The estimation of the gas concentration (process-state) associated with a stationary or moving source using a sensing aerial vehicle (SAV) is considered. The dispersion from such a gaseous source into the ambient atmosphere is representative of an accidental or deliberate release of chemicals, or a release of gases from biological systems. Estimation of the concentration field provides a superior ability for source localization, assessment of possible adverse impacts, and eventual containment. The abstract and finite-dimensional approximation framework presented couples theoretical estimation and control with computational fluid dynamics methods. The gas dispersion (process) model is based on the advection-diffusion equation with variable eddy diffusivities and ambient winds. Cases are considered for a 2D and 3D domain. The state estimator is a modified Luenberger observer with a €�collocated€� filter gain that is parameterized by the position of the SAV. The process-state (concentration) estimator is based on a 2D and 3D adaptive, multigrid, multi-step finite-volume method. The grid is adapted with local refinement and coarsening during the process-state estimation in order to improve accuracy and efficiency. The motion dynamics of the SAV are incorporated into the spatial process and the SAV€™s guidance is directly linked to the performance of the state estimator. The computational model and the state estimator are coupled in the sense that grid-refinement is affected by the SAV repositioning, and the guidance laws of the SAV are affected by grid-refinement. Extensive numerical experiments serve to demonstrate the effectiveness of the coupled approach.

abstract: The purpose of information source detection problem (or called rumor source detection) is to identify the source of information diffusion in networks based on available observations like the states of the nodes and the timestamps at which nodes adopted the information (or called infected). The solution of the problem can be used to answer a wide range of important questions in epidemiology, computer network security, etc. This dissertation studies the fundamental theory and the design of efficient and robust algorithms for the information source detection problem. For tree networks, the maximum a posterior (MAP) estimator of the information source is derived under the independent cascades (IC) model with a complete snapshot and a Short-Fat Tree (SFT) algorithm is proposed for general networks based on the MAP estimator. Furthermore, the following possibility and impossibility results are established on the Erdos-Renyi (ER) random graph: $(i)$ when the infection duration $<\frac{2}{3}t_u,$ SFT identifies the source with probability one asymptotically, where $t_u=\left\lceil\frac{\log n}{\log \mu}\right\rceil+2$ and $\mu$ is the average node degree, $(ii)$ when the infection duration $>t_u,$ the probability of identifying the source approaches zero asymptotically under any algorithm; and $(iii)$ when infection duration $<t_u,$ the breadth-first search (BFS) tree starting from the source is a fat tree. Numerical experiments on tree networks, the ER random graphs and real world networks show that the SFT algorithm outperforms existing algorithms. In practice, other than the nodes' states, side information like partial timestamps may also be available. Such information provides important insights of the diffusion process. To utilize the partial timestamps, the information source detection problem is formulated as a ranking problem on graphs and two ranking algorithms, cost-based ranking (CR) and tree-based ranking (TR), are proposed. Extensive experimental evaluations of synthetic data of different diffusion models and real world data demonstrate the effectiveness and robustness of CR and TR compared with existing algorithms. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2015

Big data concerns large-volume, complex, growing data sets, and it provides us opportunities as well as challenges. This thesis focuses on statistical methods for several specific large, complex data challenges - each involving representation of data with complex format, utilization of complicated information, and/or intensive computational cost. The first problem we work on is hypothesis testing for multilayer network data, motivated by an example in computational biology. We show how to represent the complex structure of a multilayer network as a single data point within the space of supra-Laplacians and then develop a central limit theorem and hypothesis testing theories for multilayer networks in that space. We develop both global and local testing strategies for mean comparison and investigate sample size requirements. The methods were applied to the motivating computational biology example and compared with the classic Gene Set Enrichment Analysis(GSEA). More biological insights are found in this comparison. The second problem is the source detection problem in epidemiology, which is one of the most important issues for control of epidemics. Ideally, we want to locate the sources based on all history data. However, this is often infeasible, because the history data is complex, high-dimensional and cannot be fully observed. Epidemiologists have recognized the crucial role of human mobility as an important proxy to a complete history, but little in the literature to date uses this information for source detection. We recast the source detection problem as identifying a relevant mixture component in a multivariate Gaussian mixture model. Human mobility within a stochastic PDE model is used to calibrate the parameters. The capability of our method is demonstrated in the context of the 2000-2002 cholera outbreak in the KwaZulu-Natal province. The third problem is about multivariate time series imputation, which is a classic problem in statistics. To address the common problem of low signal-to-noise ratio in high-dimensional multivariate time series, we propose models based on state-space models which provide more precise inference of missing values by clustering multivariate time series components in a nonparametric way. The models are suitable for large-scale time series due to their efficient parameter estimation. / 2019-05-15T00:00:00Z

Inverse problems have gained popularity in statistical research recently. This dissertation consists of two statistical inverse problems: a Bayesian approach to detection of small low emission sources on a large random background, and parameter estimation methods for partial differential equation (PDE) models. Source detection problem arises, for instance, in some homeland security applications. We address the problem of detecting presence and location of a small low emission source inside an object, when the background noise dominates. The goal is to reach the signal-to-noise ratio levels on the order of 10^-3. We develop a Bayesian approach to this problem in two-dimension. The method allows inference not only about the existence of the source, but also about its location. We derive Bayes factors for model selection and estimation of location based on Markov chain Monte Carlo simulation. A simulation study shows that with sufficiently high total emission level, our method can effectively locate the source. Differential equation (DE) models are widely used to model dynamic processes in many fields. The forward problem of solving equations for given parameters that define the DEs has been extensively studied in the past. However, the inverse problem of estimating parameters based on observed state variables is relatively sparse in the statistical literature, and this is especially the case for PDE models. We propose two joint modeling schemes to solve for constant parameters in PDEs: a parameter cascading method and a Bayesian treatment. In both methods, the unknown functions are expressed via basis function expansion. For the parameter cascading method, we develop the algorithm to estimate the parameters and derive a sandwich estimator of the covariance matrix. For the Bayesian method, we develop the joint model for data and the PDE, and describe how the Markov chain Monte Carlo technique is employed to make posterior inference. A straightforward two-stage method is to first fit the data and then to estimate parameters by the least square principle. The three approaches are illustrated using simulated examples and compared via simulation studies. Simulation results show that the proposed methods outperform the two-stage method.

In this dissertation, two recent problems from tomographic imaging are studied, and results from numerical simulations with synthetic data are presented. The first part deals with ultrasound modulated optical tomography, a method for imaging interior optical properties of partially translucent media that combines optical contrast with ultrasound resolution. The primary application is the optical imaging of soft tissue, for which scattering and absorption rates contain important functional and structural information about the physiological state of tissue cells. We developed a mathematical model based on the diffusion approximation for photon propagation in highly scattering media. Simple reconstruction schemes for recovering optical absorption rates from boundary measurements with focused ultrasound are presented. We show numerical reconstructions from synthetic data generated for mathematical absorption phantoms. The results indicate that high resolution imaging with quantitatively correct values of absorption is possible. Synthetic focusing techniques are suggested that allow reconstruction from measurements with certain types of non-focused ultrasound signals. A preliminary stability analysis for a linearized model is given that provides an initial explanation for the observed stability of reconstruction. In the second part, backprojection schemes are proposed for the detection of small amounts of highly enriched nuclear material inside 3D volumes. These schemes rely on the geometrically singular structure that small radioactive sources represent, compared to natural background radiation. The details of the detection problem are explained, and two types of measurements, collimated and Compton-type measurements, are discussed. Computationally, we implemented backprojection by counting the number of particle trajectories intersecting each voxel of a regular rectangular grid covering the domain of detection. For collimated measurements, we derived confidence estimates indicating when voxel trajectory counts are deviating significantly from what is expected from background radiation. Monte Carlo simulations of random background radiation confirm the estimated confidence values. Numerical results for backprojection applied to synthetic measurements are shown that indicate that small sources can be detected for signal-to-noise ratios as low as 0.1%.

<p>Acoustic signals have long been used to monitor the performance of machinery containing mechanical moving parts, especially machinery used in manufacturing. Rotating components generate harmonic signals with a fundamental frequency corresponding to the period of rotation, although the fundamental frequency and some of the harmonics may be missing. In addition, the meshing of the teeth in gears generates higher frequencies corresponding to the period of the gear teeth interaction. We call the former frequencies harmonic frequencies and the latter frequencies strong tone frequencies. Each strong tone frequency typically has associated with it, a set of modulation frequencies.<br></p><p><br></p><p>For each strong tone frequency, it is important to be able to determine which modulation frequencies correspond to a particular harmonic series, since this can help to determine which component in the overall mechanism is failing. In this work, we describe a novel process for selecting from a set of candidate modulation frequencies that comprise one or more harmonic sequences.<br></p><p><br></p><p>We also describe the signal processing pipeline used to extract the frequency components from the raw acoustic signal.<br></p>

Dans ce manuscrit, nous étudions la diffusion d'information dans les réseaux sociaux en ligne. Des sites comme Facebook ou Twitter sont en effet devenus aujourd'hui des media d'information à part entière, sur lesquels les utilisateurs échangent de grandes quantités de données. La plupart des modèles existant pour expliquer ce phénomène de diffusion sont des modèles génératifs, basés sur des hypothèses fortes concernant la structure et la dynamique temporelle de la diffusion d'information. Nous considérerons dans ce manuscrit le problème de la prédiction de diffusion dans le cas où le graphe social est inconnu, et où seules les actions des utilisateurs peuvent être observées. - Nous proposons, dans un premier temps, une méthode d'apprentissage du modèle independent cascade consistant à ne pas prendre en compte la dimension temporelle de la diffusion. Des résultats expérimentaux obtenus sur des données réelles montrent que cette approche permet d'obtenir un modèle plus performant et plus robuste. - Nous proposons ensuite plusieurs méthodes de prédiction de diffusion reposant sur des technique d'apprentissage de représentations. Celles-ci nous permettent de définir des modèles plus compacts, et plus robustes à la parcimonie des données. - Enfin, nous terminons en appliquant une approche similaire au problème de détection de source, consistant à retrouver l'utilisateur ayant lancé une rumeur sur un réseau social. En utilisant des méthodes d'apprentissage de représentations, nous obtenons pour cette tâche un modèle beaucoup plus rapide et performant que ceux de l'état de l'art. / In this thesis, we study information diffusion in online social networks. Websites like Facebook or Twitter have indeed become information medias, on which users create and share a lot of data. Most existing models of the information diffusion phenomenon relies on strong hypothesis about the structure and dynamics of diffusion. In this document, we study the problem of diffusion prediction in the context where the social graph is unknown and only user actions are observed. - We propose a learning algorithm for the independant cascades model that does not take time into account. Experimental results show that this approach obtains better results than time-based learning schemes. - We then propose several representations learning methods for this task of diffusion prediction. This let us define more compact and faster models. - Finally, we apply our representation learning approach to the source detection task, where it obtains much better results than graph-based approaches.

In recent years, the Brigham Young University (BYU) Radio Astronomy Systems group has developed phased-array feeds and the data acquisition processing systems necessary to perform radio astronomy observations. This thesis describes the development and testing of a real-time digital beamforming system that reduces both the time required to process phased-array feed data and the disk space used to record this data compared to post-processing beamforming systems. A real-data experiment is also discussed in this thesis, which focuses on some of the data post-processing required for one of BYU's data acquisition systems.Radio-frequency interference mitigation techniques for phased-array feed radio astronomy have been studied for several years, but the effect that these techniques have on weak-signal detection is not well understood. This thesis provides analysis of a simulated weak-source observation for the Green Bank 20-meter telescope and BYU 19 element phasedarray feed with radio-frequency interference present. Interference mitigation techniques are shown to reduce the detectability of weak sources compared with the no interference case, but it is also shown that a weak source can be detected that would otherwise be masked by interference.

Die Methoden der Netzwerktheorie erfreuen sich wachsender Beliebtheit, da sie die Darstellung von komplexen Systemen durch Netzwerke erlauben. Diese werden nur mit einer Menge von Knoten erfasst, die durch Kanten verbunden werden. Derzeit verfügbare Methoden beschränken sich hauptsächlich auf die deskriptive Analyse der Netzwerkstruktur. In der hier vorliegenden Arbeit werden verschiedene Ansätze für die Inferenz über Prozessen in komplexen Netzwerken vorgestellt. Diese Prozesse beeinflussen messbare Größen in Netzwerkknoten und werden durch eine Menge von Zufallszahlen beschrieben. Alle vorgestellten Methoden sind durch praktische Anwendungen motiviert, wie die Übertragung von Lebensmittelinfektionen, die Verbreitung von Zugverspätungen, oder auch die Regulierung von genetischen Effekten. Zunächst wird ein allgemeines dynamisches Metapopulationsmodell für die Verbreitung von Lebensmittelinfektionen vorgestellt, welches die lokalen Infektionsdynamiken mit den netzwerkbasierten Transportwegen von kontaminierten Lebensmitteln zusammenführt. Dieses Modell ermöglicht die effiziente Simulationen verschiedener realistischer Lebensmittelinfektionsepidemien. Zweitens wird ein explorativer Ansatz zur Ursprungsbestimmung von Verbreitungsprozessen entwickelt. Auf Grundlage einer netzwerkbasierten Redefinition der geodätischen Distanz können komplexe Verbreitungsmuster in ein systematisches, kreisrundes Ausbreitungsschema projiziert werden. Dies gilt genau dann, wenn der Ursprungsnetzwerkknoten als Bezugspunkt gewählt wird. Die Methode wird erfolgreich auf den EHEC/HUS Epidemie 2011 in Deutschland angewandt. Die Ergebnisse legen nahe, dass die Methode die aufwändigen Standarduntersuchungen bei Lebensmittelinfektionsepidemien sinnvoll ergänzen kann. Zudem kann dieser explorative Ansatz zur Identifikation von Ursprungsverspätungen in Transportnetzwerken angewandt werden. Die Ergebnisse von umfangreichen Simulationsstudien mit verschiedenstensten Übertragungsmechanismen lassen auf eine allgemeine Anwendbarkeit des Ansatzes bei der Ursprungsbestimmung von Verbreitungsprozessen in vielfältigen Bereichen hoffen. Schließlich wird gezeigt, dass kernelbasierte Methoden eine Alternative für die statistische Analyse von Prozessen in Netzwerken darstellen können. Es wurde ein netzwerkbasierter Kern für den logistischen Kernel Machine Test entwickelt, welcher die nahtlose Integration von biologischem Wissen in die Analyse von Daten aus genomweiten Assoziationsstudien erlaubt. Die Methode wird erfolgreich bei der Analyse genetischer Ursachen für rheumatische Arthritis und Lungenkrebs getestet. Zusammenfassend machen die Ergebnisse der vorgestellten Methoden deutlich, dass die Netzwerk-theoretische Analyse von Verbreitungsprozessen einen wesentlichen Beitrag zur Beantwortung verschiedenster Fragestellungen in unterschiedlichen Anwendungen liefern kann.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Neste trabalho, três técnicas para resolver numericamente problemas inversos de transporte de partículas neutras a uma velocidade para aplicações em engenharia nuclear são desenvolvidas. É fato conhecido que problemas diretos estacionários e monoenergéticos de transporte são caracterizados por estimar o fluxo de partículas como uma função-distribuição das variáveis independentes de espaço e de direção de movimento, quando os parâmetros materiais (seções de choque macroscópicas), a geometria, e o fluxo incidente nos contornos do domínio (condições de contorno), bem como a distribuição de fonte interior são conhecidos. Por outro lado, problemas inversos, neste trabalho, buscam estimativas para o fluxo incidente no contorno, ou a fonte interior, ou frações vazio em barras homogêneas. O modelo matemático usado tanto para os problemas diretos como para os problemas inversos é a equação de transporte independente do tempo, a uma velocidade, em geometria unidimensional e com o espalhamento linearmente anisotrópico na formulação de ordenadas discretas (SN). Nos problemas inversos de valor de contorno, dado o fluxo emergente em um extremo da barra, medido por um detector de nêutrons, por exemplo, buscamos uma estimativa precisa para o fluxo incidente no extremo oposto. Por outro lado, nos problemas inversos SN de fonte interior, buscamos uma estimativa precisa para a fonte armazenada no interior do domínio para fins de blindagem, sendo dado o fluxo emergente no contorno da barra. Além disso, nos problemas inversos SN de fração de vazio, dado o fluxo emergente em uma fronteira da barra devido ao fluxo incidente prescrito no extremo oposto, procuramos por uma estimativa precisa da fração de vazio no interior da barra, no contexto de ensaios não-destrutivos para aplicações na indústria. O código computacional desenvolvido neste trabalho apresenta o método espectronodal de malha grossa spectral Greens function (SGF) para os problemas diretos SN em geometria unidimensional para gerar soluções numéricas precisas para os três problemas inversos SN descritos acima. Para os problemas inversos SN de valor de contorno e de fonte interior, usamos a propriedade da proporcionalidade da fuga de partículas; ademais, para os problemas inversos SN de fração de vazio, oferecemos a técnica a qual nos referimos como o método físico da bissecção. Apresentamos resultados numéricos para ilustrar a precisão das três técnicas, conforme descrito nesta tese. / In this work, three techniques for numerically solving one-speed neutral particle inverse transport problems for nuclear engineering applications are developed. It is well known that direct steady-state monoenergetic transport problems are characterized by estimating the flux of particles as a distribution function of space and direction-of-motion independent variables, when the material parameters (cross sections), the geometry, and the incoming flux at the boundaries of the domain (boundary conditions), as well as the interior source distribution are known. Conversely, inverse problems, in this work, seek for estimates to the incident boundary flux, or interior source, or void fractions in homogeneous slabs. The mathematical model used for direct and inverse problems is the time-independent one-speed slab-geometry transport equation with linearly anisotropic scattering in the discrete ordinates (SN) formulation. In the boundary-value inverse problems, given the existing flux at one boundary of the slab, as measured by a neutron detector, for example, we seek for accurate estimate for the incident flux at the opposite boundary. On the other hand, in the interior source inverse SN problems, we seek for accurate estimate for the interior source stored within the slab for shielding purpose, given the exiting flux at the boundary of the slab. Furthermore, as with the void fraction inverse SN problems, given the exiting flux at one boundary of the slab due to prescribed incident flux at the opposite boundary, we seek for accurate estimate of the void fraction within the slab in the context of non-destructive testing applications in industry. The computer code developed in this work presents the coarse-mesh spectral Greens function (SGF) nodal method for direct SN problems in slab geometry to generate accurate numerical solutions to the three inverse SN problems described above. For the boundary-value and interior source inverse SN problems, we use the proportionality property of the leakage of particles; moreover, for the void fraction inverse SN problems, we offer the technique that we refer to as the physical bisection method. We present numerical results to illustrate the accuracy of the three techniques, as described in this dissertation.