Les malformations cardiaques congénitales sont la première cause de décès liés à une anomalie congénitale. L’´electrocardiogramme du fœtus (ECGf), qui est censé contenir beaucoup plus d’informations par rapport aux méthodes échographiques conventionnelles, peut ˆêtre mesuré´e par des électrodes sur l’abdomen de la mère. Cependant, il est tr`es faible et mélangé avec plusieurs sources de bruit et interférence y compris l’ECG de la mère (ECGm) dont le niveau est très fort. Dans les études précédentes, plusieurs méthodes ont été proposées pour l’extraction de l’ECGf à partir des signaux enregistrés par des électrodes placées à la surface du corps de la mère. Cependant, ces méthodes nécessitent un nombre de capteurs important, et s’avèrent inefficaces avec un ou deux capteurs. Dans cette étude trois approches innovantes reposant sur une paramétrisation algébrique, statistique ou par variables d’état sont proposées. Ces trois méthodes mettent en œuvre des modélisations différentes de la quasi-périodicité du signal cardiaque. Dans la première approche, le signal cardiaque et sa variabilité sont modélisés par un filtre de Kalman. Dans la seconde approche, le signal est découpé en fenêtres selon les battements, et l’empilage constitue un tenseur dont on cherchera la décomposition. Dans la troisième approche, le signal n’est pas modélisé directement, mais il est considéré comme un processus Gaussien, caractérisé par ses statistiques à l’ordre deux. Dans les différentes modèles, contrairement aux études précédentes, l’ECGm et le (ou les) ECGf sont modélisés explicitement. Les performances des méthodes proposées, qui utilisent un nombre minimum de capteurs, sont évaluées sur des données synthétiques et des enregistrements réels, y compris les signaux cardiaques des fœtus jumeaux. / Congenital heart defects are the leading cause of birth defect-related deaths. The fetal electrocardiogram (fECG), which is believed to contain much more information as compared with conventional sonographic methods, can be measured by placing electrodes on the mother’s abdomen. However, it has very low power and is mixed with several sources of noise and interference, including the strong maternal ECG (mECG). In previous studies, several methods have been proposed for the extraction of fECG signals recorded from the maternal body surface. However, these methods require a large number of sensors, and are ineffective with only one or two sensors. In this study, state modeling, statistical and deterministic approaches are proposed for capturing weak traces of fetal cardiac signals. These three methods implement different models of the quasi-periodicity of the cardiac signal. In the first approach, the heart rate and its variability are modeled by a Kalman filter. In the second approach, the signal is divided into windows according to the beats. Stacking the windows constructs a tensor that is then decomposed. In a third approach, the signal is not directly modeled, but it is considered as a Gaussian process characterized by its second order statistics. In all the different proposed methods, unlike previous studies, mECG and fECG(s) are explicitly modeled. The performances of the proposed methods, which utilize a minimal number of electrodes, are assessed on synthetic data and actual recordings including twin fetal cardiac signals.

The explosion of information and user generated content made publicly available through the internet has made it possible to develop new ways of inferring interesting phenomena automatically. Some interesting examples are the spread of a contagious disease, earth quake occurrences, rainfall rates, box office results, stock market fluctuations and many many more. To this end a mathematical framework, based on theory from machine learning, has been employed to show how frequencies of relevant keywords in user generated content can estimate daily rainfall rates of different regions in Sweden using microblog data. Microblog data are collected using a microblog crawler. Properties of the data and data collection methods are both discussed extensively. In this thesis three different model types are studied for regression, linear and nonlinear parametric models as well as a nonparametric Gaussian process model. Using cross-validation and optimization the relevant parameters of each model are estimated and the model is evaluated on independent test data. All three models show promising results for nowcasting rainfall rates.

No description available.

Despite the alarming incidence rate and potential for debilitating outcomes of sports-related concussion, the underlying mechanisms of injury remain to be expounded. Since as early as 1950, researchers have aimed to characterize head impact biomechanics through in-lab and in-game investigations. The ever-growing body of literature within this area has supported the inherent connection between head kinematics during impact and injury outcomes. Even so, traditional metrics of peak acceleration, time window, and HIC have outlived their potential. More sophisticated analysis techniques are required to advance the understanding of concussive vs subconcussive impacts. The work presented within this thesis was motivated by the exploration of advanced approaches to 1) experimental theory and design of impact reconstructions and 2) characterization of kinematic profiles for model building. These two areas of investigation resulted in the presentation of refined, systematic approaches to head impact analysis that should begin to replace outdated standards and metrics.

No description available.

With advancements in technology, electric vehicles are dominating the world making Internal Combustion engines less relevant, and hence vehicles are becoming quieter than ever before. But noise levels remain a significant concern for both passengers and automotive manufacturers. The vehicle's interior noise can affect the overall driving experience and even the safety of the driver and the passengers. The two main sources of vehicle interior noise are attributed to air-borne noises and structure-borne noises. A modern automobile is a complicated vibration system with several excitation sources like the engine, transmission system, tire/road interface excitation, and wind noise. With electric vehicles on the rise, the engine and transmission noise is practically eliminated, and effective preventive measures and control systems are already in place to reduce the aerodynamic-based noise, vibrations, and harshness (NVH) in modern automobiles making the structure-borne noise the most crucial of the noise sources. Tire/road interaction noise being the most dominant among the structure-borne noise is the main concern of the vehicle interior noise. The two main sources of vehicle interior noise induced by the tire pavement interaction noise are structure-borne noise induced by the low-frequency excitation and air-borne noises produced by the mid and high-frequency excitation. The present study tested an all-season tire over varying operational conditions such as different speeds, normal loads, and inflation pressures on an asphalt surface. Two tri-axial accelerometers attached 1800 apart from each other on the inner liner of the tire of a Volkswagen Jetta were used to measure the circumferential, lateral, and radial acceleration data. An Inertial Measurement Unit (IMU) and velocity box (VBOX) were instrumented in the vehicle to measure the acceleration at the center of gravity (COG) position of the vehicle and the longitudinal velocity of the vehicle respectively. The vehicle was also equipped with a modified hybrid of Close Proximity Testing (CPX) and On-Board Sound Intensity (OBSI) sound measurement systems which were designed and manufactured in-house to measure the tire/road interaction noise at the leading and trailing edges of the tire/road contact patch. Another microphone was instrumented inside the passenger compartment of the vehicle at the passenger's seat right ear position over the tire mounted with the sound measurement system to measure the vehicle interior noise as interpreted by the passengers in the vehicle. Two data acquisition systems coupled with a real-time Simulink model were used to collect all the measured data, one for the noise signals and the other for velocity and acceleration signals. The focus of the current study is to review different generation and amplification mechanisms of the structure-induced tire/road interaction noise and find the relevant dominant frequency ranges of the vehicle interior noise induced by the structure-borne noises using already established physics-based models and correlation techniques. It also aims to find correlations between tire acceleration, vehicle interior noise, and tire pavement interaction noise and their effect on different operational conditions like load, inflation pressure, and velocity. All the signals are studied in the time, frequency, and spectral domain and insights have been drawn on different tire/road noise generation and amplification mechanisms. / Master of Science / Structure-induced vehicle interior noise is one of the main concerns surrounding the automotive NVH industry and tire/road interaction noise being the most dominant source among the structure-borne noises affecting the vehicle interior noise is a major problem to the tire and automotive manufacturers nowadays. It leads to discomfort for the driver and the passengers in the vehicle and can cause fatigue, which in turn can directly affect the vehicle's safety. Several attempts have been made to reduce vehicle interior noise using statistical, physics-based, and hybrid models, but the research is still nowhere near completion. The current study aims to identify the frequency ranges affecting the structure-borne noise-induced vehicle interior noise and uses data-driven approaches in estimating the vehicle interior noise using only the acceleration of the tire. A test setup was designed and developed in-house where a tri-axial accelerometer embedded inside the inner liner of the tire measures the X, Y, and Z acceleration signals. Several microphones are instrumented at the tire/road contact surface and inside the passenger cabin to measure the tire/road interaction noise and the vehicle interior noise. The longitudinal velocity of the vehicle and the accelerations at the center of gravity of the vehicle have also been measured. Multiple data-driven models have been developed to directly predict the vehicle interior noise and tire/road interaction noise using the accelerometer data. This research is directly helpful for the automotive and tire industries by giving them insights on designing and developing quieter tires by using data-driven approaches and further using these with active control systems can mask the vehicle interior noise to acceptable levels in real-time.

<p>The document describes the computational framework to optimize spring-driven Autoinjectors. It involves Bayesian Optimization for efficient and cost-effective design of Autoinjectors.</p>

<p>Bridging the accuracy of ab initio (AI) QM/MM with the efficiency of semi-empirical<br> (SE) QM/MM methods has long been a goal in computational chemistry. This dissertation<br> presents four ∆-Machine learning schemes aimed at achieving this objective. Firstly, the in-<br> corporation of negative force observations into the Gaussian process regression (GPR) model,<br> resulting in GPR with derivative observations, demonstrates the remarkable capability to<br> attain high-quality potential energy surfaces, accurate Cartesian force descriptions, and reli-<br> able free energy profiles using a training set of just 80 points. Secondly, the adaptation of the<br> sparse streaming GPR algorithm showcases the potential of memory retention from previous<br> phasespace, enabling energy-only models to converge using simple descriptors while faith-<br> fully reproducing high-quality potential energy surfaces and accurate free energy profiles.<br> Thirdly, the utilization of GPR with atomic environmental vectors as input features proves<br> effective in enhancing both potential energy surface and free energy description. Further-<br> more, incorporating derivative information on solute atoms further improves the accuracy<br> of force predictions on molecular mechanical (MM) atoms, addressing discrepancies arising<br> from QM/MM interaction energies between the target and base levels of theory. Finally, a<br> comprehensive comparison of three distinct GPR schemes, namely GAP, GPR with an aver-<br> age kernel, and GPR with a system-specific sum kernel, is conducted to evaluate the impact<br> of permutational invariance and atomistic learning on the model’s quality. Additionally, this<br> dissertation introduces the adaptation of the GAP method to be compatible with the sparse<br> variational Gaussian processes scheme and the streaming sparse GPR scheme, enhancing<br> their efficiency and applicability. Through these four ∆-Machine learning schemes, this dis-<br> sertation makes significant contributions to the field of computational chemistry, advancing<br> the quest for accurate potential energy surfaces, reliable force descriptions, and informative<br> free energy profiles in QM/MM simulations.<br> </p>

In this thesis, newer Markov Chain Monte Carlo (MCMC) algorithms are implemented and compared in terms of their efficiency in the context of sampling from Gaussian processes under linear inequality constraints. Extending the framework of Gaussian process that uses Gibbs sampler, two MCMC algorithms, Exact Hamiltonian Monte Carlo (HMC) and Analytic Elliptical Slice Sampling (ESS), are used to sample values of truncated multivariate Gaussian distributions that are used for Gaussian process regression models with linear inequality constraints. In terms of generating samples from Gaussian processes under linear inequality constraints, the proposed methods generally produce samples that are less correlated than samples from the Gibbs sampler. Time-wise, Analytic ESS is proven to be a faster choice while Exact HMC produces the least correlated samples.

In this thesis, I present a decentralized sparse Gaussian process regression (DSGPR) model with event-triggered, adaptive inducing points. This DSGPR model brings the advantages of sparse Gaussian process regression to a decentralized implementation. Being decentralized and sparse provides advantages that are ideal for multi-agent systems (MASs) performing environmental modeling. In this case, MASs need to model large amounts of information while having potential intermittent communication connections. Additionally, the model needs to correctly perform uncertainty propagation between autonomous agents and ensure high accuracy on the prediction. For the model to meet these requirements, a bounded and efficient real-time sparse Gaussian process regression (SGPR) model is needed. I improve real-time SGPR models in these regards by introducing an adaptation of the mean shift and fixed-width clustering algorithms called radial clustering. Radial clustering enables real-time SGPR models to have an adaptive number of inducing points through an efficient inducing point selection process. I show how this clustering approach scales better than other seminal Gaussian process regression (GPR) and SGPR models for real-time purposes while attaining similar prediction accuracy and uncertainty reduction performance. Furthermore, this thesis addresses common issues inherent in decentralized frameworks such as high computation costs, inter-agent message bandwidth restrictions, and data fusion integrity. These challenges are addressed in part through performing maximum consensus between local agent models which enables the MAS to gain the advantages of decentral- ization while keeping data fusion integrity. The inter-agent communication restrictions are addressed through the contribution of two message passing heuristics called the covariance reduction heuristic and the Bhattacharyya distance heuristic. These heuristics enable user to reduce message passing frequency and message size through the Bhattacharyya distance and properties of spatial kernels. The entire DSGPR framework is evaluated on multiple simulated random vector fields. The results show that this framework effectively estimates vector fields using multiple autonomous agents. This vector field is assumed to be a wind field; however, this framework may be applied to the estimation of other scalar or vector fields (e.g., fluids, magnetic fields, electricity, etc.).