Digital Commons Network^™

Spectral Material Classification Of Orbital Objects - Applying Machine Learning To Visible And Near-Infrared Spectral Scenes, Stephen M. Stumpf

Theses and Dissertations

MSI and HSI techniques allow users to determine the material composition of an object at range. To avoid labor-intensive manual classification, ML is used to determine the most likely material contained in a given pixel of a target image. Previous work primarily focuses on terrestrial applications; this paper extends these techniques into the low-illumination space situational awareness domain, which is of critical importance to national security. HSI datacubes are preprocessed with RL deconvolution as a means of reducing the effects of the optical PSF; then, statistical ML techniques, including k-NN, LDA, QDA, and SVMs are implemented as means of assigning …

Comparison Of Federated Kalman Filter And Autonomous Resilient Management Of All-Source Sensors (Armas) Framework For Fault Detection And Exclusion, Flavio Fernandes

Theses and Dissertations

In recent times, there is a great demand for resilient and robust PNT solutions. Current navigation systems rely heavily on GNSS to provide this solution. This dependence is a major concern and therefore it is prudent to use additional aids to provide the best solution possible. However, traditional methods to address this need require a nontrivial number of Kalman filters to maintain a fault-free solution. The federated filter approach provides an attractive alternative to the current solutions. In this thesis, we examine the use of the federated filter design to address this need in today’s integrated navigation systems. We compared …

Detection Algorithms And Clutter Metrics Comparison For Long Wave Infrared Point-Source Targets, Rudolf N. Vonniederhausern

Theses and Dissertations

In Infrared Search and Track (IRST) systems, clutter in the image hinders target detection especially in point-source target scenarios. Currently there is not a standardized metric for quantifying background clutter. Many clutter metrics have been proposed, but none have demonstrated effectiveness or compatibility for point-source targets. Factors such as environment conditions, detection algorithm, and correlation coefficient to probability of detection (PD) and false alarm (PFA) are the main considerations in determining the effectiveness of clutter metrics. Determining the most successful metric will increase Air Force Test and Evaluation (T&E) units’ capability by providing additional information on test conditions and environments …

Monocular Vision And Machine Learning For Pose Estimation, Quang Ngoc Tran

Theses and Dissertations

This thesis introduces a monocular vision-based approach for 6 DoF pose estimation on a known object. The proposed solution is to use a CNN to find known features of an object in an image. These known features, together with their known locations, are used by a PnP algorithm to estimate the pose of the target object with respect to the camera. The primary difficulty with CNN-based methods is needing to generate a large amount of training data to effectively create the CNN. To overcome this difficulty, a 3D model of the real-world object is created and used in a visualization …

Effectiveness Of A Timing Side Channel For Deriving Neural Network Depth, Matthew P. Weeks

Theses and Dissertations

From facial recognition on cell phones to vehicle traffic modeling for city planning, integrating ML models can be an expensive investment in resources. Protecting that investment is difficult, as information about the model and how it was built can be leaked through multiple channels, such as timing and memory access. In this thesis, one method of extracting data through a timing side-channel is examined across multiple hardware and software configurations to determine its reliability for general use. While attempting to determine the layer count of a target model solely from its inference time, the research determined that it is not …

Detection And Identification Of Covert Devices Using Infrared And Stacked Optics Detection, Michael A. Reyneke

Theses and Dissertations

This work investigates stacked optics detection methodologies to successfully detect and identify observational systems with a cyber-physical sensing tool, ODIN (Observational Device Identification Network). ODIN successfully detected the presence of stacked optics and LiDAR systems using night-vision devices with a 96.32% average accuracy rating, both overt and covertly placed, with objective lens diameters ranging from 17 mm to 50 mm at distances between 1 m to 5 m with and without commonly employed anti-reflective countermeasures. ODIN provides a foundation for counter- measure capabilities of NIR devices and stacked optical systems in stationary environments. Additionally, a pilot study on smartphone LiDAR …

Safe And Reliable Software And The Formal Verification Of Prim's Algorithm In Spark, Brian S. Wheelhouse

Theses and Dissertations

Despite evidence that formal verification helps produce highly reliable and secure code, formal methods, i.e., mathematically based tools and approaches for software and hardware verification, are not commonly used in software and hardware development. The limited emphasis on formal verification in software education and training suggests that many developers have never considered the benefits of formal verification. Despite the challenging nature of their mathematical roots, software verification tools have improved; making it easier than ever to verify software. SPARK, a programming language and a formal verification toolset, is of particular interest for the AFRL, and will be a primary focus …

Strategic Action Execution Through Regret Matching In Press Diplomacy, Leif D. White

Theses and Dissertations

To take most advantage of collaboration, negotiation is paramount to succeed in press Diplomacy. Humans use this construct to work towards self victory or sometimes towards an alternative strategic objective undefined in the game’s rules. To emulate this behavior, this thesis examines how to use communication to enable the victory or defeat of any other player in the game. This research develops a press Diplomacy agent, Lyre, that can work to attain these specific objectives in Diplomacy through the regret matching algorithm (RM). We also study how Lyre can begin Diplomacy with the goal to win, then shift strategies to …

Atmospheric Polarization And Solar Position As Kalman Updates To A Navigation Solution, Thomas J. Wheeler

Theses and Dissertations

Simulation and physical testing of a sensor that measures relative position of the Sun and polarization of light in the atmosphere as a navigational aid in a Kalman filter.

Temporal Convolutional Neural Networks For Device Discrimination, Ryan T. Zacher

Theses and Dissertations

This research uses TCN modifications to CNN classifiers, specifically dilation, causal padding, and residual blocks, to focus on temporal features and improve existing DNA analysis processes. Dilation significantly improves classification accuracy, even detecting features where no other models were able to. The smallest improvement shown is a 3-6dB reduction in SNR to reach a 90% classification accuracy. The maximum improvement is shown in the data-delivery region of the Cisco dataset, with the dilated model being the only model to exceed 90% classification accuracy. The other TCN modifications are shown to have no beneficial effect on the models.

Using Embedded Systems And Augmented Reality For Automated Aerial Refueling, Nathaniel A. Wilson

Theses and Dissertations

The goal of automated aerial refueling (AAR) is to extend the range of unmanned aircraft. Control latency prevents a human from remotely controlling the receiving aircraft as it approaches a tanker. To conform with the size, weight, and power constraints of a small unmanned aircraft, an AAR system must execute in real-time on an embedded platform. This thesis explores the timing and computational performance of a NVIDIA Jetson AGX Orin to a state-of-the-art general-purpose computer using existing AAR algorithms. It also constructs an augmented reality framework as an intermediate step for testing vision-based AAR algorithms between virtual testing and expensive …

Entering Hyperspace: Conditional Hyperspectral Reflectance Image Generation Using Convolutional Neural Networks, Bret M. Wagner

Theses and Dissertations

The field of remote sensing continues to expand in both commercial and defense domains. Development of advanced space based EOIR sensors has driven corresponding demand for sensor data for algorithm development. The AFIT Sensor and Scene Emulation Tool (ASSET) produces realistic synthetic electro-optical and infrared (EO/IR) data with absolute truth for the purpose of clutter suppression, target detection, and tracking algorithm development. This thesis presents a novel model which transforms panchromatic images into realistic hyperspectral reflectance images. The direct application of this model is to allows users to generate hyperspectral background images as inputs to ASSET allowing users to benefit …

Transition Analysis Of Innovative Technologies Into Military Applications, Cristian J. Henandez-Rivera

Theses and Dissertations

The Department of Defense (DoD) invests over 1 billion dollars annually in Small Business Innovation Research (SBIR) efforts. These SBIR efforts are similar to venture capital investments, where a transition beyond seed funding is considered a success. A baseline study of 2015-2018 Air Force SBIR investments indicates that 8.8% of the efforts secured long-term funding. Current data allows for an assessment of whether or not a project scores long-term funding; however, there is no measurement of whether or not the technology transitions to DoD usage. Transition is the rate at which SBIR investments are fielded or integrated into a military …

A Survey Of Barriers/Challenges To Improve Sbir Participation & Commercialization Success, Benjamin L. Berezin

Theses and Dissertations

The composition of the U.S. Defense Industrial Base (DIB) is changing. Within the last decade we have witnessed a decline in the percentage of new entrants, especially among Small Businesses. The Department of Defense’s base of small business participants experienced a drop of 23% from 2015-2021. New entrants provide novel capabilities and increase competition, spurring innovation essential for continued economic and military advantage. Small Businesses represent well over 40% of the Nation’s Gross Domestic Product and have vastly outpaced large firms at a magnitude of 16.5 times as many patents per small firm.

The Air Force deliberately targets funding for …

Protection Of Linear Assets In Arctic Regions Using Basic Expeditionary Airfield Resources (Polaar Bear), Christopher P. Lintz

Theses and Dissertations

In the 2018 United States National Defense Strategy, the Department of Defense mandated that forces are to be more dynamic and decentralized. The Arctic region was a key topic that was addressed. This means that in the future, it is possible that personnel will need to operate in the Arctic, away from the standard built up infrastructure, to enhance the capabilities of the Air Force and enable the power projection required for mission execution. When establishing a new location, water systems are one of the first requirements for setting up a temporary base infrastructure. However, the Air Force’s current expeditionary …

Topological Variability In Water Distribution Networks, James M. Anderson

Theses and Dissertations

Water distribution networks are critical infrastructure characterized by difficulties in their assessment and deteriorating performance due to aging components. Resilience analysis of networked infrastructure has replaced traditional risk analysis to focus on performance. Global Resilience Analysis can provide useful information to decision makers and system managers regarding repair and expansion of networks. Network performance has been found to be directly informed by network structure. This work leverages graph theory to assess network qualities that correlate with resiliency characteristics across 69 real world water networks. These networks are then grouped by their structural properties through k-means clustering and compared using parametric …

Environmental Trade-Offs Of Reverse Osmosis Water Purification Units (Rowpus) And Bottled Water, Caleb A. Boone

Theses and Dissertations

The Department of Defense (DoD) conducts many remote missions around the globe. As part of any remote basing strategy, potable water needs to be secured. Currently, there are three primary means of procuring potable water at remote locations: bottled water, on-site purification, or tie-in to existing, local infrastructure. The purpose of this study is to determine the environmental tradeoffs of bottled water and on-site treatment via a Reverse Osmosis Water Purification Unit (ROWPU), which uses multiple levels of filtration to make potable water from freshwater or saline water. A cradle-to- gate assessment was developed for both systems to create a …

Temporal And Spatial Variability Of Specific Energy Consumption For Atmospheric Water Generators, Anthony T. Brenes

Theses and Dissertations

Atmospheric Water Generators (AWG) produce potable water from the moisture in the air, providing a potentially viable water source in austere locations or emergency response scenarios. In this study, the operating constraints of three existing commercially available AWG devices are investigated, compared to historical weather data from across the continental United States. Utilizing linear regression modeling and weather station data for the years of 1985-2019, the monthly and spatial trends of energy demand to produce water from these devices are evaluated. Energy and water production efficiencies for the devices are highly dependent on environmental conditions with relative humidity and temperature …

Mission Dependency Weighted Water Distribution Networks, Payten A. Connally

Theses and Dissertations

How does the United States Air Force (USAF) assess and plan to replace their most critical drinking water infrastructure? The historical answer is to wait for it to break and then replace or repair the failed pipe. While this has been the process in the past, it is no longer a sustainable approach with resources and funding becoming more constrained in the public and private sectors, and aging assets approaching the end of their usable life. The USAF has taken the first step in asset management to identify their underground water lines, but they have not developed ways to convey …

Investigation Of Possible Alternatives To Fossil Fuels For The Dod In Indopacom, Terrence W. Caploe

Theses and Dissertations

Energy security, greenhouse gas (GHG) emissions, and geopolitical concerns in the south pacific require diversification and independence from legacy energy sources in the Indo-Pacific Combatant Command (INDOPACOM) area of operation (AO). The United States Government has placed mandates and directives to minimize the impacts of GHG on the climate. These orders require divestment from GHG producing fuel sources by 2050. This study compares the energy alternates to Jet Propulsion 8 (JP8) as Ammonia, Hydrogen, and Lithium-ion Batteries. The study uses Life Cycle Assessment (LCA) tools to determine the environmental impacts of various energy candidates in the South Pacific. These results …

A Systems Modeling Approach To Support Human-Agent Team Performance For Combat Identification, Clayton W. Couch

Theses and Dissertations

Combat Identification (CID) in an air-to-air combat context is a highly complex cognitive task that requires the operator to make rapid, high consequence decisions. To accomplish CID, fighter aircrew must attend to and perceive a broad range of information while concurrently building situation awareness (SA) and conducting other tasks. While existing automated agents are available to help fighter aircrew with this CID task, they are designed for a very narrow subset of the overall task and are not well suited for human-agent teaming. An interdependence analysis of the human operator and supporting machine agents conducted for this task support the …

An Analysis On Recommended United States Air Force Additive Manufacturing Construction Unit Type Code Package For Expeditionary Deployment, Caleb G. Dann

Theses and Dissertations

Additive Manufacturing Construction (AMC) is an emerging technology in the construction industry which utilizes 3-D printing to reduce costs, labor requirements and deviations in quality. This technology has the ability to rapidly produce repeatable construction projects while tailoring each to specific requirements through the use of 3-D designs. One of the primary objectives of the 2018 National Defense Strategy (NDS) is to continue meeting mission demands with a greater focus on the efficient use of resources. AMC has the ability to satisfy the requirements of this objective. The United States Air Force has begun initial print trials but have not …

Effects Of Level Of Effort Measurement In The Application Of Earned Value Management, James M. Demos

Theses and Dissertations

Major Air Force contracts are subject to overview utilizing Earned Value Management (EVM). EVM is flexible in its application through the adherence of guidelines rather than strict rules. Due to this method, there is concern for potential abuse of application through overuse of Level of Effort (LOE) as a measurement technique. There are current recommended practices and rules of thumb that suggest LOE should be limited to 15% of a program’s budget with no quantitative research to support this claim. This study examines how LOE is currently employed in ACAT I Air Force programs and what LOE’s impact is on …

Investigation Of Rhine Pointing As A Solution To The Aircraft Human Machine Interface Problem, Alexandra C. Dobranski, Samuel J. Medvec

Theses and Dissertations

The human machine interface in 5th generation aircraft has not evolved proportionally with advances in display size and data density. The traditional cursor slew method fails to rapidly relocate the cursor, especially on large displays. Previous studies at the Air Force Test Pilot School and Air Force Institute of Technology identified methods that have the potential to improve the human machine interface. This research expanded upon those studies by providing an assessment of head tracking technology as a secondary method of cursor manipulation. Specifically, this study examined the effects that visual feedback (visible and invisible head tracking cursors) and cursor …

The Kinetics Of Biocontaminant Inactivation: A Comparative Study With Bacillus Globigii And Bacillus Anthracis, Leigh M. Durden

Theses and Dissertations

Bacillus anthracis has been a biological threat for decades and after the 2001 terrorist attack via the U.S. Postal Service where five people died, there was heightened awareness and inquiry on the subject (Goel, 2015; Greenberg et al., 2010; Nicholson & Galeano, 2003; Spotts Whitney et al., 2003). The health risk to humans makes this biological agent, a Tier 1 agent and one of the most likely to be used in an attack (Anthrax as a Bioterrorism Weapon | CDC, n.d.; Driks, 2009; Rose & Rice, 2014). B. anthracis is one of most resistant and potent biological warfare agents as …

Method Development Biological Agent Personal Decontamination Effectiveness For Airman Battle Uniform Fabric Material: Ms2 Bacteriophage, Alisha Helm

Theses and Dissertations

This article presents a study that investigates the effectiveness of a common decontamination (decon) strategy used by Airmen in the United States Air Force who may find themselves in a densely populated area during an emergency evacuation. Ultimately, this study addresses the following questions: Is there a significant difference in the number of viral particles being re-aerosolized before and after the applied decon strategy, and is this difference significant enough to consider the decon strategy effective? The study entails using MS2 bacteriophage to contaminate swatches of Airman Battle Uniform (ABU) fabric. Swatches were secured to a vortex centered in the …

Introvert Personality Labor: A Unique Theoretical Construct That Describes The Effects Of Introverts Existing In The Extrovert Idea, Kathleen S. Hendershott

Theses and Dissertations

The Extrovert Ideal led to a society that has a favorable bias toward extroverts. Classrooms, workplaces, and the general public have been designed with extroverts in mind. Introverts, who make up more than half the world’s population, are forced to act in extroverted ways due in part to the extrovert ideal. Previous studies indicate introvert performance declines when working with more extroverted preferences, like open offices that favor group work, but fail to discuss the acting introverts are forced to do in workplaces created for their extroverted counterparts. The purpose of this study is to present a unique theoretical construct, …

Human-Machine Teaming Optimization: Creating A Measurement Tool For Operator Trust In Autonomous Systems, Kevin R. Hieronymus

Theses and Dissertations

Automation has become a critical component in the modern economy. Augmenting limited human attention resources allows for greater productivity in numerous businesses, tasks, and projects. As automated processes become more integrated into everyday life, the need to understand the relationship between human operators and automation becomes paramount. In the past, automation development relied on operator feedback which can vary depending on the operator’s familiarity with similar systems and acceptance of modern technology. This fact highlights the lack of a standardized measure that can quantify the amount of trust an individual displays in an automated system. This research establishes such a …

Climate-Informed Idf Curve Updates And Impact On Design Policy, Douglas C. Jaks

Theses and Dissertations

Stormwater systems across the United States (US) are aging with the American Society of Civil Engineers awarding a grade of D for the state of the infrastructure. Additionally, these aging systems are under-designed for climate-induced non-stationarity of rainfall. Several studies indicate a global increase of extreme rainfall events as a result of climate change, driving the need for future stormwater management designs that account for a changing climate. Specifically, this research generates climate-change informed intensity-duration-frequency (IDF) curve change factors through downscaled climate scenario change factors. While previous work has identified processes for predicting future IDF curves, this study generated curves, …

Civilian And Military Civil Engineer Mission In The Space Domain, Linda E. Kuster

Theses and Dissertations

Military and civil interest in space-based operations has increased dramatically in recent years due to the discovery of life sustaining properties such as water on Mars and advancements in cyber technology. Civilian sector discussions and research have centered on the establishment of permanent extraterrestrial infrastructure, while discussions from the military perspective have focused on providing reliable, resilient infrastructure, capable of withstanding cyber-based and kinetic attacks. Both perspectives account for known threats and sustainment methods required to ensure success in the space domain. With the existence of threats for the military and civilian missions, civil engineers will undoubtedly be critical to …