Dissertação PPG.EGPSA
URI permanente para esta coleçãohttps://rigalileo.itegam.org.br/handle/123456789/3
Navegar
Item Aplicação da lógica fuzzy para tomadas de decisões nos critérios de rateio e distribuição de custos industriais(Instituto de Tecnologia e Educação Galileo da Amazônia, 2023-04-11) NOVO, Breno Tello; NASCIMENTO, Manoel Henrique Reis; http://lattes.cnpq.br/0850846128967798Industries are increasingly specializing in the financial and production sector, aided by general accounting and, especially, cost accounting. Even increasing the degree of complexity of specialized employees, cost accounting in relation to its apportionment criteria is always a challenge. Companies find it very difficult to correctly determine the unit cost of the product or service being offered. And it is precisely at this moment that cost accounting proves to be useful and indispensable. Cost apportionment is one of the branches of industrial accounting and it is a subject that seems to be simple to understand, however, it becomes more complex during your daily practices. This work aims to develop a classification model for decision making based on Fuzzy Logic for diagnosing production performance with a focus on financial improvement based on the optimization of cost apportionment. In this context, the work is justified by pointing out a new perspective of analysis through production and financial indicators implemented in a Fuzzy interference model with the objective of optimizing the apportionment criteria and proposing financial improvements. The Methodological Process of the research was developed in three phases: 1. Identification of Economic and Production Indicators; 2. Modeling of the Fuzzy “Inference” System; 3. Proposed Model Experiment. Each phase consists of three stages until reaching the results obtained from the research. The proposed Fuzzy system was able to show the different performance results when simulated with the different conditions of the input variables and which the projected performance classification could be defined. The model resulted in 576 inference rules for analysis. With a bad EGE, it is difficult to properly monitor production efficiency to a satisfactory degree, but you can maintain a standard production pace due to the good results of other indicators. In this way, the Fuzzy system helps to guide us in which costing method we should adapt the worked product so that it can generate profitability within the industry and better profit margin, allowing a more critical analysis in internal decision-making.Item Integração logística entre a Zona Franca de Manaus (ZFM) e a Venezuela: avaliação do modal por intermédio da lógica fuzzy para escoamento da produção do setor eletroeletrônico. Estudo de caso em um hospital do Amazonas(Instituto de Tecnologia e Educação Galileo da Amazônia, 2024-05-29) MIRANDA, Allan Cerdeira; NASCIMENTO, Manoel Henrique Reis; http://lattes.cnpq.br/0850846128967798The Logistics Integration between the Manaus Free Trade Zone (ZFM) and Venezuela regarding the flow of production in the electrical and electronic sector, has specificities in its commercial activity. Competition and the accelerated increase in consumption form a more competitive environment, where the ability to meet fluctuating demand in a timely manner emerges as a central component of competitive advantage. It is routine to say that the biggest deficiency of companies located in the Amazon Region is logistics, notably infrastructure and transport, which in addition to hindering the region's economic progress remain a difficulty for the work of businesspeople and the industry itself, when it comes to importing and export your products. The general objective of this dissertation was to develop a Fuzzy inference model to evaluate the most viable modal for integration between the Manaus Free Trade Zone (ZFM) and Venezuela in the flow of production in the electronics sector. The Methodological Process was developed in three phases: 1. Identification of indicators for Assessment of Available Modals; 2. Modeling of the Fuzzy “Inference” System; 3. Experiment of the Proposed Model, with its respective stages: Phase 1 (definition of inference levels of indicators), Phase 2 (Development of Fuzzy Sets, Development of “Inference” Rules and Simulation in MatlabR2013 software), Phase 3 (Compilation of the Indicator Aggregation Algorithm, 3D Results Simulation and Analysis of the Results Obtained). The results obtained with the proposed model were satisfactory in the analysis of the modal performance classifications, it was possible to identify the most relevant variables for the flow of production in the electronics sector between the Manaus Free Trade Zone and Venezuela. By inserting data into Fuzzy Logic, the model provided crucial information to improve the decision-making process, optimizing the cost of each mode used in the region.Item Metodologia fuzzy aplicada na avaliação da qualidade dos serviços hospitalares. Estudo de caso em um hospital do Amazonas(Instituto de Tecnologia e Educação Galileo da Amazônia, 2023-06-05) CESCONETO, Fernando da Silva; NASCIMENTO, Manoel Henrique Reis; http://lattes.cnpq.br/0850846128967798There is currently an important challenge for hospital companies, which is to offer their services with the highest quality to their customers. And meeting this demand requires more efforts from public or private organizations to provide quality services offered to customers who are more demanding and interested not only in cost, but in the quality of the product or service offered. Therefore, if you guarantee in the market, you have an unknown, to evaluate the quality of services to monitor the quality of service according to the expectations of your customers, thereby creating competitive advantages. In this context, the private hospital in Manaus is with an interest in measuring its quality, placing itself as an object of study, in order to know: the quality of the services offered by the Hospital in the view of the clients, identifying the relevant positive and negative aspects for that the Hospital can act more precisely on the points that allow it to achieve excellence in customer service and acquire more competitiveness. This reality dictates the need to create effective methods to meet the demand for quality in hospital services. In response, the purpose of this study arises to create a quality assessment model using the Fuzzy inference system, based on the studies by Parasuraman, Zeithaml and Berry, in 1994, who developed the SERVQUAL scale, an efficient instrument to assess the quality of services with evaluative diagnosis of quality that are important and followed until today. For this, a model was developed to evaluate the quality of private hospital services in Manaus. The questionnaire was used as data collection techniques, as determined by the SERVQUAL scale, which generated variables that were used for Fuzzy Inference in the Matlab R16 Student software. The results made it possible to evaluate the quality of customer service, which reached an index of 82.7%, thus identifying the level of customer satisfaction, highlighting the negative points, essential information for managers to implement appropriate improvements.Item Modelo híbrido com redes neurais artificiais e algoritmos evolucionários para otimização do consumo de combustível em embarcações que utilizam motor de combustão interna a diesel(Instituto de Tecnologia e Educação Galileo da Amazônia, 2021-07-27) SIQUEIRA JUNIOR, Paulo Oliveira; NASCIMENTO, Manoel Henrique ReisThe waterway transport is the main means of locomotion in the North Region, feeding cities through boats, speedboats, ships and ferries with the transport of goods and/or passengers. However, one of the problems of this modality of transport is the cost of supply, considering that the lack of technologies/resources that allow or facilitate a strategic vision of the business is a reality. The flow of passenger transport concentrates an average turnover of 9 million people, while the cargo transport with approximately 3 million, both distributed throughout the northern region. This fact characterizes a considerable demand in the water transportation sector, bringing to light the perspective of this research to study methods of analysis and support for decision making on the basis of fuel consumption. This dissertation aims to present the results about the development of an optimization model of fuel consumption considering the optimal speed for small vessels that operate on a regular basis in the Manaus River Port. In view of this, the research meets the objectives of mapping the variables related to the specifications of the vessel and engine to be analyzed, present the methods and results about the development of the computational hybrid model for optimization of fuel consumption when considering as a parameter of regulation the optimal speed for minimizing the predictor variable and the distance of the projected path for 3 scenarios: Manaus to Itacoatiara, Manaus to Barcelos and Manaus to Parintins, determine by statistical error analysis the best model of Artificial Neural Network (ANN) when considering number of neurons, hidden layers, activation functions (hyperbolic Tangent, Sigmoid and Linear) and training algorithm being the latter 12 possibilities each with different objectives and convergence strategies, To test the hybrid model analyzing the performance of 3 optimization algorithms (Particle Swarm, Genetic Algorithm and Simulated Annealing) as a function of computational cost and error rate in each generation of elites, and finally, to present the simulation results of the 3 scenarios mentioned above when using the hybrid model with the winning algorithm as a function of the requirements mentioned above. To analyze the results provided by the simulations, scenarios and tests for the acquisition of thebest models, the statistical techniques of Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Normalized Root Mean Squared Error (NRMSE) and Mean Absolute Percentage Error (MAPE) were used, the data regarding the vessel were acquired through meetings and interviews with experts (vessel owner) to formalize a specific database for the study delimited in this dissertation, 12 training algorithms were used to choose the best ANN, according to the results the Levenberg-Marquardt presented 100% correlation between the output variables and the Particle Swarm obtained the lowest computational cost in relation to the others proving the effectiveness of the computational hybrid model.Item Modelo híbrido utilizando holt-winters e rede neural não linear autoregressiva com entradas exógenas (narx) para previsão da velocidade do vento(Instituto de Tecnologia e Educação Galileo da Amazônia, 2021-07-27) PARENTE, Ricardo Silva; ALENCAR, David Barbosa de; http://lattes.cnpq.br/4890967546423188The wind energy matrix is gradually increasing in recent years and its importance for the renewable energy industry is increasingly linked to the benefits in relation to the environment, with this growing energy matrix the research around the wind power generation is also increasing, and one of the strands is the wind speed prediction, because with this it is possible to predict the wind power generation and decrease the error rate in decision making in the industry of electricity generation through wind power matrix. Considering the problem of decision making and the unpredictability of wind speed, this paper aims to develop a hybrid model for wind speed prediction and consequently wind power generation, based on HoltWinters Exponential Smoothing and Nonlinear Auto-Regressive Neural Network with Exogenous Inputs (NARX). In the materials and methods, the database of the SONDA project (System of National Organization of Environmental Data) organized by INPE (National Institute for Space Research) was used, in which it was chosen to use the anemometric data from the station of Brasilia - BRB and Petrolina - PTR, where data from the years February 2005 to March 2019 of the BRB station were used for training, validation and testing, and from January 2006 to December 2015 of the PTR station for simulations of the HW, NARX and proposed model. The results obtained with the proposed hybrid HW-NARX model were compared with the HW and NARX seasonal time series forecasting algorithms, in which the proposed model was able to achieve better performance and predictability results than HW and NARX for the ultra-short-term, medium-term, and long-term time horizons.Item Redes neurais artificiais para predição da geração de acetaldeído na resina pet no processo de injeção de pré-formas de embalagens plásticas(Instituto de Tecnologia e Educação Galileo da Amazônia, 2021-09-21) NASCIMENTO, Mauro Reis; ALENCAR, David Barbosa deThe industrial production of preforms for the manufacture of PET bottles, during the plastic injection process, is essential to regulate the temperature of the PET resin drying Silo, to control the generation of Acetaldehyde (ACH), which in high concentrations alters the flavor of carbonated or non-carbonated beverages, giving a citrus flavor to the beverage and casting doubt on the quality of packaged products. In this work, several configurations of Artificial Neural Networks (ANN's) for the Feedforward type are simulated in the specification of an ANN model to predict the formation of Acetaldehyde from the evaluation of the parameters of the PET packaging preform manufacturing process, generating information to support decision-making on optimal silo temperature control in PET resin drying, enabling specialists to make the necessary regulation decisions to lower ACH levels. The materials and methods were applied according to the manufacturer's characteristics on the moisture in the grain of the PET resin, which may contain between 50 ppm and 100 ppm of ACH, and for the analysis of the methods, data were collected, according to the temperatures and times of residence used in the blow injection process in the manufacture of the bottle preform, the generation of ACH from the PET bottle after the solid post-condensation step reached residual ACH levels lower than (3-4) ppm, as per the desired specification, reaching levels below 1 ppm. The results were found through simulations of Computational Intelligence (CI) techniques applied by ANNs, where they enabled the prediction of ACH levels generated in the plastic injection process of the preform of bottle packaging, allowing an effective management of the production parameters, helping in strategic decision making regarding the use of temperature control during the drying process of PET resin.Item Sistema fuzzy para avaliação do grau de aptidão de profissionais das áreas de gestão(Instituto de Tecnologia e Educação Galileo da Amazônia, 2024-07-30) LEITE, Lourdes Daniele Câmara; NASCIMENTO, Manoel Henrique ReisCompanies are increasingly specializing in the Human Resources sector, especially in the area of recruitment and selection of people. This work developed a fuzzy inference model to evaluate the competencies of operational level managers. Through multiple qualitative criteria, the model was designed to be used by the Human Resources sector of organizations, helping to determine if the candidate's profile fits the requirements of the position. The model was tested and resulted in 27 inference rules, offering an effective way to assess candidates' competencies during the recruitment and selection process.