[pt] Uma preocupação significativa durante a produção de óleo e gás é a garantia de escoamento para evitar desperdício de tempo e dinheiro. Devido às mudanças nas condições durante a produção (como pressão e temperatura), principalmente na região do pré-sal brasileiro, a solubilidade dos componentes do petróleo bruto (óleo-gás-água) pode diminuir, resultando na formação de depósitos. A incrustação é geralmente causada por parafina, hidratos e sal inorgânico. Neste trabalho, foram desenvolvidos modelos utilizando estratégias de Aprendizado de Máquina para monitoramento da formação de incrustações inorgânicas e medição de parâmetros de processo associados com formas de remediação de obstruções de outras fontes. Primeiramente, foram criados modelos do processo de formação de incrustação de carbonato de cálcio na presença de monoetilenoglicol (inibidor de hidrato) usando a arquitetura de redes neurais feedfoward prever o pressão diferencial um e cinco instantes à frente, obtendo um R2 superior a 92,9 porcento para ambos os horizontes de predição. O segundo tópico explorado foi desenvolver modelos para determinação do pH em sistemas pressurizados (até 6,0 MPa) por meio de análise de imagens. Podendo ser aplicados no monitoramento de sistemas como Sistema Gerador de Nitrogênio, utilizado para remediar alguns problemas de incrustação, dado que sua cinética depende fortemente do pH do sistema. Foram criados modelos de classificação para o pH do sistema (2, 3, 4, 5, 6, 7, 8, 9, 10) usando Redes Neurais Convolucionais (CNN), Máquina de Vetor de Suporte e Árvores de Decisão. Além disso, modelos CNN foram construídos para predizer o pH na faixa de 2- 10. / [en] A significant concern during oil and gas production is flow assurance to avoid loss of time and money. Due to production conditions changes (such as pressure and temperature), especially in the Brazilian pre-salt region, the solubility of the components of the crude oil (oil-gas-water) can decrease, resulting in the formation of deposits. The fouling is usually caused by wax, gas hydrate, and inorganic salt (scale). In this work, models were developed using Machine Learning strategies for scale formation monitoring and measuring process parameters associated with remediation of obstruction from other sources. First, models for the calcium carbonate scaling formation process in the presence of monoethylene glycol (typical gas hydrate inhibitor) were created using feedforward neural network architecture to predict the differential pressure (deltaP) one and five steps ahead, obtaining an R2 higher than 92.9 percent for the training and test group for both the prediction horizon. The second approach explored was the development of models for determining the pH in atmospheric and pressurized systems (up to 6.0 MPa) using image analysis. These models could be applied to control and monitor the Nitrogen Generation System, which can be used for different flow assurance problems, and its kinetics strongly depend on the system s pH value. This step initially created classification models for the system pH (2, 3, 4, 5, 6, 7, 8, 9, 10) using the Convolution Neural Networks (CNN), Support Vector Machine, and decision tree architectures. Also, CNN models were built to predict the pH in the range of 2-10.

Chronic cardiovascular disease (CVD) is increasingly becoming a burden for global healthcare systems. This burden can be attributed in part to traditional methods of managing CVD in an aging population that involves periodic meetings between the patient and their healthcare provider. There is growing interest in developing continuous monitoring systems to assist in the management of CVD. Monitoring systems can utilize advances in wearable devices and health records, which provides minimally invasive methods to monitor a patient’s health. Despite these advances, the algorithms deployed to automatically analyze the wearable sensor and health data is considered too computationally expensive to run on the mobile device. Instead, current mobile devices continuously transmit the collected data to a server for analysis at great computational and data transmission expense. In this thesis a novel mobile system designed for monitoring CVD is presented. Unlike existing systems, the proposed system allows for the continuous monitoring of physiological sensors, data from a patient’s health record and analysis of the data directly on the mobile device using machine learning algorithms (MLA) to predict an individual’s CVD severity level. The system successfully demonstrated that a mobile device can act as a complete monitoring system without requiring constant communication with a server. A comparative analysis between the support vector machine (SVM) and multilayer perceptron (MLP) to explore the effectiveness of each algorithm for monitoring CVD is also discussed. Both models were able to classify CVD risk with the SVM achieving the highest accuracy (63%) and specificity (76%). Finally, unlike current systems the resource requirements for each component in the system was evaluated. The MLP was found to be more efficient when running on the mobile device compared to the SVM. The results of thesis also show that the MLAs complexity was not a barrier to deployment on a mobile device. / Thesis / Master of Applied Science (MASc) / In this thesis, a novel mobile system for monitoring cardiovascular (CVD) disease is presented. The system allows for the continuous monitoring of both physiological sensors, data from a patient’s health record and analysis of the data directly on the mobile device using machine learning algorithms (MLA) to predict an individual’s CVD severity level. The system successfully demonstrated that a mobile device can act as a complete monitoring system without requiring constant communication with a remote server. A comparative analysis between the support vector machine (SVM) and multilayer perceptron (MLP) to explore the effectiveness of each MLA for monitoring CVD is also discussed. Both models were able to classify CVD severity with the SVM achieving the highest accuracy (63%) and specificity (76%). Finally, the resource requirements for each component in the system were evaluated. The results show that the MLAs complexity was not a barrier to deployment on a mobile device.

<p dir="ltr">The vagus nerve (VN) is the tenth cranial nerve that mediates most of the parasympathetic functions of the autonomic nervous system. The axons of the human VN comprise a mix of unmyelinated and myelinated axons, where ~80% of the axons are unmyelinated C fibers (Havton et al., 2021). Understanding that most VN axons are unmyelinated, there is a need to map the pathways of these axons to and from organs to understand their function(s) and whether C fiber morphology or signaling characteristics yield insights into their functions. Developing a machine learning model that detects and predicts the morphology of VN single fiber action potentials based on select fiber characteristics, e.g., diameter, myelination, and position within the VN, allows us to more readily categorize the nerve fibers with respect to their function(s). Additionally, the features of this machine learning model could help inform peripheral neuromodulation devices that aim to restore, replace, or augment one or more specific functions of the VN that have been lost due to injury, disease, or developmental abnormalities.</p><p dir="ltr">We designed and trained four types of Multi-layer Perceptron Artificial Deep Neural Networks (MLP-ANN) with 10,000 rat abdominal vagal C-fibers simulated via the peripheral neural interface model ViNERS. We analyze the accuracy of each MLP-ANN’s SFAP predictions by conducting normalized cross-correlation and morphology analyses with the ViNERS C-fiber SFAP counterparts. Our results showed that our best MLP predicted over 94% of the C-fiber SFAPs with strong normalized cross-correlation coefficients of 0.7 through 1 with the ViNERS SFAPs. Overall, this novel tool can use a C-fiber’s biophysical characteristics (i.e., fiber diameter size, fiber position on the x/y axis, etc.) to predict C-fiber SFAP morphology.</p>

No description available.

Machining chatter is an undesirable phenomenon of material removal processes and hardly to control or avoid. Its occurrence and extent essentially depend onthe kinematic, which alters with the position of the Tool Centre Point, of the machine tool. Research as to chatter was done widely but rarely with respect to changing structural dynamics during manufacturing. This thesis applies intelligent methods to learn the underlying functions of modal parameters – natural frequency, damping ratio, and mode shape – and defines the dynamic properties of a system firstly at this extent. To do so, it embraces three steps: first, the elaboration of the necessary dynamic parameters, second, the acquisition of the data via a simulation,and third, the prediction of the modal parameters with two kinds of Machine Learning techniques: Gradient Boosting Machine and Multilayer Perceptron. In total, it investigates three types of kinematics: cross bed, gantry, and overhead gantry. It becomes apparent that Light Gradient Boosting Machine outperforms Multilayer Perceptron throughout all studies. It achieves a prediction error of at most 1.7 % for natural frequency and damping ratio for all kinematics. However, it cannot really control the prediction of the participation factor yet which might originate in the complexity of the data and the data size. As expected, the error rises with noisy data and less amount of measurement points but at a tenable extent for both natural frequency and damping ratio. / 'Bearbetningsvibrationer är ett oönskat fenomen i materialborttagningsprocesser och är svåra att kontrollera eller undvika. Dess förekomst och omfattning beror i huvudsak på kinematiken, som förändras med positionen för verktygets centrumpunkt på verktygsmaskinen. Det har gjorts mycket forskning om bearbetningsvibrationer, men sällan om förändrad strukturell dynamik under tillverkningen. I denna avhandling tillämpas intelligenta metoder för att lära sig de underliggande funktionerna hos modalparametrar – egenfrekvens, dämpningsgrad och modalform – och definierar systemets dynamiska egenskaper för första gången i denna omfattning. För att göra detta omfattar den tre steg: för det första utarbetandet av de nödvändiga dynamiska parametrarna, för det andra insamling av data via en simulering och för det tredje förutsägelse av modalparametrarna med hjälp av två typer av tekniker för maskininlärning: Gradient Boosting Machine och Multilayer Perceptron. Sammanlagt undersöks tre typer av kinematik: crossbed, gantry och overhead gantry. Det framgår tydligt att Light Gradient Boosting Machine överträffar Multilayer Perceptron i alla studier. Den uppnår ett prediktionsfel på högst 1,7 % för egenfrekvens och dämpningsförhållande för alla kinematiker. Den kan dock ännu inte riktigt kontrollera förutsägelsen av deltagarfaktorn, vilket kan bero på datans komplexitet och datastorlek. Som väntat ökar felet med bullrig data och färre mätpunkter, men i en acceptabel omfattning för både naturfrekvens och dämpningsförhållande.

Cette thèse s’intéresse à la problématique de la prédiction dans le cadre du design de systèmes énergétiques et des problèmes d’opération, et en particulier, à l’évaluation de l’adéquation de systèmes de production d’énergie renouvelables. L’objectif général est de développer une approche empirique pour générer des prédictions avec les incertitudes associées. En ce qui concerne cette direction de la recherche, une approche non paramétrique et empirique pour estimer les intervalles de prédiction (PIs) basés sur les réseaux de neurones (NNs) a été développée, quantifiant l’incertitude dans les prédictions due à la variabilité des données d’entrée et du comportement du système (i.e. due au comportement stochastique des sources renouvelables et de la demande d'énergie électrique), et des erreurs liées aux approximations faites pour établir le modèle de prédiction. Une nouvelle méthode basée sur l'optimisation multi-objectif pour estimer les PIs basée sur les réseaux de neurones et optimale à la fois en termes de précision (probabilité de couverture) et d’information (largeur d’intervalle) est proposée. L’ensemble de NN individuels par deux nouvelles approches est enfin présenté comme un moyen d’augmenter la performance des modèles. Des applications sur des études de cas réels démontrent la puissance de la méthode développée. / This Ph.D. work addresses the problem of prediction within energy systems design and operation problems, and particularly the adequacy assessment of renewable power generation systems. The general aim is to develop an empirical modeling framework for providing predictions with the associated uncertainties. Along this research direction, a non-parametric, empirical approach to estimate neural network (NN)-based prediction intervals (PIs) has been developed, accounting for the uncertainty in the predictions due to the variability in the input data and the system behavior (e.g. due to the stochastic behavior of the renewable sources and of the energy demand by the loads), and to model approximation errors. A novel multi-objective framework for estimating NN-based PIs, optimal in terms of both accuracy (coverage probability) and informativeness (interval width) is proposed. Ensembling of individual NNs via two novel approaches is proposed as a way to increase the performance of the models. Applications on real case studies demonstrate the power of the proposed framework.

Made available in DSpace on 2016-12-12T20:22:52Z (GMT). No. of bitstreams: 1 RAFAEL ALCESTE BERRI.pdf: 28428368 bytes, checksum: 667b9facc9809bfd5e0847e15279b0e6 (MD5) Previous issue date: 2014-02-21 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / In this work, three proposals of systems have been developed using a frontal camera to monitor the driver and enabling to identificate if a cell phone is being used while driving the vehicle. It is estimated that 80% of crashes and 65% of near collisions involved drivers who were inattentive in traffic for three seconds before the event. Five videos in real environment were generated to test the systems. The pattern recognition system (RP) uses adaptive skin segmentation, feature extraction, and machine learning to detect cell phone usage on each frame. The cell phone detection happens when, in periods of 3 seconds, 60% (threshold) of frames or more are identified as a cell phone use, individually. The average accuracy on videos achieved was 87.25% with Multilayer Perceptron (MLP), Gaussian activation function, and two neurons of the intermediate layer. The movement detection system (DM) uses optical flow, filtering the most relevant movements of the scene, and three successive frames for detecting the movements to take the phone to the ear and take it off. The DM proposal was not demonstrated as being an effective solution for detecting cell phone use, reaching an accuracy of 52.86%. The third solution is a hybrid system. It uses the RP system for classification and the DM for choosing the RP parameters. The parameters chosen for RP are the threshold and the classification system. The definition of these two parameters occurs at the end of each period, based on movement detected by the DM. Experimentally it was established that, when the movement induces to use cell phone, it is proper to use the threshold of 60%, and the classifier as MLP/Gaussian with seven neurons of the intermediate layer; otherwise, it is used threshold 85%, and MLP/Gaussian with two neurons of the intermediate layer for classification. The hybrid solution is the most robust system with average accuracy of 91.68% in real environment. / Neste trabalho, são desenvolvidas três propostas de sistemas que permitem identificar o uso de celular, durante o ato de dirigir um veículo, utilizando imagens capturadas de uma câmera posicionada em frente ao motorista. Estima-se que 80% das colisões e 65% das quase colisões envolveram motoristas que não estavam prestando a devida atenção ao trânsito por três segundos antes do evento. Cinco vídeos em ambiente real foram gerados com o intuito de testar os sistemas. A proposta de reconhecimento de padrões (RP) emprega segmentação de pele adaptativa, extração de características e aprendizado de máquina (classificador) na detecção do celular em cada quadro processado. A detecção do uso do celular ocorre quando, em períodos de 3 segundos, ao menos em 60% dos quadros (corte) são identificados com celular. A acurácia média nos vídeos alcançou 87, 25% ao utilizar Perceptron Multi-camadas (MLP) com função de ativação gaussiana e dois neurônios na camada intermediária como classificador. A proposta de detecção de movimento (DM) utiliza o fluxo ótico, filtragem dos movimentos mais relevantes da cena e três quadros consecutivos para detectar os momentos de levar o celular ao ouvido e o retirá-lo. A aplicação do DM, como solução para detectar o uso do celular, não se demostrou eficaz atingindo uma acurácia de 52, 86%. A terceira proposta, uma solução híbrida, utiliza o sistema RP como classificador e o de DM como seu parametrizador. Os parâmetros escolhidos para o sistema de RP são o corte e o sistema classificador. A definição desses dois parâmetros ocorre ao final de cada período, baseada na movimentação detectada pela DM. Com experimentações definiu-se que, caso a movimentação induza ao uso do celular, é adequado o uso do corte de 60% e o classificador MLP/Gaussiana com sete neurônios na camada intermediária, caso contrário, utiliza-se o corte de 85% e classificador MLP/Gaussiana com dois neurônios na mesma camada. A versão híbrida é a solução desenvolvida mais robusta, atingindo a melhor acurácia média de 91, 68% em ambiente real.

Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.

Software prediction is a complex area as there are no accurate models to represent reliability throughout the use of software, unlike hardware reliability. In the context of the software reliability of on-board train systems, ensuring good software reliability over time is all the more critical given the current density of rail traffic and the risk of accidents resulting from a software malfunction. This thesis proposes to use soft computing methods and historical failure data to predict the software reliability of on-board train systems. For this purpose, four machine learning models (Multi-Layer Perceptron, Imperialist Competitive Algorithm Multi-Layer Perceptron, Long Short-Term Memory Network and Convolutional Neural Network) are compared to determine which has the best prediction performance. We also study the impact of having one or more features represented in the dataset used to train the models. The performance of the different models is evaluated using the Mean Absolute Error, Mean Squared Error, Root Mean Squared Error and the R Squared. The report shows that the Long Short-Term Memory Network is the best performing model on the data used for this project. It also shows that datasets with a single feature achieve better prediction. However, the small amount of data available to conduct the experiments in this project may have impacted the results obtained, which makes further investigations necessary. / Att förutsäga programvara är ett komplext område eftersom det inte finns några exakta modeller för att representera tillförlitligheten under hela programvaruanvändningen, till skillnad från hårdvarutillförlitlighet. När det gäller programvarans tillförlitlighet i fordonsbaserade tågsystem är det ännu viktigare att säkerställa en god tillförlitlighet över tiden med tanke på den nuvarande tätheten i järnvägstrafiken och risken för olyckor till följd av ett programvarufel. I den här avhandlingen föreslås att man använder mjuka beräkningsmetoder och historiska data om fel för att förutsäga programvarans tillförlitlighet i fordonsbaserade tågsystem. För detta ändamål jämförs fyra modeller för maskininlärning (Multi-Layer Perceptron, Imperialist Competitive Algorithm Mult-iLayer Perceptron, Long Short-Term Memory Network och Convolutional Neural Network) för att fastställa vilken som har den bästa förutsägelseprestandan. Vi undersöker också effekten av att ha en eller flera funktioner representerade i den datamängd som används för att träna modellerna. De olika modellernas prestanda utvärderas med hjälp av medelabsolut fel, medelkvadratfel, rotmedelkvadratfel och R-kvadrat. Rapporten visar att Long Short-Term Memory Network är den modell som ger bäst resultat på de data som använts för detta projekt. Den visar också att dataset med en enda funktion ger bättre förutsägelser. Den lilla mängd data som fanns tillgänglig för att genomföra experimenten i detta projekt kan dock ha påverkat de erhållna resultaten, vilket gör att ytterligare undersökningar är nödvändiga.

This study aimed to explore the application of artificial intelligence (AI) and machine learning (ML) techniques in implementing a QRS detector forambulatory electrocardiography (ECG) monitoring devices. Three ML models, namely long short-term memory (LSTM), convolutional neural network (CNN), and multilayer perceptron (MLP), were compared and evaluated using the MIT-BIH arrhythmia database (MITDB) and the MIT-BIH noise stress test database (NSTDB). The MLP model consistently outperformed the other models, achieving high accuracy in R-peak detection. However, when tested on noisy data, all models faced challenges in accurately predicting R-peaks, indicating the need for further improvement. To address this, the study emphasized the importance of iteratively refining the input data configurations for achieving accurate R-peak detection. By incorporating both the MITDB and NSTDB during training, the models demonstrated improved generalization to noisy signals. This iterative refinement process allowed for the identification of the best models and configurations, consistently surpassing existing ML-based implementations and outperforming the current ECG analysis system. The MLP model, without shifting segments and utilizing both datasets, achieved an outstanding accuracy of 99.73 % in R-peak detection. This accuracy exceeded values reported in the literature, demonstrating the superior performance of this approach. Furthermore, the shifted MLP model, which considered temporal dependencies by incorporating shifted segments, showed promising results with an accuracy of 99.75 %. It exhibited enhanced accuracy, precision, and F1-score compared to the other models, highlighting the effectiveness of incorporating shifted segments. For future research, it is important to address challenges such as overfitting and validate the models on independent datasets. Additionally, continuous refinement and optimization of the input data configurations will contribute to further advancements in ECG signal analysis and improve the accuracy of R-peak detection. This study underscores the potential of ML techniques in enhancing ECG analysis, ultimately leading to improved cardiac diagnostics and better patient care. / Syftet med denna studie var att utforska användningen av AI- och ML-tekniker för att implementera en QRS-detektor i EKG-övervakningsenheter. Tre olika ML-modeller, LSTM, CNN och MLP jämfördes och utvärderades med hjälp av MITDB och NSTDB. Resultaten visade att MLP-modellen konsekvent presterade bättre än de andra modellerna och uppnådde hög noggrannhet vid detektion av R-toppar i EKG-signalen. Trots detta stötte alla modeller på utmaningar när de testades på brusig realtidsdata, vilket indikerade behovet av ytterligare förbättringar. För att hantera dessa utmaningar betonade studien vikten av att iterativt förbättra konfigurationen av indata för att uppnå noggrann detektering av R toppar. Genom att inkludera både MITDB och NSTDB under träningen visade modellerna förbättrad förmåga att generalisera till brusiga signaler. Denna iterativa process möjliggjorde identifiering av de bästa modellerna och konfigurationerna, vilka konsekvent överträffade befintliga ML-baserade implementeringar och presterade bättre än den nuvarande EKG-analysystemet. MLP-modellen, utan användning av skiftade segment och med båda databaserna, uppnådde en imponerande noggrannhet på 99,73 % vid detektion av R-toppar. Denna noggrannhet överträffade tidigare studier och visade på den överlägsna prestandan hos denna metod. Dessutom visade den skiftade MLP-modellen, som inkluderade skiftade segment för att beakta tidsberoenden, lovande resultat med en noggrannhet på 99,75 %. Modellen uppvisade förbättrad noggrannhet, precision och F1-score jämfört med de andra modellerna, vilket betonar vikten av att inkludera skiftade segment. För framtida studier är det viktigt att hantera utmaningar som överanpassning och att validera modellerna med oberoende datamängder. Dessutom kommer en kontinuerlig förfining och optimering av konfigurationen av indata att bidra till ytterligare framsteg inom EKG-signalanalys och förbättrad noggrannhet vid detektion av R-toppar. Denna studie understryker potentialen hos ML-modeller för att förbättra EKG-analysen och därigenom bidra till förbättrad diagnostik av hjärtsjukdomar och högre kvalitet inom patientvården.