The mobile and wireless community has brought a significant growth of location-aware devices including smart phones, connected vehicles and IoT devices. The combination of location-aware sensing, data processing and wireless communication in these devices leads to the rapid development of mobile and location-aware applications. Meanwhile, user privacy is becoming an indispensable concern. These mobile and location-aware applications, which collect data from mobile sensors carried by users or vehicles, return valuable data collection services (e.g., health condition monitoring, traffic monitoring, and natural disaster forecasting) in real time. The sequential spatial-temporal data queries sent by users provide their location trajectory information. The location trajectory information not only contains users’ movement patterns, but also reveals sensitive attributes such as users’ personal habits, preferences, as well as home and work addresses. By exploring this type of information, the attackers can extract and sell user profile data, decrease subscribed data services, and even jeopardize personal safety. This research spans from the realization that user privacy is lost along with the popular usage of emerging location-aware applications. The outcome seeks to relive user location and trajectory privacy problems. First, we develop a pseudonym-based anonymity zone generation scheme against a strong adversary model in continuous location-based services. Based on a geometric transformation algorithm, this scheme generates distributed anonymity zones with personalized privacy parameters to conceal users’ real location trajectories. Second, based on the historical query data analysis, we introduce a query-feature-based probabilistic inference attack, and propose query-aware randomized algorithms to preserve user privacy by distorting the probabilistic inference conducted by attackers. Finally, we develop a privacy-aware mobile sensing mechanism to help vehicular users reduce the number of queries to be sent to the adversarial servers. In this mechanism, mobile vehicular users can selectively query nearby nodes in a peer-to-peer way for privacy protection in vehicular networks.

The Hilbert space of probability mass functions (pmf) is introduced in this thesis. A factorization method for multivariate pmfs is proposed by using the tools provided by the Hilbert space of pmfs. The resulting factorization is special for two reasons. First, it reveals the algebraic relations between the involved random variables. Second, it determines the conditional independence relations between the random variables. Due to the first property of the resulting factorization, it can be shown that channel decoders can be employed in the solution of probabilistic inference problems other than decoding. This approach might lead to new probabilistic inference algorithms and new hardware options for the implementation of these algorithms. An example of new inference algorithms inspired by the idea of using channel decoder for other inference tasks is a multiple-input multiple-output (MIMO) detection algorithm which has a complexity of the square-root of the optimum MIMO detection algorithm. Keywords: The Hilbert space of pmfs, factorization of pmfs, probabilistic inference, MIMO detection, Markov random fields iv

The fundamental question of how cells maintain their characteristic size remains open. Cell size measurements made through microscopic time-lapse imaging of microfluidic single cell cultivations have posed serious challenges to classical cell growth models and are supporting the development of newer, nuanced models that explain empirical findings better. Yet current models are limited, either to specific types of cells and/or to cell growth under specific microenvironmental conditions. Together with the fact that tools for robust analysis of said time-lapse images are not widely available as yet, the above-mentioned point presents an opportunity to progress the cell growth and size homeostasis discourse through generative, probabilistic modeling and analysis of the utility of different statistical estimation and inference techniques in recovering the parameters of the same. In this thesis, I present a novel Model Framework for simulating microfluidic single-cell cultivations with 36 different simulation modalities, each integrating dominant cell growth theories and generative modelling techniques. I also present a comparative analysis of how different Frequentist and Bayesian probabilistic inference techniques such as Nuisance Variable Elimination and Variational Inference work in the context of a case study of the estimation of a single model describing a microfluidic cell cultivation.

Increasing societal demand for automation has led to considerable efforts to control large-scale complex systems, especially in the area of autonomous intelligent control methods. The control system of a large-scale complex system needs to satisfy four system level requirements: robustness, flexibility, reusability, and scalability. Corresponding to the four system level requirements, there arise four major challenges. First, it is difficult to get accurate and complete information. Second, the system may be physically highly distributed. Third, the system evolves very quickly. Fourth, emergent global behaviors of the system can be caused by small disturbances at the component level. The Multi-Agent Based Control (MABC) method as an implementation of distributed intelligent control has been the focus of research since the 1970s, in an effort to solve the above-mentioned problems in controlling large-scale complex systems. However, to the author's best knowledge, all MABC systems for large-scale complex systems with significant uncertainties are problem-specific and thus difficult to extend to other domains or larger systems. This situation is partly due to the control architecture of multiple agents being determined by agent to agent coupling and interaction mechanisms. Therefore, the research objective of this dissertation is to develop a comprehensive, generalized framework for the control system design of general large-scale complex systems with significant uncertainties, with the focus on distributed control architecture design and distributed inference engine design. A Hybrid Multi-Agent Based Control (HyMABC) architecture is proposed by combining hierarchical control architecture and module control architecture with logical replication rings. First, it decomposes a complex system hierarchically; second, it combines the components in the same level as a module, and then designs common interfaces for all of the components in the same module; third, replications are made for critical agents and are organized into logical rings. This architecture maintains clear guidelines for complexity decomposition and also increases the robustness of the whole system. Multiple Sectioned Dynamic Bayesian Networks (MSDBNs) as a distributed dynamic probabilistic inference engine, can be embedded into the control architecture to handle uncertainties of general large-scale complex systems. MSDBNs decomposes a large knowledge-based system into many agents. Each agent holds its partial perspective of a large problem domain by representing its knowledge as a Dynamic Bayesian Network (DBN). Each agent accesses local evidence from its corresponding local sensors and communicates with other agents through finite message passing. If the distributed agents can be organized into a tree structure, satisfying the running intersection property and d-sep set requirements, globally consistent inferences are achievable in a distributed way. By using different frequencies for local DBN agent belief updating and global system belief updating, it balances the communication cost with the global consistency of inferences. In this dissertation, a fully factorized Boyen-Koller (BK) approximation algorithm is used for local DBN agent belief updating, and the static Junction Forest Linkage Tree (JFLT) algorithm is used for global system belief updating. MSDBNs assume a static structure and a stable communication network for the whole system. However, for a real system, sub-Bayesian networks as nodes could be lost, and the communication network could be shut down due to partial damage in the system. Therefore, on-line and automatic MSDBNs structure formation is necessary for making robust state estimations and increasing survivability of the whole system. A Distributed Spanning Tree Optimization (DSTO) algorithm, a Distributed D-Sep Set Satisfaction (DDSSS) algorithm, and a Distributed Running Intersection Satisfaction (DRIS) algorithm are proposed in this dissertation. Combining these three distributed algorithms and a Distributed Belief Propagation (DBP) algorithm in MSDBNs makes state estimations robust to partial damage in the whole system. Combining the distributed control architecture design and the distributed inference engine design leads to a process of control system design for a general large-scale complex system. As applications of the proposed methodology, the control system design of a simplified ship chilled water system and a notional ship chilled water system have been demonstrated step by step. Simulation results not only show that the proposed methodology gives a clear guideline for control system design for general large-scale complex systems with dynamic and uncertain environment, but also indicate that the combination of MSDBNs and HyMABC can provide excellent performance for controlling general large-scale complex systems.

This thesis incorporates three studies that analyze how information is presented in various contexts, how these different modes of presentation affect decision makers’ perceptions and how to improve communication of information to eliminate distortions. Chapter 1 features a scenario where experts make inferences given different presentations of a regression analysis, a widely used statistical method. Chapter 2 introduces an experience-based presentation mode and tests its effectiveness on decision makers with varying statistical abilities, across multiple probabilistic tasks. Chapter 3 demonstrates the effects of presentation mode and the number of available options on the amounts and distributions of donations to NGOs and their campaigns. Overall, the findings suggest that presentation mode is an important determinant of judgments and decisions, and they can be restructured to improve the accuracy of inferences. / Esta tesis incluye tres estudios que analizan cómo la información se presenta en varios contextos, cómo estos diferentes modos de presentación influyen las percepciones de los tomadores de decisiones y cómo mejorar la comunicación de la información para eliminar distorsiones. Capítulo 1 analiza una situación donde expertos hacen inferencias utilizando diferentes presentaciones de un análisis de regresión, un método de estadística ampliamente utilizado. Capítulo 2 introduce un modo de presentación basado en experiencia y pone a prueba su eficacia a través de múltiples problemas probabilísticas. Capítulo 3 demuestra los efectos del modo de presentación y el número de opciones disponibles sobre las cantidades y la distribución de las donaciones a las ONG y sus campañas. En general, los resultados sugieren que el modo de presentación es un determinante importante de las percepciones y decisiones, y pueden ser reestructuradas para mejorar la precisión de las inferencias.

With the rapid development of information technology, data availability is improved greatly. Data may be accessed at anytime by people from any location. However,threats to data security and privacy arise as one of the major problems of the development of information systems, especially those information systems which contain personal information. An association database is a personal information system which contains associations between persons. In this thesis, we identify the security and privacy problems of association databases. In order to solve these problems, we propose a new security and privacy model for association databases equipped with both direct access control and inference control mechanisms. In this model, there are multiple criteria including, not only confidentiality, but also privacy and other aspects of security to classify the association. The methods used in the system are: The direct access control method is based on the mandatory model; The inference control method is based on both logic reasoning and probabilistic reasoning (Belief Networks). My contributions to security and privacy model for association databases and to inference control in the model include: Identification of security and privacy problems in association databases; Formal definition of association database model; Representation association databases as directed multiple graphs; Development of axioms for direct access control; Specification of the unauthorized inference problem; A method for unauthorized inference detection and control that includes: Development of logic inference rules and probabilistic inference rule; Application of belief networks as a tool for unauthorized inference detection and control.

With the rapid development of information technology, data availability is improved greatly. Data may be accessed at anytime by people from any location. However,threats to data security and privacy arise as one of the major problems of the development of information systems, especially those information systems which contain personal information. An association database is a personal information system which contains associations between persons. In this thesis, we identify the security and privacy problems of association databases. In order to solve these problems, we propose a new security and privacy model for association databases equipped with both direct access control and inference control mechanisms. In this model, there are multiple criteria including, not only confidentiality, but also privacy and other aspects of security to classify the association. The methods used in the system are: The direct access control method is based on the mandatory model; The inference control method is based on both logic reasoning and probabilistic reasoning (Belief Networks). My contributions to security and privacy model for association databases and to inference control in the model include: Identification of security and privacy problems in association databases; Formal definition of association database model; Representation association databases as directed multiple graphs; Development of axioms for direct access control; Specification of the unauthorized inference problem; A method for unauthorized inference detection and control that includes: Development of logic inference rules and probabilistic inference rule; Application of belief networks as a tool for unauthorized inference detection and control.

Les réseaux de télécommunication doivent être fiables et robustes pour garantir la haute disponibilité des services. Les opérateurs cherchent actuellement à automatiser autant que possible les opérations complexes de gestion des réseaux, telles que le diagnostic de pannes.Dans cette thèse nous nous sommes intéressés au diagnostic automatique de pannes dans les réseaux d'accès optiques de l'opérateur Orange. L'outil de diagnostic utilisé jusqu'à présent, nommé DELC, est un système expert à base de règles de décision. Ce système est performant mais difficile à maintenir en raison, en particulier, du très grand volume d'informations à analyser. Il est également impossible de disposer d'une règle pour chaque configuration possible de panne, de sorte que certaines pannes ne sont actuellement pas diagnostiquées.Dans cette thèse nous avons proposé une nouvelle approche. Dans notre approche, le diagnostic des causes racines des anomalies et alarmes observées s'appuie sur une modélisation probabiliste, de type réseau bayésien, des relations de dépendance entre les différentes alarmes, compteurs, pannes intermédiaires et causes racines au niveau des différents équipements de réseau. Ce modèle probabiliste a été conçu de manière modulaire, de façon à pouvoir évoluer en cas de modification de l'architecture physique du réseau.Le diagnostic des causes racines des anomalies est effectué par inférence, dans le réseau bayésien, de l'état des noeuds non observés au vu des observations (compteurs, alarmes intermédiaires, etc...) récoltées sur le réseau de l'opérateur. La structure du réseau bayésien, ainsi que l'ordre de grandeur des paramètres probabilistes de ce modèle, ont été déterminés en intégrant dans le modèle les connaissances des experts spécialistes du diagnostic sur ce segment de réseau. L'analyse de milliers de cas de diagnostic de pannes a ensuite permis de calibrer finement les paramètres probabilistes du modèle grâce à un algorithme EM (Expectation Maximization).Les performances de l'outil développé, nommé PANDA, ont été évaluées sur deux mois de diagnostic de panne dans le réseau GPON-FTTH d'Orange en juillet-août 2015. Dans la plupart des cas, le nouveau système, PANDA, et le système en production, DELC, font un diagnostic identique. Cependant un certain nombre de cas sont non diagnostiqués par DELC mais ils sont correctement diagnostiqués par PANDA. Les cas pour lesquels les deux systèmes émettent des diagnostics différents ont été évalués manuellement, ce qui a permis de démontrer dans chacun de ces cas la pertinence des décisions prises par PANDA. / Telecommunication networks must be reliable and robust to ensure high availability of services. Operators are currently searching to automate as much as possible, complex network management operations such as fault diagnosis.In this thesis we are focused on self-diagnosis of failures in the optical access networks of the operator Orange. The diagnostic tool used up to now, called DELC, is an expert system based on decision rules. This system is efficient but difficult to maintain due in particular to the very large volume of information to analyze. It is also impossible to have a rule for each possible fault configuration, so that some faults are currently not diagnosed.We proposed in this thesis a new approach. In our approach, the diagnosis of the root causes of malfunctions and alarms is based on a Bayesian network probabilistic model of dependency relationships between the different alarms, counters, intermediate faults and root causes at the level of the various network component. This probabilistic model has been designed in a modular way, so as to be able to evolve in case of modification of the physical architecture of the network. Self-diagnosis of the root causes of malfunctions and alarms is made by inference in the Bayesian network model of the state of the nodes not observed in view of observations (counters, alarms, etc.) collected on the operator's network. The structure of the Bayesian network, as well as the order of magnitude of the probabilistic parameters of this model, were determined by integrating in the model the expert knowledge of the diagnostic experts on this segment of the network. The analysis of thousands of cases of fault diagnosis allowed to fine-tune the probabilistic parameters of the model thanks to an Expectation Maximization algorithm. The performance of the developed probabilistic tool, named PANDA, was evaluated over two months of fault diagnosis in Orange's GPON-FTTH network in July-August 2015. In most cases, the new system, PANDA, and the system in production, DELC, make an identical diagnosis. However, a number of cases are not diagnosed by DELC but are correctly diagnosed by PANDA. The cases for which self-diagnosis results of the two systems are different were evaluated manually, which made it possible to demonstrate in each of these cases the relevance of the decisions taken by PANDA.

Probabilistic inference, especially in the Bayesian framework, is a foundation for quantifying uncertainties in geophysical inversion applications. However, due to the presence of high-dimensional datasets and the large-scale nature of geophysical inverse problems, the applicability and scalability of probabilistic inference face significant challenges for such applications. This thesis is dedicated to improving the probabilistic inference algorithms' scalability and demonstrating their applicability for large-scale geophysical inversion applications. In this thesis, I delve into three leading applied approaches in computing the Bayesian posterior distribution in geophysical inversion applications: Laplace's approximation, Markov chain Monte Carlo (MCMC), and variational Bayesian inference. The first approach, Laplace's approximation, is the simplest form of approximation for intractable Bayesian posteriors. However, its accuracy relies on the estimation of the posterior covariance matrix. I study the visualization of the misfit landscape in low-dimensional subspace and the low-rank approximations of the covariance for full waveform inversion (FWI). I demonstrate that a non-optimal Hessian's eigenvalues truncation for the low-rank approximation will affect the approximation accuracy of the standard deviation, leading to a biased statistical conclusion. Furthermore, I also demonstrate the propagation of uncertainties within the Bayesian physics-informed neural networks for hypocenter localization applications through this approach. For the MCMC approach, I develop approximate Langevin MCMC algorithms that provide fast sampling at efficient computational costs for large-scale Bayesian FWI; however, this inflates the variance due to asymptotic bias. To account for this asymptotic bias and assess their sample quality, I introduce the kernelized Stein discrepancy (KSD) as a diagnostic tool. When larger computational resources are available, exact MCMC algorithms (i.e., with a Metropolis-Hastings criterion) should be favored for an accurate posterior distribution statistical analysis. For the variational Bayesian inference, I propose a regularized variational inference framework that performs posterior inference by implicitly regularizing the Kullback-Leibler divergence loss with a deep denoiser through a Plug-and-Play method. I also developed Plug-and-Play Stein Variational Gradient Descent (PnP-SVGD), a novel algorithm to sample the regularized posterior distribution. The PnP-SVGD demonstrates its ability to produce high-resolution, trustworthy samples representative of the subsurface structures for a post-stack seismic inversion application.

No description available.