Made available in DSpace on 2014-06-11T19:33:38Z (GMT). No. of bitstreams: 0 Previous issue date: 2008-11-26Bitstream added on 2014-06-13T20:45:32Z : No. of bitstreams: 1 andrade_ag_dr_jabo.pdf: 23073379 bytes, checksum: 890e280dd903085eca5cf094bbbb6ce3 (MD5) / Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) / Para o estudo da viabilidade do emprego de metodologias de sistema de informação geográfica, geoestatística e redes neurais foram desenvolvidos dois ensaios. O primeiro visou a modelagem da evolução espaço-temporal da incidência do Huanglongbing ao longo dos anos de 2004, 2007 e 2008 em cinco grupos de idade (0 a 2 anos, 3 a 5 anos, 6 a 10 anos, mais de 10 anos, todas as idades), por meio da técnica geoestatística da krigagem e da técnica de inteligência artificial de rede neurais do tipo perceptron de múltiplas camadas com topologia 3x10x10x1, treinada pelo algoritmo da propagação elástica do erro. Neste ensaio foi ainda realizada a análise do modelo do semivariograma, cálculo da média zonal dos talhões dentro de cada faixa de idade e mesorregião do estado de São Paulo, e finalmente, foi previsto o padrão espacial da incidência da doença para o ano de 2009 pelas redes neurais. O segundo ensaio consistiu em se verificar o efeito do alinhamento de plantio na severidade da mancha preta dos citros e sua implicação na qualidade do suco e produção. Neste ensaio foram selecionados talhões distribuídos ao longo do cinturão citrícola paulista com diferentes alinhamentos de plantio, onde foram analisadas as variáveis supracitadas nas linhas de plantio e nas faces expostas da planta. / For viability study of using geographic information systems, geostatistics and neural networks two experiments were carried out. The first one was focused on modeling the spatial-temporal progress of Huanglongbing incidence in 2004, 2007 and 2008 on five age groups (0 – 2 years old, 3 – 5 years old, 6 – 7 years old, more than 10 years old and all ages) using the geostatistical technique of kriguing and the artificial intelligence technique of neural networks of multi-layer perceptron type with 3x10x10x1 topology, trained by resilient error propagation. Complementing the study the analysis of semivariogram model, zonal mean calculation of blocks on each age group were realized inside the mesoregions of São Paulo state and finally the disease incidence spatial pattern for 2009 was forecasted by the neural networks. The objective of the second experiment was verifying effect of planting alignment on citrus black spot severity and its implication on juice quality and production. On this experiment was selected blocks distributed among the São Paulo state citrus belt with different planting alignments, where was analyzed those variables on the lines and exposed faces.

In present diploma thesis called The Problem of Communication between Man and Machine in Contemporary Visual Culture I will analyse the movie by Spike Jonze called Her (2013), in which the topic of interconnection between Artificial Intelligence and real human world is presented. I will deal mostly with the themes of virtual reality and communication between man and computer. The thesis is divided into two parts. The first is based on the analysis of chosen theories of new media in order to reveal the theoretical foundation of the theme of interaction between the man (as human body) and machine (as computer); also I will analyse the development in the fiedl of AI to describe various forms of human-computer communication. The second part of the thesis is based on the case study/analysis of the movie Her, in which the theme of communication between human and computer is presented. In the first part of the thesis I will follows ideas of Lev Manovich, Marshall McLuhan, Pierre Lévy, Paul Virilio, John Searle, Jakub Macek and Mark B. N. Hansen. Keywords Machine, artificial intelligence, virtual reality, new media, computers, internet

CoordenaÃÃo de AperfeÃoamento de Pessoal de NÃvel Superior / Esta dissertaÃÃo visa a detecÃÃo de falhas incipientes por curto-circuito entre espiras de um motor de induÃÃo trifÃsico do tipo gaiola de esquilo acionado por conversor de frequÃncia com modulaÃÃo por largura de pulso do tipo senoidal. Para detectar este tipo de falha, uma bancada de testes à utilizada para impor diferentes condiÃÃes de operaÃÃo ao motor, e cada amostra do conjunto de dados foi extraÃda das correntes de linha do conversor de frequÃncia supracitado. Para extraÃÃo de caracterÃsticas, a anÃlise da assinatura de corrente do motor foi utilizada. Para solucionar este problema, a detecÃÃo desta falha à tratada como um problema de classificaÃÃo, por isso, diferentes algoritmos supervisionados de aprendizado de mÃquina sÃo utilizados: MÃnimos Quadrados OrdinÃrios, Redes Perceptron Simples, Redes Perceptron Multicamadas, MÃquina de Aprendizado Extremo, MÃquina de Vetor de Suporte, MÃquina de Vetor de Suporte por MÃnimos Quadrados, MÃquina de Aprendizado MÃnimo, e Classificadores Gaussianos. Juntamente com a tÃcnica de opÃÃo de rejeiÃÃo, estes classificadores sÃo testados e os resultados destes sÃo comparados entre si e com outros trabalhos que fizeram uso mesmo banco de dados. Taxas de acerto mÃximo de 100% com os classificadores MÃquina de Vetor de Suporte e MÃquina de Vetor de Suporte por MÃnimos Quadrados sugerem que, em um futuro prÃximo, um sistema embarcado pode ser desenvolvido com estes algoritmos. / This dissertation aims at the detection of short-circuit incipient fault condition in a threephase squirrel-cage induction motor fed by a sinusoidal PWM inverter. In order to detect this fault, a test bench is used to impose different operation conditions to an induction motor, and each sample of the data set is taken from the line currents of the PWM inverter aforementioned. For feature extraction, the Motor Current Signature Analysis is used. The detection of this fault is treated as a classification problem, therefore different supervised algorithms of machine learning are used so as to solve it: Ordinary Least Squares, Singlelayer Perceptron, Multi-layer Perceptron, Extreme Learning Machine, Support-Vector Machine, Least-Squares Support-Vector Machine, the Minimal Learning Machine, and Gaussian Classifiers. Together with Reject Option technique, these classifiers are tested and the results are compared with other works that use the same data set. Maximum accuracy rates of 100% with Support-Vector Machine and Least-Squares Support-Vector Machine classifiers suggest that, in near future, an embedded system can be developed with these algorithms.

This thesis in its theoretical part summarizes international knowledge of the problematics of expert systems and their application in automotive diagnostics. In the practical part it solves the methodology and selection of appropriate expert system for the development of diagnostic application. This issue is further elaborated by the methodology of an expert´s knowledge transfer into the knowledge database and creating application for its use within the Windows, Web and Android platforms. Beside the working out the product itself it also provides instructions for others who are interested in preparing similar applications and topic for the future development of the already prepared tool.

This dissertation thesis deals with the topic of Business Intelligence and Balanced Scorecard and its use in České odborné nakladatelství, s.r.o., a relatively small company of 29 employees, which publishes magazines about business, gastronomy, textile, foods, hotels etc. The first part of my thesis describes the BI and BSC theoretically and offers a methodical basis for the following chapters. It gives the reader a definition and structure of BI, with access to a Data Warehouse including the fundamentals of building an OLAP database. It furthermore explains what BSC is, which perspectives use and what a strategic map is. The theoretical chapters of my paper will draw conclusions about the use of BI and BSC and the links between them. The practical, hands-on, chapters continue with the actual application of BI and BSC in the afore-mentioned ČON, s.r.o. It describes the goals and ambitions of the company, which are further on divided into individual strategic goals and metrics, fragmented into perspectives of the BSC and portrayed in a strategic map. Upon analyzing the demands of the company a BI framework is created, data sources are identified, Data Warehouse are designed and brought into effect. In the end a multidimensional OLAP cube is created with MS SQL Server 2008. Finally, there is a MS Excel 2007 explanation and interpretation of the measured values (reporting), which is taken from the available sources of ČON, s.r.o. and is compared against the set strategic goals and metrics of the company. The results of this thesis are based on actual demands of the company and are ready to be implemented and used in real-life.

This thesis explores current and future possible uses of ICT in financial reporting, describes the properties, usage and implementation of EDI and XBRL, describes the concept of online reporting and continuous auditing, introduces the area of artificial intelligence and expert systems and their application in accounting and auditing, describes development and application of FRAANK for extraction of financial data from EDGAR repository, describes the implementation of continuous auditing in Siemens and finally states the possible reasons, why the technologies are not used to their full potential.

This work is aimed at creating a single view in the field of cognitive processes. Namely it is analysis of providing importance of cognitive processes for the entire field of artificial intelligence. The whole area of cognitive processes is described through the analysis of biological cognitive processes and their subsequent comparison with the processes of artificial intelligence and also the overall analysis of their limitations and their use. The work also contains a brief overview of the architecture of artificial intelligence and philosophical essay focused on the relationship of mind and body. In the end we present a project from IBM workshop, which is very important for their ability to work with natural language and understanding the content of questions asked.

This diploma thesis deals with the evaluation of security companies for ZETOR TRACTORS a.s. using fuzzy logic models. The main part of the thesis consists of proposals for the evaluation of the suppliers' evaluation of the company. Decision models are created in Microsoft Excel and Matlab. Another part of the thesis deals with analysis and comparison of results from both programs.

The diploma thesis deals with evaluation of fertilizer suppliers using fuzzy logic models. The main part of the thesis consists of proposals for the evaluation of the company's suppliers. Decision models are created in Microsoft Excel and Matlab. Another part of the thesis deals with analysis and comparison of results from both programs.

This thesis deals with summarization, processing, transformation and interpretation of large amounts of betting odds data. The goal of this thesis is to find out whether it is possible to invest in sports betting odds market without any previous knowledge about sport, using only mathematical skills and business intelligence tools.