No description available.

The fuzzy inference system has been tuned and revamped many times over and applied to numerous domains. New and improved techniques have been presented for fuzzification, implication, rule composition and defuzzification, leaving rule aggregation relatively underrepresented. Current FIS aggregation operators are relatively simple and have remained more-or-less unchanged over the years. For many problems, these simple aggregation operators produce intuitive, useful and meaningful results. However, there exists a wide class of problems for which quality aggregation requires nonditivity and exploitation of interactions between rules. Herein, the fuzzy integral, a parametric non-linear aggregation operator, is used to fill this gap. Specifically, recent advancements in extensions of the fuzzy integral to “unrestricted” fuzzy sets, i.e., subnormal and non-convex, makes this now possible. The roles of two extensions, gFI and the NDFI, are explored and demonstrate when and where to apply these aggregations, and present efficient algorithms to approximate their solutions.

During recent years, much focus have been put on replacing time consuming manual mappingand classification tasks with automatic methods, having minimal human interaction. Now it ispossible to quickly classify land cover and terrain features covering large areas to a digital formatand with a high accuracy. This can be achieved using nothing but remote sensing techniques,which provide a far more sustainable process and product. Still, some terrain features do not havean established methodology for high quality automatic mapping.The Scandinavian Mountains contain several terrain features with low passability, such asmires, shrub and stony ground. It would be of interest to anyone passing the land to avoid theseareas. However, they are not sufficiently mapped in current map products.The aim of this thesis was to find a methodology to classify and map these terrain featuresin the Scandinavian Mountains with high accuracy and minimal human interaction, using remotesensing techniques. The study area chosen for the analysis is a large valley and mountain sidesouth-east of the small town Abisko in northern Sweden, which contain clearly visible samplesof the targeted terrain features. The methodology was based on training a Fuzzy Logic classifierusing labeled training samples and descriptors derived from ortophotos, LiDAR data and currentmap products, chosen to separate the classes from each other by their characteristics. Firstly,a set of candidate descriptors were chosen, from which the final descriptors were obtained byimplementing a Fisher score filter. Secondly a Fuzzy Inference System was constructed usinglabeled training data from the descriptors, created by the user. Finally the entire study area wasclassified pixel-by-pixel by using the trained classifier and a majority filter was used to cluster theoutputs. The result was validated by visual inspection, comparison to the current map productsand by constructing Confusion Matrices, both for the training data and validation samples as wellas for the clustered- and non-clustered results.The results showed that / De senaste åren har mycket fokus lagts på att ersätta tidskrävande manuella karterings- och klassificeringsmetodermed automatiserade lösningar med minimal mänsklig inverkan. Det är numeramöjligt att digitalt klassificera marktäcket och terrängföremål över stora områden, snabbt och medhög noggrannhet. Detta med hjälp av enbart fjärranalys, vilket medför en betydligt mer hållbarprocess och slutprodukt. Trots det finns det fortfarande terrängföremål som inte har en etableradmetod för noggrann automatisk kartering.Den skandinaviska fjällkedjan består till stor del av svårpasserade terrängföremål som sankmarker,videsnår och stenig mark. Alla som tar sig fram i terrängen obanat skulle ha nytta av attkunna undvika dessa områden men de är i nuläget inte karterade med önskvärd noggrannhet.Målet med denna analys var att utforma en metod för att klassificera och kartera dessa terrängföremåli Skanderna, med hög noggrannhet och minimal mänsklig inverkan med hjälp avfjärranalys. Valet av testområde för analysen är en större dal och bergssida sydost om Abisko inorra Sverige som innehåller tydliga exemplar av alla berörda terrängföremål. Metoden baseradespå att träna en Fuzzy Logic classifier med manuellt utvald träningsdata och deskriptorer,valda för att bäst separera klasserna utifrån deras karaktärsdrag. Inledningsvis valdes en uppsättningav kandidatdeskriptorer som sedan filtrerades till den slutgiltiga uppsättningen med hjälp avett Fisher score filter. Ett Fuzzy Inference System byggdes och tränades med träningsdata fråndeskriptorerna vilket slutligen användes för att klassificera hela testområdet pixelvis. Det klassificeraderesultatet klustrades därefter med hjälp av ett majoritetsfilter. Resultatet validerades genomvisuell inspektion, jämförelse med befintliga kartprodukter och genom confusion matriser, vilkaberäknades både för träningsdata och valideringsdata samt för det klustrade och icke-klustraderesultatet.Resultatet visade att de svårpasserade terrängföremålen sankmark, videsnår och stenig markkan karteras med hög noggrannhet med hjälp denna metod och att resultaten generellt är tydligtbättre än nuvarande kartprodukter. Däremot kan metoden finjusteras på flera plan för att optimeras.Bland annat genom att implementera deskriptorer för markvattenrörelser och användandeav LiDAR med högre spatial upplösning, samt med ett mer fulltäckande och spritt val av klasser.

A eficiência e a racionalidade energética da iluminação pública têm relevante importância no sistema elétrico, porque contribui para diminuir a necessidade de investimentos na construção de novas fontes geradoras de energia elétrica e nos desperdícios energéticos. Apresenta-se como objetivo deste trabalho de pesquisa o desenvolvimento e aplicação do IDE (índice de desempenho energético), fundamentado no sistema de inferência nebulosa e indicadores de eficiência e racionalidade de uso da energia elétrica. A opção em utilizar a inferência nebulosa deve-se aos fatos de sua capacidade de reproduzir parte do raciocínio humano, e estabelecer relação entre a diversidade de indicadores envolvidos. Para a consecução do sistema de inferência nebulosa, foram definidas como variáveis de entrada: os indicadores de eficiência e racionalidade; o método de inferência foi baseado em regras produzidas por especialista em iluminação pública, e como saída um número real que caracteriza o IDE. Os indicadores de eficiência e racionalidade são divididos em duas classes: globais e específicos. Os indicadores globais são: FP (fator de potência), FC (fator de carga) e FD (fator de demanda). Os indicadores específicos são: FU (fator de utilização), ICA (consumo de energia por área iluminada), IE (intensidade energética) e IL (intensidade de iluminação natural). Para a aplicação deste trabalho, foi selecionada e caracterizada a iluminação pública da Cidade Universitária \"Armando de Salles Oliveira\" da Universidade de São Paulo. Sendo assim, o gestor do sistema de iluminação, a partir do índice desenvolvido neste trabalho, dispõe de condições para avaliar o uso da energia elétrica e, desta forma, elaborar e simular estratégias com o objetivo de economizá-la. / The energy efficiency and rationality of public lighting have great importance in the electrical system, because it contributes to reduce the need for investment in building new sources of power and energy waste. It presented as objective of this work research development and application of IDE (Energy Performance Index), based on the fuzzy inference system and indicators of efficiency and rationality of use of electricity. The option to use the fuzzy inference is due to the facts of his ability to play part of human reasoning, and establish the relationship between indicators of diversity involved. To achieve the fuzzy inference system, it was defined as input variables: the efficiency and rationality indicators; the inference rules-based method was produced by expert in public lighting and as output a real number that characterizes the IDE. Efficiency and rationality indicators are divided into two classes: global and specific. The global indicators are: PF (power factor), FC (load factor) and FD (demand factor). Specific indicators are: FU (utilization factor), ICA (energy consumption per lit area), IE (energy intensity) and IL (daylight intensity). For the application of this work was selected and characterized the public lighting of the University City \"Armando de Salles Oliveira\" the University of São Paulo. Thus, the lighting system manager from the index developed in this work, have conditions to evaluate the use of electricity and thus prepare and simulate strategies in order to save it.

As empresas lidam com grupos de clientes distintos, com requisitos que os diferem entre si, portanto é importante aperfeiçoar o atendimento destes clientes por meio de estratégias da cadeia de suprimentos que sejam diferenciadas para cada grupo. A escola enxuta-ágil, apesar de sugerir formas práticas de avaliação da cadeia de suprimento para a tomada de decisão, não oferece muitas opções para sua segmentação. Por outro lado, a proposta de segmentação da escola do alinhamento dinâmico é mais robusta, entretanto esta escola sofre com excessiva normatização, além da imprecisão inerente a seu processo de avaliação primordialmente qualitativo e de difícil aplicação. Uma alternativa para lidar com a imprecisão relativa ao processo de segmentação é a aplicação da teoria dos conjuntos fuzzy. Nesse contexto, este trabalho tem por objetivo desenvolver um modelo quantitativo que utilize a teoria dos conjuntos fuzzy e, com base em dados de vendas, avalie a(s) cadeia(s) de suprimentos da empresa facilitando esta alcançar o alinhamento dinâmico. Os procedimentos de pesquisa utilizados no trabalho podem ser agrupados em três partes: pesquisa bibliográfica, desenvolvimento do modelo quantitativo axiomático descritivo e ilustração por meio de aplicação prática. O modelo computacional desenvolvido colaborou com a busca do alinhamento dinâmico. Obteve-se a identificação das cadeias de suprimentos que atendem aos grupos de clientes avaliados, fornecendo respostas de forma muito mais rápida que a análise proposta pelos modelos encontrados na literatura. A aplicação em caso real validou o modelo, uma vez que os resultados obtidos mostraram-se coerentes com a realidade apontada pelos especialistas da empresa estudada, indicando possíveis ações para o realinhamento da cadeia de suprimentos. / Companies deal with different customer groups, with requirements that differ between them, so it is important to improve customer service through different supply chain strategies for each group. The Leagile School, while suggesting practical ways of assessing the supply chain for decision-making, does not offer many options for its segmentation. The segmentation proposal of Dynamic Alignment School is more robust, however, this school is excessively normative, besides the vagueness inherent in its evaluation process that is primarily qualitative and difficult to apply. An alternative to deal with imprecision related to the segmentation process is the application of fuzzy set theory. In this context, the objective of this work is to develop a quantitative model that uses the fuzzy set theory and, based on sales data, assess the company\'s supply chain(s), facilitating the achievement of the dynamic alignment. The research procedures applied in the work can be grouped into three parts: bibliographic research, development of the descriptive axiomatic quantitative model, and illustration through practical application. The computational model developed collaborated with the search for dynamic alignment. It was possible to identify the supply chains that serve the client groups evaluated, providing answers faster than the analysis proposed by the models found in the literature. The application in real situation validated the model, since the results obtained were consistent with the reality pointed out by the experts of the company studied, indicating possible actions for the realignment of the supply chain.

A eficiência e a racionalidade energética da iluminação pública têm relevante importância no sistema elétrico, porque contribui para diminuir a necessidade de investimentos na construção de novas fontes geradoras de energia elétrica e nos desperdícios energéticos. Apresenta-se como objetivo deste trabalho de pesquisa o desenvolvimento e aplicação do IDE (índice de desempenho energético), fundamentado no sistema de inferência nebulosa e indicadores de eficiência e racionalidade de uso da energia elétrica. A opção em utilizar a inferência nebulosa deve-se aos fatos de sua capacidade de reproduzir parte do raciocínio humano, e estabelecer relação entre a diversidade de indicadores envolvidos. Para a consecução do sistema de inferência nebulosa, foram definidas como variáveis de entrada: os indicadores de eficiência e racionalidade; o método de inferência foi baseado em regras produzidas por especialista em iluminação pública, e como saída um número real que caracteriza o IDE. Os indicadores de eficiência e racionalidade são divididos em duas classes: globais e específicos. Os indicadores globais são: FP (fator de potência), FC (fator de carga) e FD (fator de demanda). Os indicadores específicos são: FU (fator de utilização), ICA (consumo de energia por área iluminada), IE (intensidade energética) e IL (intensidade de iluminação natural). Para a aplicação deste trabalho, foi selecionada e caracterizada a iluminação pública da Cidade Universitária \"Armando de Salles Oliveira\" da Universidade de São Paulo. Sendo assim, o gestor do sistema de iluminação, a partir do índice desenvolvido neste trabalho, dispõe de condições para avaliar o uso da energia elétrica e, desta forma, elaborar e simular estratégias com o objetivo de economizá-la. / The energy efficiency and rationality of public lighting have great importance in the electrical system, because it contributes to reduce the need for investment in building new sources of power and energy waste. It presented as objective of this work research development and application of IDE (Energy Performance Index), based on the fuzzy inference system and indicators of efficiency and rationality of use of electricity. The option to use the fuzzy inference is due to the facts of his ability to play part of human reasoning, and establish the relationship between indicators of diversity involved. To achieve the fuzzy inference system, it was defined as input variables: the efficiency and rationality indicators; the inference rules-based method was produced by expert in public lighting and as output a real number that characterizes the IDE. Efficiency and rationality indicators are divided into two classes: global and specific. The global indicators are: PF (power factor), FC (load factor) and FD (demand factor). Specific indicators are: FU (utilization factor), ICA (energy consumption per lit area), IE (energy intensity) and IL (daylight intensity). For the application of this work was selected and characterized the public lighting of the University City \"Armando de Salles Oliveira\" the University of São Paulo. Thus, the lighting system manager from the index developed in this work, have conditions to evaluate the use of electricity and thus prepare and simulate strategies in order to save it.

As empresas lidam com grupos de clientes distintos, com requisitos que os diferem entre si, portanto é importante aperfeiçoar o atendimento destes clientes por meio de estratégias da cadeia de suprimentos que sejam diferenciadas para cada grupo. A escola enxuta-ágil, apesar de sugerir formas práticas de avaliação da cadeia de suprimento para a tomada de decisão, não oferece muitas opções para sua segmentação. Por outro lado, a proposta de segmentação da escola do alinhamento dinâmico é mais robusta, entretanto esta escola sofre com excessiva normatização, além da imprecisão inerente a seu processo de avaliação primordialmente qualitativo e de difícil aplicação. Uma alternativa para lidar com a imprecisão relativa ao processo de segmentação é a aplicação da teoria dos conjuntos fuzzy. Nesse contexto, este trabalho tem por objetivo desenvolver um modelo quantitativo que utilize a teoria dos conjuntos fuzzy e, com base em dados de vendas, avalie a(s) cadeia(s) de suprimentos da empresa facilitando esta alcançar o alinhamento dinâmico. Os procedimentos de pesquisa utilizados no trabalho podem ser agrupados em três partes: pesquisa bibliográfica, desenvolvimento do modelo quantitativo axiomático descritivo e ilustração por meio de aplicação prática. O modelo computacional desenvolvido colaborou com a busca do alinhamento dinâmico. Obteve-se a identificação das cadeias de suprimentos que atendem aos grupos de clientes avaliados, fornecendo respostas de forma muito mais rápida que a análise proposta pelos modelos encontrados na literatura. A aplicação em caso real validou o modelo, uma vez que os resultados obtidos mostraram-se coerentes com a realidade apontada pelos especialistas da empresa estudada, indicando possíveis ações para o realinhamento da cadeia de suprimentos. / Companies deal with different customer groups, with requirements that differ between them, so it is important to improve customer service through different supply chain strategies for each group. The Leagile School, while suggesting practical ways of assessing the supply chain for decision-making, does not offer many options for its segmentation. The segmentation proposal of Dynamic Alignment School is more robust, however, this school is excessively normative, besides the vagueness inherent in its evaluation process that is primarily qualitative and difficult to apply. An alternative to deal with imprecision related to the segmentation process is the application of fuzzy set theory. In this context, the objective of this work is to develop a quantitative model that uses the fuzzy set theory and, based on sales data, assess the company\'s supply chain(s), facilitating the achievement of the dynamic alignment. The research procedures applied in the work can be grouped into three parts: bibliographic research, development of the descriptive axiomatic quantitative model, and illustration through practical application. The computational model developed collaborated with the search for dynamic alignment. It was possible to identify the supply chains that serve the client groups evaluated, providing answers faster than the analysis proposed by the models found in the literature. The application in real situation validated the model, since the results obtained were consistent with the reality pointed out by the experts of the company studied, indicating possible actions for the realignment of the supply chain.

Artificial intelligence techniques have been widely used for prediction in various areas of sciences and engineering. In the thesis, applications of AI techniques are studied to predict the dilution of industrial outfall discharges. The discharge of industrial effluents from the outfall systems is broadly divided into two categories on the basis of density. The effluent with density higher than the water receiving will sink and called as negatively buoyant jet. The effluent with density lower than the receiving water will rise and called as positively buoyant jet. The effluent discharge in the water body creates major environmental threats. In this work, negatively buoyant jet is considered. For the study, ANFIS model is taken into consideration and incorporated with algorithms such as GA, PSO and FFA to determine the suitable model for the discharge prediction. The training and test dataset for the ANFIS-type models are obtained by simulating the jet using the realizable k-ε turbulence model over a wide range of Froude numbers i.e. from 5 to 60 and discharge angles from 20 to 72.5 degrees employing OpenFOAM platform. Froude number and angles are taken as input parameters for the ANFIS-type models. The output parameters were peak salinity (Sm), return salinity (Sr), return point in x direction (xr) and peak salinity coordinates in x and y directions (xm and ym). Multivariate regression analysis has also been done to verify the linearity of the data using the same input and output parameters. To evaluate the performance of ANFIS, ANFIS-GA, ANFIS-PSO, ANFIS-FFA and multivariate regression model, some statistical parameters such as coefficient of determination (R2), root mean squared error (RMSE), mean absolute error (MAE) and average absolute deviation in percentage are determined. It has been observed that ANFIS-PSO is better in predicting the discharge characteristics.

Precision agriculture requires detailed and timely information about field condition. In less than the short flight time a UAV (Unmanned Aerial Vehicle) can provide, an entire field can be scanned at the highest allowed altitude. The resulting NDVI (Normalized Difference Vegetation Index) imagery can then be used to classify each point in the field using a FIS (Fuzzy Inference System). This identifies areas that are expected to be similar, but only closer inspection can quantify and diagnose crop properties. In the remaining flight time, the goal is to scout a set of representative points maximizing the quality of actionable information about the field condition. This quality is defined by two new metrics: the average sampling probability (ASP) and the total scouting luminance (TSL). In simulations, the scouting flight plan created using a GA (Genetic Algorithm) significantly outperformed plans created by grid sampling or human experts, obtaining over 99% ASP while improving TSL by an average of 285%.

Battery energy management plays a crucial role in fuel economy improvement of charge-sustaining parallel hybrid electric vehicles. Currently available control strategies consider battery state of charge (SOC) and driver’s request through the pedal input in decision-making. This method does not achieve an optimal performance for saving fuel or maintaining appropriate SOC level, especially during the operation in extreme driving conditions or hilly terrain. The objective of this thesis is to develop a control algorithm using forthcoming traffic condition and road elevation, which could be fed from navigation systems. This would enable the controller to predict potential of regenerative charging to capture cost-free energy and intentionally depleting battery energy to assist an engine at high power demand. The starting point for this research is the modelling of a small sport-utility vehicle by the analysis of the vehicles currently available in the market. The result of the analysis is used in order to establish a generic mild hybrid powertrain model, which is subsequently examined to compare the performance of controllers. A baseline is established with a conventional powertrain equipped with a spark ignition direct injection engine and a continuously variable transmission. Hybridisation of this vehicle with an integrated starter alternator and a traditional rule-based control strategy is presented. Parameter optimisation in four standard driving cycles is explained, followed by a detailed energy flow analysis. An additional potential improvement is presented by dynamic programming (DP), which shows a benefit of a predictive control. Based on these results, a predictive control algorithm using fuzzy logic is introduced. The main tools of the controller design are the DP, adaptive-network-based fuzzy inference system with subtractive clustering and design of experiment. Using a quasi-static backward simulation model, the performance of the controller is compared with the result from the instantaneous control and the DP. The focus is fuel saving and SOC control at the end of journeys, especially in aggressive driving conditions and a hilly road. The controller shows a good potential to improve fuel economy and tight SOC control in long journey and hilly terrain. Fuel economy improvement and SOC correction are close to the optimal solution by the DP, especially in long trips on steep road where there is a large gap between the baseline controller and the DP. However, there is little benefit in short trips and flat road. It is caused by the low improvement margin of the mild hybrid powertrain and the limited future journey information. To provide a further step to implementation, a software-in-the-loop simulation model is developed. A fully dynamic model of the powertrain and the control algorithm are implemented in AMESim-Simulink co-simulation environment. This shows small deterioration of the control performance by driver’s pedal action, powertrain dynamics and limited computational precision on the controller performance.