DC to DC converters stabilize the voltage obtained from voltage sources such as solar power system, wind energy sources, wave energy sources, rectified voltage from alternators, and so forth. Hence, the need for improving its control algorithm is inevitable. Many algorithms are applied to DC to DC converters. This thesis designs fuzzy adaptive dynamic programming (Fuzzy ADP) algorithm. Also, this thesis implements both adaptive dynamic programming (ADP) and Fuzzy ADP on DC to DC converters to observe the performance of the output voltage trajectories.

This master thesis deals with detection of microsleep on the basis of the changes in power spectrum of EEG signal. The results of time-frequency analysis are input values for the classifikation. Proposed classification method uses fuzzy logic. Four classifiers were designed, which are based on a fuzzy inference systems, that are differ in rule base. The results of fuzzy clustering are used for the design of rule premises membership functions. The two classifiers microsleep detection use only alpha band of the EEG signal’s spectrogram then allows the detection of the relaxation state of a person. Unlike to first and second classifiers, the third classifier is supplemented with rules for the delta band, which makes it possible to distinguish the 3 states: vigilance, relaxation and somnolence. The fourth classifier inference system includes the rules for the whole spectrum band. The method was implemented by computer. The program with a graphical user interface was created.

[pt] A série temporal é a representação mais comum para a evoluçãao no tempo de uma variável qualquer. Em um problema de previsão de séries temporais, procura-se ajustar um modelo para obter valores futuros da série, supondo que as informações necessárias para tal se encontram no próprio histórico da série. Como os fenômenos representados pelas séries temporais nem sempre existem de maneira isolada, pode-se enriquecer o modelo com os valores históricos de outras séries temporais relacionadas. A estrutura formada por diversas séries de mesmo intervalo e dimensão ocorrendo paralelamente é denominada série temporal multivariada. Esta dissertação propõe uma metodologia de geração de um Sistema de Inferência Fuzzy (SIF) para previsão de séries temporais multivariadas a partir de dados históricos, com o objetivo de obter bom desempenho tanto em termos de acurácia de previsão como no quesito interpretabilidade da base de regras – com o intuito de extrair conhecimento sobre o relacionamento entre as séries. Para tal, são abordados diversos aspectos relativos ao funcionamento e à construção de um SIF, levando em conta a sua complexidade e claridade semântica. O modelo é avaliado por meio de sua aplicação em séries temporais multivariadas da base completa da competição M3, comparandose a sua acurácia com as dos métodos participantes. Além disso, através de dois estudos de caso com dados reais públicos, suas possibilidades de extração de conhecimento são exploradas por meio de dois estudos de caso construídos a partir de dados reais. Os resultados confirmam a capacidade do AutoMFIS de modelar de maneira satisfatória séries temporais multivariadas e de extrair conhecimento da base de dados. / [en] A time series is the most commonly used representation for the evolution of a given variable over time. In a time series forecasting problem, a model aims at predicting the series future values, assuming that all information needed to do so is contained in the series past behavior. Since the phenomena described by the time series does not always exist in isolation, it is possible to enhance the model with historical data from other related time series. The structure formed by several different time series occurring in parallel, each featuring the same interval and dimension, is called a multivariate time series. This dissertation proposes a methodology for the generation of a Fuzzy Inference System (FIS) for multivariate time series forecasting from historical data, aiming at good performance in both forecasting accuracy and rule base interpretability – in order to extract knowledge about the relationship between the modeled time series. Several aspects related to the operation and construction of such a FIS are investigated regarding complexity and semantic clarity. The model is evaluated by applying it to multivariate time series obtained from the complete M3 competition database and by comparing it to other methods in terms of accuracy. In addition knowledge extraction possibilities are explored through two case studies built from actual data. Results confirm that AutoMFIS is indeed capable of modeling time series behaviors in a satisfactory way and of extractig meaningful knowldege from the databases.

[pt] Por definição, a série temporal representa o comportamento de uma variável em função do tempo. Para o processo de previsão de séries, o modelo deve ser capaz de aprender a dinâmica temporal das variáveis para obter valores futuros. Contudo, prever séries temporais com exatidão é uma tarefa que vai além de escolher o modelo mais complexo, e portanto a etapa de análise é um processo fundamental para orientar o ajuste do modelo. Especificamente em problemas multivariados, o AutoMFIS é um modelo baseado na lógica fuzzy, desenvolvido para introduzir uma explicabilidade dos resultados através de regras semanticamente compreensíveis. Mesmo com características promissoras e positivas, este sistema possui limitações que tornam sua utilização impraticável em problemas com bases de dados com alta dimensionalidade. E com a presença cada vez maior de bases de dados mais volumosas, é necessário que a síntese automática de sistemas fuzzy seja adaptada para abranger essa nova classe de problemas de previsão. Por conta desta necessidade, a presente dissertação propõe a extensão do modelo AutoMFIS para a previsão de séries temporais com alta dimensionalidade, chamado de e-AutoMFIS. Apresentase uma nova metodologia, baseada em comitê de previsores, para o aprendizado distribuído de geração de regras fuzzy. Neste trabalho, são descritas as características importantes do modelo proposto, salientando as modificações realizadas para aprimorar tanto a previsão quanto a interpretabilidade do sistema. Além disso, também é avaliado o seu desempenho em problemas reais, comparando-se a acurácia dos resultados com as de outras técnicas descritas na literatura. Por fim, em cada problema selecionado também é considerado o aspecto da interpretabilidade, discutindo-se os critérios utilizados para a análise de explicabilidade. / [en] By definition, the time series represents the behavior of a variable as a time function. For the series forecasting process, the model must be able to learn the temporal dynamics of the variables in order to obtain consistent future values. However, an accurate time series prediction is a task that goes beyond choosing the most complex (or promising) model that is applicable to the type of problem, and therefore the analysis step is a fundamental procedure to guide the adaptation of a model. Specifically, in multivariate problems, AutoMFIS is a model based on fuzzy logic, developed not only to give accurate forecasts but also to introduce the explainability of results through semantically understandable rules. Even with such promising characteristics, this system has shown practical limitations in problems that involve datasets of high dimensionality. With the increasing demand formethods to deal with large datasets, it should be great that approaches for the automatic synthesis of fuzzy systems could be adapted to cover a new class of forecasting problems. This dissertation proposes an extension of the base model AutoMFIS modeling method for time series forecasting with high dimensionality data, named as e-AutoMFIS. Based on the Ensemble learning theory, this new methodology applies distributed learning to generate fuzzy rules. The main characteristics of the proposed model are described, highlighting the changes in order to improve both the accuracy and the interpretability of the system. The proposed model is also evaluated in different case studies, in which the results are compared in terms of accuracy against the results produced by other methods in the literature. In addition, in each selected problem, the aspect of interpretability is also assessed, which is essential for explainability evaluation.

[pt] Hoje em dia, grande parte do conhecimento acumulado está armazenada em forma de dados. Dentre as ferramentas capazes de atuar como modelos representativos de sistemas reais, os Sistemas de Inferência Fuzzy têm se destacado pela capacidade de fornecer modelos precisos e, ao mesmo tempo, interpretáveis. A interpretabilidade é obtida a partir de regras linguísticas, que podem ser extraídas de bases de dados bases históricas e que permitem ao usuário compreender a relação entre as variáveis do problema. Entretanto, tais sistemas sofrem com a maldição da dimensionalidade ao lidar com problemas complexos, isto é, com um grande número de variáveis de entrada ou padrões, gerando problemas de escalabilidade. Esta dissertação apresenta um novo algoritmo de geração automática de regras, denominado RandomFIS, especificamente para problemas de classificação, capaz de lidar com grandes bases de dados tanto em termos de número de variáveis de entrada (atributos) quanto em termos de padrões (instâncias). O modelo RandomFIS utiliza os conceitos de seleção de variáveis (Random Subspace) e Bag of Little Bootstrap (BLB), que é uma versão escalável do Bootstrapping, criando uma estrutura de comitê de classificadores. O RandomFIS é avaliado em várias bases benchmark, demostrando ser um modelo robusto que mantém a interpretabilidade e apresenta boa acurácia mesmo em problemas envolvendo grandes bases de dados. / [en] Nowadays, much of the accumulated knowledge is stored as data. Among the tools capable of acting as representative models of real systems, Fuzzy Inference Systems are recognized by their ability to provide accurate and at the same time interpretable models. Interpretability is obtained from linguistic rules, which can be extracted from historical databases. These rules allow the end user to understand the relationship between variables in a specific problem. However, such systems experience the curse of dimensionality when handling complex problems, i.e. with a large number of input variables or patterns in the dataset, giving origin to scalability issues. This dissertation presents a new algorithm for automatic generation of fuzzy rules, called RandomFIS, specifically for classification problems, which is able to handle large databases both in terms of number of input variables (attributes) and in terms of patterns (instances). The RandomFIS model makes use of feature selection concepts (Random Subspace) and Bag of Little Bootstrap (BLB), which is a scalable version of Bootstrapping, creating a classifier committee structure. RandomFIS is tested in several benchmark datasets and shows to be a robust model that maintains interpretability and good accuracy even in problems involving large databases.

No description available.

Submitted in complete fulfillment for the degree of Doctor of Philosophy (Biotechnology), Durban University of Technology, Durban, South Africa, 2016. / Seasonal nitrification breakdown is a major problem in wastewater treatment plants which makes it difficult for the plant operators to meet discharge limits. The present study focused on understanding the seasonal impact of environmental and operational parameters on nitrifiers and nitrification, in a biological nutrient removal wastewater treatment works situated in the midlands of KwaZulu Natal. Composite sludge samples (from the aeration tank), influent and effluent water samples were collected twice a month for 237 days. A combination of fluorescent in-situ hybridization, polymerase chain reaction (PCR)-clone library, quantitative polymerase chain reaction (qPCR) were employed for characterizing and quantifying the dominant nitrifiers in the plant. In order to have more insight into the activated sludge community structure, pyrosequencing was used in profiling the amoA locus of ammonia oxidizing bacteria (AOB) community whilst Illumina sequencing was used in characterising the plant’s total bacterial community. The nonlinear effect of operating parameters and environmental conditions on nitrification was also investigated using an adaptive neuro-fuzzy inference system (ANFIS), Pearson’s correlation coefficient and quadratic models. The plant operated with higher MLSS of 6157±783 mg/L during the first phase (winter) whilst it was 4728±1282 mg/L in summer. The temperature recorded in the aeration tanks ranged from 14.2oC to 25.1oC during the period. The average ammonia removal during winter was 60.0±18% whereas it was 83±13% during summer and this was found to correlate with temperature (r = 0.7671; P = 0.0008). A significant correlation was also found between the AOB (amoA gene) copy numbers and temperature in the reactors (α= 0.05; P=0.05), with the lowest AOB abundance recorded during winter. Sanger sequencing analysis indicated that the dominant nitrifiers were Nitrosomonas spp. Nitrobacter spp. and Nitrospira spp. Pyrosequencing revealed significant differences in the AOB population which was 6 times higher during summer compared to winter. The AOB sequences related to uncultured bacterium and uncultured AOB also showed an increase of 133% and 360% respectively when the season changed from winter to summer. This study suggests that vast population of novel, ecologically significant AOB species, which remain unexploited, still inhabit the complex activated sludge communities. Based on ANFIS model, AOB increased during summer season, when temperature was 1.4-fold higher than winter (r 0.517, p 0.048), and HRT decreased by 31% as a result of rainfall (r - 0.741, p 0.002). Food: microorganism ratio (F/M) and HRT formed the optimal combination of two inputs affecting the plant’s specific nitrification (qN), and their quadratic equation showed r2-value of 0.50. This study has significantly contributed towards understanding the complex relationship between the microbial population dynamics, wastewater composition and nitrification performance in a full-scale treatment plant situated in the subtropical region. This is the first study applying ANFIS technique to describe the nitrification performance at a full-scale WWTP, subjected to dynamic operational parameters. The study also demonstrated the successful application of ANFIS for determining and ranking the impact of various operating parameters on plant’s nitrification performance, which could not be achieved by the conventional spearman correlation due to the non-linearity of the interactions during wastewater treatment. Moreover, this study also represents the first-time amoA gene targeted pyrosequencing of AOB in a full-scale activated sludge is being done. / D

[pt] Esta tese apresenta uma nova metodologia para valoração dinâmica do Capital Intelectual, aplicada ao Capital Humano. Trata-se de oferecer, ao tomador de decisão, uma ferramenta capaz de calcular e comparar o retorno do investimento em ativos intangíveis, como ocorre com outros ativos tangíveis. Através da metodologia proposta, denominada KVA-ACHE, é possível estimar a quantidade potencial de conhecimento humano, utilizado na geração do resultado financeiro da empresa. Essa metodologia também permite medir variações de desempenho nos processos-chave que compõem a cadeia de valor da empresa e o impacto do investimento em educação em um determinado processo. O método KVA-ACHE é composto de cinco módulos, que são executados em três fases. Na primeira fase se avalia a empresa de forma agregada, segundo seu modelo estratégico e, na segunda fase, avalia-se a quantidade de conhecimento potencial e disponível, associado a cada processo-chave. A terceira fase é aplicado o método KVA e obtido o indicador de desempenho ROI. Ao final da sua aplicação, essa metodologia permite: identificar os processos que estão drenando resultado da empresa, através da observação de indicador financeiro adaptado, como o ROIK (Return on Investment on Knowledg), identificar a necessidade individualizada de treinamento para se atingir o máximo de desempenho em um determinado processochave; analisar o impacto percebido em termos percentuais do investimento em educação, realizado em determinado processo-chave; e, finalmente, dar uma visão sobre os recursos de conhecimentos e habilidades disponíveis na equipe de colaboradores, os quais poderão ser aproveitados na avaliação de novos negócios e desafios para empresa. A principal inovação dessa metodologia está no fato de se utilizar a Teoria dos Conjuntos Fuzzy e de Sistemas de Inferência Fuzzy - SIF para transformar conceitos relacionados à disponibilidade e ao uso de conhecimento humano em valores que, dessa forma, permitem a comparação de ativos intangíveis com ativos tangíveis. / [en] This thesis presents a new methodology for dynamic valuation of Intellectual Capital, applied to the Human Capital. It offers, to the decision-maker, a computational tool able to quote and compare the return on investment in intangible assets, as with tangible assets. Through the proposed methodology, called KVAACHE, it is possible to estimate the potential amount of human knowledge, used in generating the company’s financial results. This approach also allows the measurement of variations in performance in the key processes that make up the value chain of the company and the impact of investment in education in a given process. The method KVA-ACHE is composed of five modules, which are executed in three phases. The first phase evaluates the company on an aggregate basis, according to its strategic model, and, in the second phase, the amount of potential and available knowledge, associated with each key process, is evaluated. The third phase applies KVA method. This methodology allows: the identification of the processes that are draining the company’s income by looking at the adapted financial indicators, such as ROIK (Return on Investment on Knowledge); the individualized need for training to achieve maximum performance in a particular key process; the analysis of the impact noticed in terms of percentage of the investment in education, held in a certain key process; and finally, an insight into the resources of knowledge and skills available in the team of collaborators, which may be used in the assessment of new challenges and business to the enterprise. The main innovation of this methodology lies in the use of Fuzzy Set Theory and Fuzzy Inference Systems - FIS to transform concepts related to the availability and use of human knowledge into values, and thus allow the comparison of intangible assets with tangible assets.

Les données manquantes constituent un challenge commun en reconnaissance de forme et traitement de signal. Une grande partie des techniques actuelles de ces domaines ne gère pas l'absence de données et devient inutilisable face à des jeux incomplets. L'absence de données conduit aussi à une perte d'information, des difficultés à interpréter correctement le reste des données présentes et des résultats biaisés notamment avec de larges sous-séquences absentes. Ainsi, ce travail de thèse se focalise sur la complétion de larges séquences manquantes dans les séries monovariées puis multivariées peu ou faiblement corrélées. Un premier axe de travail a été une recherche d'une requête similaire à la fenêtre englobant (avant/après) le trou. Cette approche est basée sur une comparaison de signaux à partir d'un algorithme d'extraction de caractéristiques géométriques (formes) et d'une mesure d'appariement élastique (DTW - Dynamic Time Warping). Un package R CRAN a été développé, DTWBI pour la complétion de série monovariée et DTWUMI pour des séries multidimensionnelles dont les signaux sont non ou faiblement corrélés. Ces deux approches ont été comparées aux approches classiques et récentes de la littérature et ont montré leur faculté de respecter la forme et la dynamique du signal. Concernant les signaux peu ou pas corrélés, un package DTWUMI a aussi été développé. Le second axe a été de construire une similarité floue capable de prender en compte les incertitudes de formes et d'amplitude du signal. Le système FSMUMI proposé est basé sur une combinaison floue de similarités classiques et un ensemble de règles floues. Ces approches ont été appliquées à des données marines et météorologiques dans plusieurs contextes : classification supervisée de cytogrammes phytoplanctoniques, segmentation non supervisée en états environnementaux d'un jeu de 19 capteurs issus d'une station marine MAREL CARNOT en France et la prédiction météorologique de données collectées au Vietnam. / Missing data are a prevalent problem in many domains of pattern recognition and signal processing. Most of the existing techniques in the literature suffer from one major drawback, which is their inability to process incomplete datasets. Missing data produce a loss of information and thus yield inaccurate data interpretation, biased results or unreliable analysis, especially for large missing sub-sequence(s). So, this thesis focuses on dealing with large consecutive missing values in univariate and low/un-correlated multivariate time series. We begin by investigating an imputation method to overcome these issues in univariate time series. This approach is based on the combination of shape-feature extraction algorithm and Dynamic Time Warping method. A new R-package, namely DTWBI, is then developed. In the following work, the DTWBI approach is extended to complete large successive missing data in low/un-correlated multivariate time series (called DTWUMI) and a DTWUMI R-package is also established. The key of these two proposed methods is that using the elastic matching to retrieving similar values in the series before and/or after the missing values. This optimizes as much as possible the dynamics and shape of knowledge data, and while applying the shape-feature extraction algorithm allows to reduce the computing time. Successively, we introduce a new method for filling large successive missing values in low/un-correlated multivariate time series, namely FSMUMI, which enables to manage a high level of uncertainty. In this way, we propose to use a novel fuzzy grades of basic similarity measures and fuzzy logic rules. Finally, we employ the DTWBI to (i) complete the MAREL Carnot dataset and then we perform a detection of rare/extreme events in this database (ii) forecast various meteorological univariate time series collected in Vietnam

[pt] Uma forma de avaliar a qualidade da água e a qualidade ambiental de um reservatório para monitoramento futuro é listar e analisar as concentrações de tudo o que a mesma tem. Tal lista poderia ser tão longa quanto o número de elementos analisados, podendo ir de 20 e poucos componentes comuns a centenas. É assim que vários índices de qualidade têm sido propostos por serem capazes de sintetizar o maior número destes parâmetros de qualidade em um único valor de fácil interpretação. Não obstante, uma vez que a maior parte dos índices formulados serem para águas moventes, os mesmos têm pouca utilidade para lagos e reservatórios. Lagos e reservatórios são geralmente avaliados e classificados com base em índices de estado trófico e em análises de suas composições químicas. Porém, um índice de estado trófico não tem a mesma representatividade de um índice de qualidade, visto que o termo qualidade sugere uma avaliação subjetiva, importante ressaltar essa distinção de conceitos. Excelente ou pobre, a referência de qualidade da água depende do seu uso e das atitudes locais das pessoas. A definição de estado trófico e seu índice correspondente deveriam permanecer neutros a tais julgamentos subjetivos, mantendo-se numa estrutura dentro da qual podem ser feitas várias avaliações da qualidade da água. Dessa forma, no presente trabalho, criou-se um modelo de avaliação da qualidade da água e da qualidade ambiental para um reservatório tropical oligo-mesotrófico (reservatório das Lajes) capaz de representar em uma escala numérica as gradações nos níveis de qualidade, além de levar em consideração a subjetividade implícita no conceito de qualidade. A subjetividade da avaliação em discussão motivou o emprego da Lógica Fuzzy, metodologia capaz de representar, de forma mais eficiente e clara, os limites dos intervalos de variação dos parâmetros de qualidade para um conjunto de categorias subjetivas, quando esses limites não são bem definidos ou são imprecisos. Assim, foi desenvolvida uma ferramenta computacional baseada em Sistemas de Inferência Fuzzy que avalia automaticamente a qualidade em função de variáveis físicas, químicas e biológicas do reservatório. O referido modelo foi desenvolvido com base no conhecimento de especialistas em qualidade de água e qualidade ambiental do Centro de Ciências Biológicas e da Saúde da Universidade Federal do Estado do Rio de Janeiro (UNIRIO) e do Departamento de Biologia Animal da Universidade Federal Rural do Rio de Janeiro (UFRRJ). O modelo foi avaliado utilizando dados de coleta do reservatório das Lajes coletados no ano 2005, 2008 e 2009. / [en] There are many approaches to monitor the water and environmental qualities of a reservoir. One approach is to list and analyze the concentration of chemicals and physical characteristics that the amount of water it contains. Such a list could be as long as the number of elements analyzed, from a few common components to hundreds. Thus, many indices have been proposed since they are able to synthesize as many of these quality parameters into a single value for an easy interpretation. However, majority of the indices are formulated to evaluate lentic ecosystems, they have little use for lakes and reservoirs. Lakes and reservoirs are generally evaluated and classified based on trophic state indices and chemical composition analysis. Nevertheless, a trophic state index does not have the same representativeness of a quality index. The term quality implies a subjective judgment that is best kept separate from the concept of trophic state. Excellent or poor, water quality depends on the use of that water and the local attitudes of the people. The definition of trophic state and its corresponding index should remain neutral to these subjective judgments, remaining a framework within which various evaluations of water quality may be made. Accordingly, in today s world of technology and advancement there exists a unique model to evaluate water quality and environmental quality for a tropical oligo-mesotrophic reservoir which is located and known as the reservoir of Lajes in the State of Rio de Janeiro, Brazil. This model is capable of representing quality levels on a numerical scale gradation, and also takes into consideration the subjectivity implicit in the concept of quality. The subjectivity, implicit in the concept of quality, motivated the use of fuzzy logic. This is a methodology to represent more efficiently the limits of ranges of quality parameters for a set of subjective categories, when these limits are not well defined or are inaccurate. As a result, we developed a computational tool based on a Fuzzy Inference System that automatically assesses the quality in terms of the physical, chemical and biological characteristics of the reservoir. The model was developed based on the knowledge of experts on water quality and environmental quality from the Biological Sciences and Health Center of Universidade Federal do Estado do Rio de Janeiro (UNIRIO) and from the Department of Animal Biology of the Universidade Federal Rural do Rio de Janeiro (UFRRJ). The model was evaluated with data from the Lajes reservoir during the years 2005, 2008 and 2009.