Physical Sciences and Mathematics Commons^™

Robust Interventions In Network Epidemiology, Erik Weis

Graduate College Dissertations and Theses

Which individual should we vaccinate to minimize the spread of a disease? Designing optimal interventions of this kind can be formalized as an optimization problem on networks, in which we have to select a budgeted number of dynamically important nodes to receive treatment that optimizes a dynamical outcome. Describing this optimization problem requires specifying the network, a model of the dynamics, and an objective for the outcome of the dynamics. In real-world contexts, these inputs are vulnerable to misspecification---the network and dynamics must be inferred from data, and the decision-maker must operationalize some (potentially abstract) goal into a mathematical objective …

Compact Representations Of Uncertainty In Clustering, Craig Stuart Greenberg

Doctoral Dissertations

Flat clustering and hierarchical clustering are two fundamental tasks, often used to discover meaningful structures in data, such as subtypes of cancer, phylogenetic relationships, taxonomies of concepts, and cascades of particle decays in particle physics. When multiple clusterings of the data are possible, it is useful to represent uncertainty in clustering through various probabilistic quantities, such as the distribution over partitions or tree structures, and the marginal probabilities of subpartitions or subtrees. Many compact representations exist for structured prediction problems, enabling the efficient computation of probability distributions, e.g., a trellis structure and corresponding Forward-Backward algorithm for Markov models that model …

Increasing The Value Of Information During Planning In Uncertain Environments, Gaurab Pokharel

Honors Papers

Prior studies have demonstrated that for many real-world problems, POMDPs can be solved through online algorithms both quickly and with near optimality [10, 8, 6]. However, on an important set of problems where there is a large time delay between when the agent can gather information and when it needs to use that information, these solutions fail to adequately consider the value of information. As a result, information gathering actions, even when they are critical in the optimal policy, will be ignored by existing solutions, leading to sub-optimal decisions by the agent. In this research, we develop a novel solution …

Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo

Theses and Dissertations

Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …

Establishing Topological Data Analysis: A Comparison Of Visualization Techniques, Tanmay J. Kotha

USF Tampa Graduate Theses and Dissertations

When visualizing data, we would like to convey both the data and the uncertainty associated with it. There are many incentives to do this, ranging from hurricane path projection to geographical surveys. Important decision making tasks rely upon humans perceiving a clear picture of the data and having confidence in their decisions. Topological Data Analysis has the potential to visualize the data as features or hierarchies in ways that are familiar to human intuition, and thus could help us convey the variation associated with uncertainty.

In this thesis, we evaluate four visualization techniques: color maps, isocontours, Reeb graphs, and persistence …

Relationship Between Risk Identification, Risk Response, And Project Success, Marsha Marinich

Walden Dissertations and Doctoral Studies

AbstractProjects are used to implement the organization's strategic goals, but high failure rates reduce projects' effectiveness in successfully achieving goals. High failure rates reduce project managers’ effectiveness of projects in successfully achieving goals. Senior leaders and project managers are unable to deliver successful projects due to unmanaged risks. Grounded in expected utility theory, the purpose of this quantitative correlational study was to examine the relationship between risk identification, risk responses, and project success. A survey was created in SurveyMonkey® and distributed on LinkedIn. Survey responses were analyzed from 71 project managers with at least five years of experience in Washington, …

Uncertainty Learning In Subjective Logic And Pattern Discovery In Network Data, Adilijiang Alimu

Legacy Theses & Dissertations (2009 - 2024)

Uncertainty caused by unreliable or insufficient data and vulnerable machine learning models

Proactive And Reactive Resource/Task Allocation For Agent Teams In Uncertain Environments, Pritee Agrawal

Dissertations and Theses Collection (Open Access)

Synergistic interactions between task/resource allocation and multi-agent coordinated planning/assignment exist in many problem domains such as trans- portation and logistics, disaster rescue, security patrolling, sensor networks, power distribution networks, etc. These domains often feature dynamic environments where allocations of tasks/resources may have complex dependencies and agents may leave the team due to unforeseen conditions (e.g., emergency, accident or violation, damage to agent, reconfiguration of environment).

Uncertainty Estimation Of Deep Neural Networks, Chao Chen

Theses and Dissertations

Normal neural networks trained with gradient descent and back-propagation have received great success in various applications. On one hand, point estimation of the network weights is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. On the other hand, exact Bayesian neural network methods are intractable and non-applicable for real-world applications. To date, approximate methods have been actively under development for Bayesian neural networks, including but not limited to: stochastic variational methods, Monte Carlo dropouts, and expectation propagation. Though these methods are applicable for current large networks, there are limits to these approaches with either underestimation …

Decision Making For Dynamic Systems Under Uncertainty: Predictions And Parameter Recomputations, Leobardo Valera

Open Access Theses & Dissertations

In this Thesis, we are interested in making decision over a model of a dynamic system. We want to know, on one hand, how the corresponding dynamic phenomenon unfolds under different input parameters (simulations). These simulations might help researchers to design devices with a better performance than the actual ones. On the other hand, we are also interested in predicting the behavior of the dynamic system based on knowledge of the phenomenon in order to prevent undesired outcomes. Finally, this Thesis is concerned with the identification of parameters of dynamic systems that ensure a specific performance or behavior.

Understanding the …

Combining Interval And Probabilistic Uncertainty In Engineering Applications, Andrew Martin Pownuk

Open Access Theses & Dissertations

In many practical application, we process measurement results and expert estimates. Measurements and expert estimates are never absolutely accurate, their result are slightly different from the actual (unknown) values of the corresponding quantities. It is therefore desirable to analyze how this measurement and estimation inaccuracy affects the results of data processing. There exist numerous methods for estimating the accuracy of the results of data processing under different models of measurement and estimation inaccuracies: probabilistic, interval, and fuzzy. To be useful in engineering applications, these methods should provide accurate estimate for the resulting uncertainty, should not take too much computation time, …

Propagation Of Interval And Probabilistic Uncertainty In Cyberinfrastructure-Related Data Processing And Data Fusion, Christian Servin

Open Access Theses & Dissertations

Data uncertainty affects the results of data processing. So, it is necessary to find out how the data uncertainty propagates into the uncertainty of the results of data processing. This problem is especially important when cyberinfrastructure enables us to process large amounts of heterogeneous data. In the ideal world, we should have an accurate description of data uncertainty, and well-justified efficient algorithms to propagate this uncertainty. In practice, we are often not yet in this ideal situation: the description of uncertainty is often only approximate, and the algorithms for uncertainty propagation are often not well-justified and not very computationally efficient. …

Partial Orders For Representing Uncertainty, Causality And Decision Making: General Properties, Operations, And Algorithms, Francisco Adolfo Zapata

Open Access Theses & Dissertations

One of the main objectives of science and engineering is to help people select the most beneficial decisions. To make these decisions, we must know people's preferences, we must have the information about different possible consequences of different decisions. Since information is never absolutely accurate and precise, we must also have information about the degree of certainty of different parts on information. All these types of information naturally lead to partial orders:

- For preferences, a <= b means that b is preferable to a. This relation is used in decision theory.

- For events, a <= b means that a can influence b. This causality relation is one of the fundamental notions of physics, especially of physics of space-time.

* For uncertain statements, a <= b means that a is less certain than b. This relation is used in logics describing uncertainty, such as fuzzy logic.

In each of these areas, there is abundant research about studying the corresponding partial orders. …

A Geospatial Based Decision Framework For Extending Marssim Regulatory Principles Into The Subsurface, Robert Nathan Stewart

Doctoral Dissertations

The Multi-Agency Radiological Site Survey Investigation Manual (MARSSIM) is a regulatory guidance document regarding compliance evaluation of radiologically contaminated soils and buildings (USNRC, 2000). Compliance is determined by comparing radiological measurements to established limits using a combination of hypothesis testing and scanning measurements. Scanning allows investigators to identify localized pockets of contamination missed during sampling and allows investigators to assess radiological exposure at different spatial scales. Scale is important in radiological dose assessment as regulatory limits can vary with the size of the contaminated area and sites are often evaluated at more than one scale (USNRC, 2000). Unfortunately, scanning is …

Improving The Analyst And Decision-Maker’S Perspective Through Uncertainty Visualization, Evan T. Watkins

Theses and Dissertations

This thesis constructs the Taxonomy of Uncertainty and an approach for enhancing the information in decision support systems. The hierarchical categorization of numerous causes for uncertainty defines the taxonomy, which fostered the development of a technique for visualizing uncertainty. This technique is fundamental to expressing the multi-dimensional uncertainty that can be associated with any object. By including and intuitively expressing uncertainty, the approach facilitates and enhances intuition and decision-making without undue information overload. The resulting approach for enhancing the information involves recording uncertainty, identifying the relevant items, computing and visualizing uncertainty, and providing interaction with the selection of uncertainty. A …

A Methodology For The Selection Of A Paradigm Of Reasoning Under Uncertainty In Expert System Development, Vivian Campbell

Theses: Doctorates and Masters

The aim of this thesis is to develop a methodology for the selection of a paradigm of reasoning under uncertainty for the expert system developer. This is important since practical information on how to select a paradigm of reasoning under uncertainty is not generally available. The thesis explores the role of uncertainty in an expert system and considers the process of reasoning under uncertainty. The possible sources of uncertainty are investigated and prove to be crucial to some aspects of the methodology. A variety of Uncertainty Management Techniques (UMTs) are considered, including numeric, symbolic and hybrid methods. Considerably more information …

On Unifying Time And Uncertainty: The Probabilistic Temporal Network, Joel D. Young

Theses and Dissertations

Complex real-world systems consist of collections of interacting processes/events. These processes change over time in response to both internal and external stimuli as well as to the passage of time. Many domains such as real-time systems diagnosis, (mechanized) story understanding, planning and scheduling, and financial forecasting require the capability to model complex systems under a unified framework to deal with both time and uncertainty. Existing uncertainty representations and existing temporal models already provide rich languages for capturing uncertainty and temporal information, respectively. Unfortunately, these partial solutions have made it extremely difficult to unify time and uncertainty in a way that …