Computer Sciences Commons^™

A Method To Evaluate The Impact Of Assistive Displays On The Comfort And Safety Of Driving In Low Visibility Conditions, Hussain Talal Alatiyyah

Theses and Dissertations

Natural phenomena may affect car drivers in terms of having a clear view. It may hinder or distract the driver’s eyesight from essential objects, such as traffic signs, people, or other obstacles in the street. A poor view for a driver could cause accidents that lead to significant harm. Fog is one of these natural phenomena that could impact a driver’s concentration. This study aims to test a methodology for evaluating the use of an assistive computer display, especially in fog situations. An experiment is performed with participants who perform simulated driving under controlled fog conditions with or without an …

Cross-Gender And 1-To-N Face Recognition Error Analysis Of Gender Misclassified Images, Paloma Vela Achu

Theses and Dissertations

A number of recent research studies have shown that face recognition accuracy is meaningfully worse for females than males. Gender classification algorithms also perform worse: one commercial classifier gives a 7% error rate for African-American females vs. 0.5% for Caucasian males. In response to these observations, we consider one primary question: do errors in gender classification lead to errors in facial recognition? We approach this question by focusing on two main areas (1) do gender-misclassified images generate higher similarity scores with different individuals from the false-gender category versus their true-gender category? (2) What is the impact of gender misclassified images …

Concurrent Identification, Characterization, And Reconstruction Of Protein Structure And Mixed-Mode Dynamics From Rdc Data Using Redcraft, Hanin Rafiq Omar

Theses and Dissertations

A complete understanding of the structure-function relationship of proteins requires an analysis of their dynamic behaviors and the static structure. However, all current approaches to studying dynamics in proteins have their shortcomings. A conceptually attractive and alternative approach simultaneously characterizes a protein's structure and its intrinsic dynamics⁠. Ideally, such an approach could solely rely on RDC data-carrying both structural and dynamical information. The major bottleneck in utilizing RDC data in recent years has been attributed to a lack of RDC analysis tools capable of extracting the pertinent information embedded within this complex data source.

Here we present a comprehensive strategy …

Automata-Theoretic Approaches To Planning In Robotics: Combinatorial Filter Minimization, Planning To Chronicle, Temporal Logic Planning With Soft Specifications, And Sensor Selection For Detecting Deviations From A Planned Itinerary, Hazhar Rahmani

Theses and Dissertations

In this dissertation, we present a collection of new planning algorithms that enable robots to achieve complex goals, beyond simple point-to-point path planning, using automata-theoretic methods, and we consider the filter minimization (FM) problem and a variant of it, filter partitioning minimization (FPM) problem, which aims to minimize combinatorial filters, used for filtering and automata-theoretic planning in systems with discrete sensor data. We introduce a new variant of bisimulation, compatibility, and using this notion we identify several classes of filters for which FM or FPM is solvable in polynomial time, and propose several integer linear programming (ILP) formulations …

On Providing Efficient Real-Time Solutions To Motion Planning Problems Of High Complexity, Marios Xanthidis

Theses and Dissertations

The holy grail of robotics is producing robotic systems capable of efficiently executing all the tasks that are hard, or even impossible, for humans. Humans, undoubtedly, from both a hardware and software perspective, are extremely complex systems capable of executing many complicated tasks. Thus, the complexity of many state-of-the-art robotic systems is also expected to progressively increase, with the goal to match or even surpass human abilities. Recent developments have emphasized mostly hardware, providing highly complex robots with exceptional capabilities. On the other hand, they have illustrated that one important bottleneck of realizing such systems as a common reality is …

Graph Neural Network And Phylogenetic Tree Construction, Gaofeng Pan

Theses and Dissertations

Deep Learning had been widely used in computational biology research in past few years. A great amount of deep learning methods were proposed to solve bioinformatics problems, such as gene function prediction, protein interaction classification, drug effects analysis, and so on; most of these methods yield better solutions than traditional computing methods. However, few methods were proposed to solve problems encountered in evolutionary biology research. In this dissertation, two neural network learning methods are proposed to solve the problems of genome location prediction and median genome generation encountered in phylogenetic tree construction; the ability of neural network learning models on …

Deep Learning Based Generative Materials Design, Yong Zhao

Theses and Dissertations

Discovery of novel functional materials is playing an increasingly important role in many key industries such as lithium batteries for electric vehicles and cell phones. However experimental tinkering of existing materials or Density Functional Theory (DFT) based screening of known crystal structures, two of the major current materials design approaches, are both severely constrained by the limited scale (around 250,000 in ICSD database) and diversity of existing materials and the lack of a sufficient number of materials with annotated properties. How to generate a large number of physically feasible, stable, and synthesizable crystal materials and build accurate property prediction models …

Confronting Barriers To Human-Robot Cooperation: Balancing Efficiency And Risk In Machine Behavior, Tim Whiting

Theses and Dissertations

In strategically rich settings in which machines and people do not fully share the same preferences, machines must learn to cooperate and compromise with people to establish mutually successful relationships. However, designing machines that effectively cooperate with people in these settings is difficult due to a variety of technical and psychological challenges. To better understand these challenges, we conducted a series of user studies in which we investigated human-human, robot-robot, and human-robot cooperation in a simple, yet strategically rich, resource-sharing scenario called the Block Dilemma, a game in which players must balance fairness, efficiency, and risk. While both human-human and …

Symbolic Semantic Memory In Transformer Language Models, Robert Kenneth Morain

Theses and Dissertations

This paper demonstrates how transformer language models can be improved by giving them access to relevant structured data extracted from a knowledge base. The knowledge base preparation process and modifications to transformer models are explained. We evaluate these methods on language modeling and question answering tasks. These results show that even simple additional knowledge augmentation leads to a reduction in validation loss by 73%. These methods also significantly outperform common ways of improving language models such as increasing the model size or adding more data.

Malware Detection Using Electromagnetic Side-Channel Analysis, Matthew A. Bergstedt

Theses and Dissertations

Many physical systems control or monitor important applications without the capacity to monitor for malware using on-device resources. Thus, it becomes valuable to explore malware detection methods for these systems utilizing external or off-device resources. This research investigates the viability of employing EM SCA to determine whether a performed operation is normal or malicious. A Raspberry Pi 3 was set up as a simulated motor controller with code paths for a normal or malicious operation. While the normal path only calculated the motor speed before updating the motor, the malicious path added a line of code to modify the calculated …

Investigating Collaboration In Software Reverse Engineering, Allison M. Wong

Theses and Dissertations

Reverse engineering (RE) is a rigorous process of exploration and analysis to support software design recovery and exploit development. The process is often conducted in teams to divide the workload and take full advantage of engineers' individual expertise and strengths. Collaboration in RE requires versatile and reliable tools that can match the environment's unpredictable and fluid nature. While studies on collaborative software development have indicated common best practices and implementations, similar standards have not been explored in reverse engineering. This research conducts semi-structured interviews with reverse engineering experts to understand their needs and solutions while working in a team. The …

Automated Reconstructions For The Digital Forensic Examiner Workflow, Ryan P. Montgomery

Theses and Dissertations

One product of a digital forensics examination is a reconstruction of events recorded in the media. A reconstruction places all of the case relevant trace into temporal, identity and associative relationships. Creating this reconstruction is a manual and time consuming process for the examiner. This thesis presents AIER. AIER integrates automation, abstraction and visualization into the Autopsy forensic software to improve the reconstruction process. The integration utilizes a custom Autopsy ingest module to extract and abstract artifact data and an interactive graph-based timeline visualization module. These improvements to the forensic examiner workflow are evaluated through a series of use cases.

Performance Of Heterogeneous Multi-Agent Systems With Applications In Combined Arms, Robert J. Wilson

Theses and Dissertations

Multi-agent systems show great potential for solving problems in complex and dynamic domains. Such systems comprise multiple individual entities called agents. Agents possessing the same behavior or physical form are called homogeneous while agents which differ in these respects are termed heterogeneous. The overall behavior of the system emerges from the many interactions of its component agents. Most multi-agent systems research to date focuses on systems of homogeneous agents, but recent work suggests that heterogeneous agents may improve system performance in certain tasks. This research examines the impact of heterogeneity on multi-agent system effectiveness and investigates the application of multi-agent …

Identifying Characteristics For Success Of Robotic Process Automations, Charles M. Unkrich

Theses and Dissertations

In the pursuit of digital transformation, the Air Force creates digital airmen. Digital airmen are robotic process automations designed to eliminate the repetitive high-volume low-cognitive tasks that absorb so much of our Airmen's time. The automation product results in more time to focus on tasks that machines cannot sufficiently perform data analytics and improving the Air Force's informed decision-making. This research investigates the assessment of potential automation cases to ensure that we choose viable tasks for automation and applies multivariate analysis to determine which factors indicate successful projects. The data is insufficient to provide significant insights.

Double Cone Flow Field Reconstruction Between Mach 4 And 12 Using Machine Learning Techniques, Trevor A. Toros

Theses and Dissertations

No abstract provided.

Securing Infiniband Networks With End-Point Encryption, Noah B. Diamond

Theses and Dissertations

The NVIDIA-Mellanox Bluefield-2 is a 100 Gbps high-performance network interface which offers hardware offload and acceleration features that can operate directly on network traffic without routine involvement from the ARM CPU. This allows the ARM multi-core CPU to orchestrate the hardware to perform operations on both Ethernet and RDMA traffic at high rates rather than processing all the traffic directly. A testbed called TNAP was created for performance testing and a MiTM verification process called MiTMVMP is used to ensure proper network configuration. The hardware accelerators of the Bluefield-2 support a throughput of nearly 86 Gbps when using IPsec to …

Evaluating Semantic Matching Techniques For Technical Documents, Rain F. Dartt

Theses and Dissertations

Machine learning models that employ NLP techniques have become more widely accessible, making them an attractive solution for text and document classification tasks traditionally accomplished by humans. Two such use cases are matching the specialized experience required for a job to statements in applicant resumes, and finding and labelling clauses in legal contracts The AFMC has an immediate need for solutions to civilian hiring. However, there is currently no truth data to validate against. A similar task is contract understanding for which there is the CUAD, a recently published repository of 510 contracts manually labelled by legal experts. The presented …

Exploiting The Iot Through Network-Based Covert Channels, Kyle S. Harris

Theses and Dissertations

Information leaks are a top concern to industry and government leaders. The IoT is a technology capable of sensing real-world events. A method for exfiltrating data from these devices is by covert channel. This research designs a novel IoT CTC without the need for inter-packet delays to encode data. Instead, it encodes data within preexisting network information, namely ports or addresses. Additionally, the CTC can be implemented in two different modes: Stealth and Bandwidth. Performance is measured using throughput and detectability. The Stealth methods mimic legitimate traffic captures while the Bandwidth methods forgo this approach for maximum throughput. Detection results …

Dds-Cerberus: Improving Security In Dds Middleware Using Kerberos Tickets, Andrew T. Park

Theses and Dissertations

The military deploys many IoT in battlefield operations to provide information on terrain and enemy combatants. It also deploys automated robots or UAVs where securing and trusting collected data is essential. Choosing the middleware that handles this message transfer is crucial for real-time operations. Networks with multiple entities, including IoT devices, UAVs, and small computers, require robust middleware facilitating message sending in real-time. Ideally, the middleware would provide QoS to handle lost packets and retransmissions in lossy environments, especially between low-power machines. DDS is a middleware that implements real-time and QoS capabilities by sending messages, not based on endpoints but …

Exploring Learning Classifier System Behaviors In Multi-Action, Turn-Based Wargames, Garth J.S. Terlizzi Iii

Theses and Dissertations

State of the art game-playing Artificial Intelligence research focuses heavily on non-symbolic learning methods. These methods offer little explainable insight into their decision-making processes. Learning Classifier Systems (LCSs) provide an alternative. LCSs use rule-based learning, guided by a Genetic Algorithm (GA), to produce a human-readable rule-set. This thesis explores LCS usefulness in game-playing agents for multi-agent wargames. Several Multi-Agent Learning Classifier System (MALCS) variants are implemented in the wargame Stratagem MIST: a Zeroeth-Level Classifier System (ZCS), an extended Classifier System (XCS), and an Adaptive Pittsburgh Classifier System (APCS). These algorithms were tested against baseline agents as well as the Online …

Improving Anonymized Search Relevance With Natural Language Processing And Machine Learning, Niko A. Petrocelli

Theses and Dissertations

Users often sacrifice personal data for more relevant search results, presenting a problem to communities that desire both search anonymity and relevant results. To balance these priorities, this research examines the impact of using Siamese networks to extend word embeddings into document embeddings and detect similarities between documents. The predicted similarity can locally re-rank search results provided from various sources. This technique is leveraged to limit the amount of information collected from a user by a search engine. A prototype is produced by applying the methodology in a real-world search environment. The prototype yielded an additional function of finding new …

Smoothing Of Convolutional Neural Network Classifications, Glen R. Drumm

Theses and Dissertations

Smoothing convolutional neural networks is investigated. When intermittent and random false predictions happen, a technique of average smoothing is applied to smooth out the incorrect predictions. While a simple problem environment shows proof of concept, obstacles remain for applying such a technique to a more operationally complex problem.

Approximate Dynamic Programming For An Unmanned Aerial Vehicle Routing Problem With Obstacles And Stochastic Target Arrivals, Kassie M. Gurnell

Theses and Dissertations

The United States Air Force is investing in artificial intelligence (AI) to speed analysis in efforts to modernize the use of autonomous unmanned combat aerial vehicles (AUCAVs) in strike coordination and reconnaissance (SCAR) missions. This research examines an AUCAVs ability to execute target strikes and provide reconnaissance in a SCAR mission. An orienteering problem is formulated as anMarkov decision process (MDP) model wherein a single AUCAV must optimize its target route to aid in eliminating time-sensitive targets and collect imagery of requested named areas of interest while evading surface-to-air missile (SAM) battery threats imposed as obstacles. The AUCAV adjusts its …

Incorporating Armed Escorts To The Military Medical Evacuation Dispatching Problem Via Stochastic Optimization And Reinforcement Learning, Andrew G. Gelbard

Theses and Dissertations

The military medical evacuation (MEDEVAC) dispatching problem seeks to determine high-quality dispatching policies to maximize the survivability of casualties within contingency operations. This research leverages applied operations research and machine learning techniques to solve the MEDEVAC dispatching problem and evaluate system performance. More specifically, we develop an infinite-horizon, continuous-time Markov decision process (MDP) model and approximate dynamic programming (ADP) solution approach to generate high-quality policies. The ADP solution approach utilizes an approximate value iteration algorithm strategy incorporating gradient descent Q-learning to approximate the value function. A notional, synthetically-generated scenario in Africa based around the capital city of Niger, Niamey is …

An Entity-Component System Based, Ieee Dis Interoperability Interface, Noah W. Scott

Theses and Dissertations

In practice, there are several different methods of organizing data within a given software to fulfil its function. The method known as the Entity-Component System (ECS) is a software architecture where data components define entities. These components are stored as organized lists which are operated upon by systems to inject the system's desired behavior. Data is sent across the networks to communicate between simulation nodes as Protocol Data Units (PDUs). When sending PDUs across a network protocol, each simulation represents a common understanding of the world at the desired level of detail. DIS-compliant simulations are commonly written using an Object-Oriented …

Autonomous And Resilient Management Of All-Source Sensors For Navigation Integrity: A Comparison And Analysis, Niles A. Tate

Theses and Dissertations

When navigating using Global Navigation Satellite Systems (GNSS), multiple/redundant, synchronous pseudorange measurements are readily available. However, when navigating in a GNSS degraded and/or denied region, this is not guaranteed. In response to this challenge, the ANT Center developed a framework known as Autonomous and Resilient Management of All-source Sensors (ARMAS). The ARMAS framework is designed to be resilient towards data corruption caused from mismodeled, uncalibrated, and faulty sensors. This thesis further expands on this work by performing a comparison against a Residual-Based Receiver Autonomous Integrity Monitoring (RBRAIM) scheme using simulated and real flight data to evaluate each systems performance.

Bayesian Convolutional Neural Network With Prediction Smoothing And Adversarial Class Thresholds, Noah M. Miller

Theses and Dissertations

Using convolutional neural networks (CNNs) for image classification for each frame in a video is a very common technique. Unfortunately, CNNs are very brittle and have a tendency to be over confident in their predictions. This can lead to what we will refer to as “flickering,” which is when the predictions between frames jump back and forth between classes. In this paper, new methods are proposed to combat these shortcomings. This paper utilizes a Bayesian CNN which allows for a distribution of outputs on each data point instead of just a point estimate. These distributions are then smoothed over multiple …

Using Generative Adversarial Networks To Augment Unmanned Aerial Vehicle Image Classification Training Sets, Benjamin J. Mccloskey

Theses and Dissertations

A challenging task in computer vision is finding techniques to improve the object detection and classification capabilities of ML models used for processing images acquired by moving aerial platforms. This research explores if GAN augmented UAV training sets can increase the generalizability of a detection model trained on said data. To answer this question, the YOLOv4-Tiny Object Detection Model was trained with aerial image training sets depicting rural environments. The salient objects within the frames were recreated using various GAN architectures, placed back into the original frames, and the augmented frames appended to the original training sets. GAN augmentation on …

Obsolescence: Evaluating An Educational Serious Game On Artificial Intelligence Impacts To Military Strategic Goals, Timothy C. Kokotajlo

Theses and Dissertations

Artificial Intelligence (AI) threatens to bring significant disruption to all aspects of military operations. This research develops a Serious Game (SG) and assessment methodology to provide education on the mindsets required for engaging with disruptive AI technologies. The game, Obsolescence, teaches strategic-level concepts recommended to the Department of Defense (DoD) from a compilation of reports on the current and future state of AI and warfighting. The methodology for assessing the educational value of Obsolescence addresses common challenges such as subjective reporting, control groups, population sizes, and measuring abstract or high levels of learning. The games proposed educational value is tested …

Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice

Theses and Dissertations

We formulate the first generalized air combat maneuvering problem (ACMP), called the MvN ACMP, wherein M friendly AUCAVs engage against N enemy AUCAVs, developing a Markov decision process (MDP) model to control the team of M Blue AUCAVs. The MDP model leverages a 5-degree-of-freedom aircraft state transition model and formulates a directed energy weapon capability. Instead, a model-based reinforcement learning approach is adopted wherein an approximate policy iteration algorithmic strategy is implemented to attain high-quality approximate policies relative to a high performing benchmark policy. The ADP algorithm utilizes a multi-layer neural network for the value function approximation regression mechanism. One-versus-one …