com base em tais necessidades, essa dissertação apresenta uma solução guiada por dados para análise de causa raiz em ambientes de computação em nuvem. A solução proposta contempla as funcionalidades necessárias para a aquisição, processamento e análise de dados no diagnóstico de falhas, bem como um método baseado em Redes Bayesianas para a identificação automática de causas raiz de falhas. A validação da proposta é realizada por meio de uma prova de conceito utilizando o OpenStack, um arcabouço para infraestrutura de computação em nuvem, e o Hadoop, um arcabouço para processamento distribuído de grande volume de dados. Os testes apresentaram desempenhos satisfatórios da arquitetura proposta, e o modelo desenvolvido classificou corretamente com baixo número de falsos positivos.

There are different models, which describe conditional independence induced by multivariate distributions. Models such as Undirected Graphs, Directed Acyclic Graphs, Essential Graphs and Annotated Graphs are introduced and compared in this thesis. The focus is put on annotated graphs. It is shown that annotated graphs represent equivalence classes of DAG-representable relations. An algorithm for reconstruction of an annotated graph from an essential graph as well as the algorithm for the inverse procedure are given. Some properties of a characteristic imset, which is a non-graphical representation, are discussed. A relationship between annotated graphs and characteristic imsets is investigated, an algorithm, which reconstructs an annotated graph from a characteristic imset is given. Powered by TCPDF (www.tcpdf.org)

Background: Modern Code Review (MCR) is a process of reviewing code which is a commonly used practice in software development. It is the process of reviewing any new code changes that need to be merged with the existing codebase. As a developer, one receives many code review requests daily that need to be reviewed. When the developer receives the review requests, they are not prioritised. Manuallyprioritising them is a challenging and time-consuming process. Objectives: This thesis aims to address and solve the above issues by developing a machine intelligence-based code review prioritisation tool. The goal is to identify the factors that impact code review prioritisation process with the help of feedback provided by experienced developers and literature; these factors can be used to develop and implement a solution that helps in prioritising the code review requests automatically. The solution developed is later deployed and evaluated through user and reviewer feedback in a real large-scale project. The developed prioritisation tool is named as Pineapple. Methods: A case study has been conducted at Ericsson. The identification of factors that impact the code review prioritisation process was identified through literature review and semi-structured interviews. The feasibility, usability, and usefulness of Pineapple have been evaluated using a static validation method with the help of responses provided by the developers after using the tool. Results: The results indicate that Pineapple can help developers prioritise their code review requests and assist them while performing code reviews. It was found that the majority of people believed Pineapple has the ability to decrease the lead time of the code review process while providing reliable prioritisations. The prioritisations are performed in a production environment with an average time of two seconds. Conclusions: The implementation and validation of Pineapple suggest the possible usefulness of the tool to help developers prioritise their code review requests. The tool helps to decrease the code review lead-time, along with reducing the workload on a developer while reviewing code changes.

This thesis consists of two papers studying structure learning in probabilistic graphical models for both undirected graphs anddirected acyclic graphs (DAGs). Paper A, presents a novel family of graph theoretical algorithms, called the junction tree expanders, that incrementally construct junction trees for decomposable graphs. Due to its Markovian property, the junction tree expanders are shown to be suitable for proposal kernels in a sequential Monte Carlo (SMC) sampling scheme for approximating a graph posterior distribution. A simulation study is performed for the case of Gaussian decomposable graphical models showing efficiency of the suggested unified approach for both structural and parametric Bayesian inference. Paper B, develops a novel prior distribution over DAGs with the ability to express prior knowledge in terms of graph layerings. In conjunction with the prior, a search and score algorithm based on the layering property of DAGs, is developed for performing structure learning in Bayesian networks. A simulation study shows that the search and score algorithm along with the prior has superior performance for learning graph with a clearly layered structure compared with other priors. / <p>QC 20160111</p>

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / This research proposes a prediction model that might help reducing the dropout rate of university students in Peru. For this, a three-phase predictive analysis model was designed which was combined with the stages proposed by the IBM SPSS Modeler methodology. Bayesian network techniques was compared with decision trees for their level of accuracy over other algorithms in an Educational Data Mining (EDM) scenario. Data were collected from 500 undergraduate students from a private university in Lima. The results indicate that Bayesian networks behave better than decision trees based on metrics of precision, accuracy, specificity, and error rate. Particularly, the accuracy of Bayesian networks reaches 67.10% while the accuracy for decision trees is 61.92% in the training sample for iteration with 8:2 rate. On the other hand, the variables athletic person (0.30%), own house (0.21%), and high school grades (0.13%) are the ones that contribute most to the prediction model for both Bayesian networks and decision trees.