>Magister Scientiae - MSc / This study has been conducted to accurately determine fluid saturation within Fula sub-basin reservoirs which is located at the Southern part of the Republic of Sudan. The area is regarded as Shaly Sand Reservoirs. Four deferent shaly sand lithofacies (A, B, C, D) have been identified. Using method based on the Artificial Neural Networks (ANN), the core surrounding facies, within Fula reservoirs were identified. An average shale volume of 0.126 within the studied reservoirs was determined using gamma ray and resistivity logs. While average porosity of 26.7% within the reservoirs was determined using density log and the average core grain density. An average water resistivity of 0.8 Ohm-m was estimated using Pickett plot method. While formation temperature was estimated using the gradient that constrained between surface and bottom hole temperature. Water saturation was determined using Archie model and four shaly sand empirical models, the calculation was constrained within each facies zone to specify a model for each facies, and another approach was used to obtain the water saturation based on Artificial Neural Networks. The net pay was identified for each reservoir by applying cut-offs on permeability 5 mD, porosity 16%, shale volume 0.33, and water saturation 0.65. The gross thickness of the reservoirs ranges from 7.62m to 19.85m and net pay intervals from 4.877m to 19.202m. The study succeeded in establishing water saturation model for the Fula sub-basin based on neural networking which was very consistent with the core data, and hence has been used for net pay determination.

Táto diplomová práca sa zaoberá klasifikáciou kovov pomocou spektroskopie laserom indukovanej plazmy (LIBS) a chemometrických metód. Práca poskytuje prehľad o štúdiách na danú tému. Sú vybrané tri široko používané chemometrické klasifikačné metódy: "Soft Independent Modeling of Class Analogy" (SIMCA), "Partial Least Squares Discriminant Analysis" (PLS-DA) a variácia umelých neurónových sietí (ANN), "Feedforward Multilayer Perceptron". Rôzne prístupy k prieskumovej analýze su tiež preskúmané. Metódy sú stručne opísané. Následne sú klasifikátory experimentálne porovnané.

En esta tesis se presenta la aplicación de redes neuronales artificiales (ANNs) para modelar dos variables de gran importancia en la ingeniería del riego: la evapotranspiración de referencia y las pérdidas de carga localizadas provocadas por los emisores integrados. Por una parte, se ha propuesto un modelo ANN para la predicción de las pérdidas de presión ocasionadas por la inserción de emisores integrados en los laterales de riego localizado, lo que nunca se ha llevado a cabo mediante redes neuronales. Por otro lado, se ha analizado la validez de un modelo ANN de 4 inputs existente para predicción de ETo en distintos contextos continentales de la Comunidad Valenciana y se ha planteado un nuevo modelo ANN de 6 inputs para mejorar el rendimiento del anterior. Para llevar a cabo dichos estudios, se ha recurrido al uso de perceptrones multinivel (MLP) sometidos al algoritmo Levenberg Marquardt. En los tres casos, se analizaron redes con múltiples configuraciones y se repitió el proceso de entrenamiento de cada red un número variable de veces para compensar el efecto derivado de la asignación inicial aleatoria de pesos en dicho proceso. Asimismo, en los tres problemas abordados se llevaron a cabo distintas estrategias en la asignación de los datos disponibles a los conjuntos de entrenamiento, validación cruzada y test. A diferencia de los modelos estadísticos existentes, el modelo ANN propuesto para predicción de pérdidas de carga localizadas posee indicadores de rendimiento referidos a un set de test independiente, lo que ha permitido evaluar su potencial real de generalización. Para diferentes combinaciones de validación cruzada, con datos al menos de tres emisores, se obtuvieron valores medios del performance index por encima de 0.85. En cuanto a los modelos de predicción de ETo, el rendimiento del modelo existente de 4 inputs depende del grado de oscilación térmica del contexto continental en que se utilice y su validez fuera de la sede de entrenamiento es muy lim / Martí Pérez, PC. (2009). Aplicación de redes neuronales artificiales para predicción de variables en ingeniería del riego: evapotranspiración de referencia y pérdidas de carga localizadas en emisores integrados [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/64909 / Palancia

Coal gasification stripped gas liquor (CGSGL) wastewater contains large quantities of complex organic and inorganic pollutants which include phenols, ammonia, hydantoins, furans, indoles, pyridines, phthalates and other monocyclic and polycyclic nitrogen-containing aromatics, as well as oxygen- and sulphur-containing heterocyclic compounds. The performance of most conventional aerobic systems for CGSGL wastewater is inadequate in reducing pollutants contributing to chemical oxygen demand (COD), phenols and ammonia due to the presence of toxic and inhibitory organic compounds. There is an ever-increasing scarcity of freshwater in South Africa, thus reclamation of wastewater for recycling is growing rapidly and the demand for higher effluent quality before being discharged or reused is also increasing. The selection of hybrid fixed-film bioreactor (HFFBR) systems in the detoxification of a complex mixture of compounds such as those found in CGSGL has not been investigated. Thus, the objective of this study was to investigate the detoxification of the CGSGL in a H-FFBR bioaugmented with a mixed-culture inoculum containing Pseudomonas putida, Pseudomonas plecoglossicida, Rhodococcus erythropolis, Rhodococcus qingshengii, Enterobacter cloacae, Enterobacter asburiae strains of bacteria, as well as the seaweed (Silvetia siliquosa) and diatoms. The results indicated a 45% and 79% reduction in COD and phenols, respectively, without bioaugmentation. The reduction in COD increased by 8% with inoculum PA1, 13% with inoculum PA2 and 7% with inoculum PA3. Inoculum PA1 was a blend of Pseudomonas, Enterobacter and Rhodococcus strains, inoculum PA2 was a blend of Pseudomonas putida iistrains and inoculum PA3 was a blend of Pseudomonas putida and Pseudomonas plecoglossicida strains. The results also indicated that a 70% carrier fill formed a dense biofilm, a 50% carrier fill formed a rippling biofilm and a 30% carrier fill formed a porous biofilm. The autotrophic nitrifying bacteria were out-competed by the heterotrophic bacteria of the genera Thauera, Pseudaminobacter, Pseudomonas and Diaphorobacter. Metagenomic sequencing data also indicated significant dissimilarities between the biofilm, suspended biomass, effluent and feed microbial populations. A large population (20% to 30%) of unclassified bacteria were also present, indicating the presence of novel bacteria that may play an important role in the treatment of the CGSGL wastewater. The artificial neural network (ANN) model developed in this study is a novel virtual tool for the prediction of COD and phenol removal from CGSGL wastewater treated in a bioaugmented H-FFBR. Knowledge extraction from the trained ANN model showed that significant nonlinearities exist between the H-FFBR operational parameters and the removal of COD and phenol. The predictive model thus increases knowledge of the process inputs and outputs and thus facilitates process control and optimisation to meet more stringent effluent discharge requirements. / Thesis (PhD)--University of Pretoria, 2017. / Chemical Engineering / PhD / Unrestricted

Orientador: Carolina dos Santos Batista Bonini / Resumo: Os solos sob um manejo inadequado, têm suas qualidades físicas, químicas e biológicas afetadas negativamente, dando origem a sua degradação. No estado de São Paulo, grande parte das pastagens estão degradadas e/ou em degradação. Entender como um funciona um solo degradado e sua resiliência e iniciar seu processo de restauração, são fundamentais para desenvolver técnicas de manejo adequado do solo. Inúmeras técnicas estão sendo utilizadas para recuperação de solo degradado, descobrir e detalhar os índices físicos do solo ajuda em como proceder, e com qual técnica de recuperação utilizar; visando isso, este projeto teve por objetivo desenvolver um programa interativo (analisar e classificar) com a utilização das redes neurais artificiais (RNA) para estimar os níveis de recuperação do solo (recuperado (R), parcialmente recuperado (PR) e não recuperado (NR) em função dos atributos físicos e comparar com os dados obtidos via estatística convencional. O experimento foi realizado na Agência Paulista de Tecnologias dos Agronegócios – APTA do Extremo Oeste, no município de Andradina/SP no período de 2015 a 2017, em solo classificado como Argissolo Vermelho Amarelo cultivado com pastagem de Urochloa, com diferentes formas de introdução de Estilosantes cv. Campo Grande (Stylosanthes capitata e S. macrocephala). Os atributos do solo estudados foram: densidade do solo, porosidade do solo (macroporosidade e microporosidade), resistência mecânica a penetração, infiltração de água no solo e ... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Soils under inadequate management have their physical, chemical and biological qualities negatively affected, giving rise to their degradation. In the state of São Paulo, most of the pastures are degraded and / or in degradation. Understanding how a degraded soil and its resilience works and starting its restoration process are essential to develop proper soil management techniques. Countless techniques are being used to recover degraded soil, discovering and detailing the physical indexes of the soil helps in how to proceed, and with which recovery technique to use; with this in mind, this project has developed an interactive program (analyze and classify) using artificial neural networks (ANN) to estimate soil recovery levels (recovered (R), partially recovered (PR) and not recovered ( NR) as a function of physical attributes and compare with data obtained using conventional statistics.The experiment was carried out at the São Paulo Agribusiness Technologies Agency - APTA in the Far West, in the city of Andradina / SP from 2015 to 2017, on classified soil as Red Yellow Argisol cultivated on Urochloa decumbens pasture in recovery since 2012, with different ways of introducing Estiloantes cv. Campo Grande (Stylosanthes capitata and S. macrocephala). The studied soil attributes are: soil density, soil porosity (macroporosity and microporosity), mechanical resistance to penetration, water infiltration in the soil and weighted average diameter, in soil layers: 0-10; 0.10-0.20 an... (Complete abstract click electronic access below) / Mestre

No description available.

Anxiety is becoming more and more common, seeking help to evaluate your anxiety canfirst of all take a long time, secondly, many of the tests are self-report assessments that could cause incorrect results. It has been shown there are several voice characteristics that are affected in people with anxiety. Knowing this, we got the idea that an algorithm can be developed to classify the amount of anxiety based on a person's voice. Our goal is that the developed algorithm can be used in collaboration with today's evaluation methods to increase the validity of anxiety evaluation. The algorithm would, in our opinion, give a more objective result than self-report assessments. In this thesis we answer questions such as “Is it possible toclassify anxiety based on a speech recording?”, as well as if deep learning algorithms perform better than machine learning algorithms on such a task. To answer the research questions we compiled a data set containing samples of people speaking with a varying degree of anxiety applied to their voice. We then implemented two algorithms able to classify the samples from our data set. One of the algorithms was a machine learning algorithm (ANN) with manual feature extraction, and the other one was a deep learning model (CNN) with automatic feature extraction. The performance of the two models were compared, and it was concluded that ANN was the better algorithm. When evaluating the models a 5-fold cross validation was used with a data split of 80/20. Every fold contains 100 epochs meaning we train both the models for a total of 500 epochs. For every fold the accuracy, precision, and recall is calculated. From these metrics we have then calculated other metrics such as sensitivity and specificity to compare the models. The ANN model performed a lot better than the CNN model on every single metric that was measured: accuracy, sensitivity, precision, f1-score, recall andspecificity.

Ron Rash’s Serena and Ann Pancake’s Strange as This Weather Has Been are two contemporary Appalachian novels that have yet to be analyzed from a biblical ecocritical perspective. While some literary scholars acknowledge the environmental aspects of the novels, little of their research goes beyond examining the land and its resources as commodities or metaphorical extensions for the characters. In this thesis, I elaborate on those interpretations by scrutinizing the natural descriptions in both novels and comparing those findings to some of the landscapes and environmental verses located within the Bible. Unlike the pastoral ideal found in a portion of the literature preceding the twentieth century, contemporary Appalachian writers such as Rash and Pancake have moved away from such a bucolic, prelapsarian idealization in favor of limning a more industrialized, postlapsarian Appalachia. Following both analyses, I conclude by predicting how emerging Appalachian writers will portray the landscape in future works.

Since mid to late 2010 image synthesizing using neural networks has become a trending research topic. And the framework mostly used for solving these tasks is the Generative adversarial network (GAN). GAN works by using two networks, a generator and a discriminator that trains and competes alongside each other. In today’s research regarding image synthesis, it is mostly about generating or altering images in any way which could be used in many fields, for example creating virtual environments. The topic is however still in quite an early stage of its development and there are fields where image synthesizing using Generative adversarial networks fails. In this work, we will answer one thesis question regarding the limitations and discuss for example the limitation causing GAN networks to get stuck during training. In addition to some limitations with existing GAN models, the research also lacks more experimental GAN variants. It exists today a lot of different variants, where GAN has been further developed and modified. But when it comes to GAN models where the discriminator has been changed to a different network, the number of existing works reduces drastically. In this work, we will experiment and compare an existing deep convolutional generative adversarial network (DCGAN), which is a GAN variant, with one that we have modified using a deep neuro-fuzzy system. We have created the first DCGAN model that uses a deep neuro-fuzzy system as a discriminator. When comparing these models, we concluded that the performance differences are not big. But we strongly believe that with some further improvements our model can outperform the DCGAN model. This work will therefore contribute to the research with the result and knowledge of a possible improvement to DCGAN models which in the future might cause similar research to be conducted on other GANmodels.

A proof-of-concept indirect tire-pressure monitoring system is developed using neural net- works to identify the tire pressure of a vehicle tire. A quarter-car model was developed with Matlab and Simulink to generate simulated accelerometer output data. Simulation data are used to train and evaluate a recurrent neural network with long short-term memory blocks (RNN-LSTM) and a convolutional neural network (CNN) developed in Python with Tensorflow. Bayesian Optimization via SigOpt was used to optimize training and model parameters. The predictive accuracy and training speed of the two models with various parameters are compared. Finally, future work and improvements are discussed.