Physical Sciences and Mathematics Commons^™

Forecasting Army Recruiting Mission Distribution, Maxwell A. Deihl

Theses and Dissertations

The Army’s recruiting landscape has changed markedly in recent years, raising questions about whether forecasting methods of Army contracts remain robust. This thesis recreates the presented models in Joshua McDonald’s 2015 thesis. It replicates and evaluates the models with updated data (2018–2023) to assess their current validity and compare them to novel alternative approaches, such as simpler regression models or neural networks. While the 2015 model remains a valuable baseline, results suggest that either refining its variables or adopting alternative methods can improve predictive accuracy and interpretability. Ultimately, the United States Army Recruiting Command has many options regarding how it …

Evaluating Learning Outcomes In A Serious Game: A Practical And Model Checking Approach, Matthew D. Douglas

Theses and Dissertations

This research introduces a novel computational framework to evaluate and predict the educational impact of serious games during development. By using finite state machines (FSM) and model-checking techniques, this study evaluates two serious games. Traditional evaluation approaches, often reliant on resource-intensive human trials, lack scalability and fail to provide early insight into the alignment of game mechanics with learning objectives. This study addresses these challenges of traditional evaluation methods.

Geo-Spatial Mapping Of Sentiment Analysis With Transformer-Based Models, Dugan J. Turnbow

Theses and Dissertations

The public sentiment of events of interest, and their impacts, is vital for decision makers to allocate resources. This research develops a robust algorithm for aggregating sentiment analysis from social media and published articles, while contextualizing results through spatial and temporal mapping. The methodology employs two transformer-based language models for sentiment analysis and named entity recognition (NER). Sentiment scores are generated and augmented using explicit location data, such as latitude and longitude, and implicit location data derived through NER or location features. Results are mapped using a geo-tagged location dictionary, enabling visualization of sentiment trends at state and county levels …

A Standardized Methodology For Evaluating A Digital Badging System [ Data Package ], Benjamin T. Pederson, Mark G. Reith, Ralucca Gera, David S. Long, Edward D. White, Jonathan Zemmer

Faculty Publications

Digital badges, a form of micro-credentials, have grown in popularity over the past decade. However, few standard processes exist to assess the potential of digital badging systems within an organization. This study proposes a generalizable methodology for comparing a badging system with other methods of recording skills and competencies. The experimental design is tested using the military's cyber operations community as the target organization. Finally, mixed-method data from thirty-six participants is analyzed in accordance with the methodology. Based on the results, digital badging systems are perceived to be more valuable and usable than a current method of military talent management. …

Convergent Close-Coupling Approach To Electron Impact Dissociation Of The Polyatomic Molecule H 3 + And Its Isotopologues, Reese K. Horton, Michael V. Pak, Igor Bray, Dmitry V. Fursa

Faculty Publications

Cross sections for electron impact dissociative excitation and ionization in scattering on vibrationally excited levels of the ground electronic state of H₃⁺ and its isotopologues are reported in the energy range of 8 to 1000 eV. Calculations have been performed using a newly developed version of the molecular convergent close-coupling code. Cross sections for total dissociative excitation, ionization yielding atomic fragments such as D⁺, and the total inelastic cross section are presented. Good agreement with available experiments has been demonstrated.

Convergent Close-Coupling Approach To Electron Scattering On H3+ : Scattering Dynamics And Dissociative Processes, Reese K. Horton, Michael V. Pak, Igor Bray, Dmitry V. Fursa

Faculty Publications

Cross sections for electron impact dissociative excitation and ionization in scattering on vibrationally excited levels of the ground electronic state of H₃⁺, D₃⁺, and T₃⁺ are reported in the energy range of 8–1000 eV. Calculations have been performed using a newly developed version of the molecular convergent close-coupling code. Convergence of the cross sections with the size of the projectile partial-wave and close-coupling expansions is examined. Branching ratios and cross sections for the yields of D₂⁺ and D⁺ from dissociative excitation of D₃⁺ are presented and isotope …

Accelerated Multiobjective Calibration Of Fused Deposition Modeling 3d Printers Using Multitask Bayesian Optimization And Computer Vision, Craig S. Ganitano, Benji Maruyama, Gilbert L. Peterson

Faculty Publications

Proper process parameter calibration is critical to the success of fused deposition modeling (FDM) three-dimensional (3D) printing, but is time-consuming and requires expertise. While existing systems for autonomous calibration have demonstrated success in calibrating for a single objective, users may need to balance multiple conflicting objectives. Herein, an easily deployable, camera-based system for autonomous calibration of FDM printers that optimizes for both part quality and completion time is presented. Autonomous calibration is achieved through a novel, multifaceted computer vision characterization and a multitask learning extension to Bayesian optimization. The system is demonstrated on four popular filament types using two distinct …

Display System Interface Using Visually-Evoked Cortical Potentials, Michael E. Miller, Brett J. Borghetti, Kellie D. Kennedy, Chad L. Stephens, Alan T. Pope

AFIT Patents

A brain-computer interface system includes a video processor for producing a display signal, a temporal controller for producing a plurality of repetitive visual stimulus (RVS) signals with different respective temporal aspects, a display device that receives the display signal and displays a corresponding image on a plurality of different display regions and receives the RVS signals and displays corresponding RVS in respective ones of the display regions, an electroencephalographic (EEG) sensor for sensing a visually-evoked cortical potential (VECP) signal in a user with eyes fixated on a viewed one of the display regions, and a VECP processor for processing the …

Afit Generative Ai Teaching Guidebook Synopsis, Afit Faculty Learning Community, Mark Bateman, Brett J. Borghetti, Allen W. Dukes, Nicholas C. Francis, Mike Frick, Bobbie Oh, Kevin Patterson, Hiren J. Patel, Mark G. Reith, Erick S. Tyndall, Teresa M. Walton, Torrey J. Wagner, Timothy S. Wolfe, Jonathan Zemmer

AFIT Documents

The main objective of this work was to bring together various perspectives on how to envision incorporating Gen AI capabilities into the learning environment and identify some best practices for their implementation. Any instructor who is interested in these capabilities but does not necessarily have a technical background can find pragmatic use of the examples provided. While the examples have a wide range of applicability, they are meant to serve as a starting point for educators to explore what would be beneficial to their educational environment, from traditional classroom settings to online continuing education courses.

Afit Generative Ai Teaching Guidebook, Afit Faculty Learning Community, Mark Bateman, Brett J. Borghetti, Allen W. Dukes, Nicholas C. Francis, Mike Frick, Bobbie Oh, Kevin Patterson, Hiren J. Patel, Mark G. Reith, Erick S. Tyndall, Teresa M. Walton, Torrey J. Wagner, Timothy S. Wolfe, Jonathan Zemmer

AFIT Documents

AFIT is proud to highlight the Generative AI Teaching Guidebook, a resource designed to provide military educators with practical insights, strategies, and use cases for integrating Generative AI (Gen AI) into their teaching practices. Developed through a collaborative effort involving AFIT faculty across various departments within the Graduate School of Engineering and Management and the School of Systems and Logistics, this digital resource serves as a starting point for educators exploring how to leverage Gen AI in their classrooms. It offers accessible examples and best practices, ensuring utility for instructors of all technical backgrounds. The guidebook provides a comprehensive overview …

Navigating Together: The Conav Testbed And Framework For Benchmarking Cooperative Localization, Rohith Boyinine, Jayanth Ammapalli, Anusna Chakraborty, Rajnikant Sharma, Kevin Brink, Clark N. Taylor

Faculty Publications

This paper presents CoNaV, a comprehensive framework for creating a multi-vehicle cooperative localization (CL) testbed designed to support the benchmarking, development, and deployment of cooperative navigation algorithms. Given the essential role of CL in improving localization accuracy for both defense and civilian applications, CoNaV provides a robust environment for rigorously validating algorithms under real-world conditions. By establishing a benchmark for CL algorithms, CoNaV lays a foundation for advancing research into more sophisticated and distributed CL solutions. This framework highlights the potential of cooperative navigation to enhance multi-vehicle operations and offers a scalable, practical approach for future developments in CL technology.

Editorial: Artificial Intelligence For Smart Health: Learning, Simulation, And Optimization, Bing Yao, Nathan Gaw, Hyo Kyung Lee

Faculty Publications

With rapid developments in medical sensing and imaging, we now live in an era of data explosion in which large amounts of data are readily available in clinical environments. The fast-growing biomedical and healthcare data provide unprecedented opportunities for data-driven scientific knowledge discovery and clinical decision support. Our Research Topic aims to catalyze synergies among biomedical informatics, machine learning, computer simulation, operations research, systems engineering, and other related fields with three specific goals: (1) develop cutting-edge data-driven models to accelerate scientific knowledge discovery in biomedicine using healthcare data collected from laboratory systems, imaging systems, and medical and sensing devices; (2) …

Ultraviolet And Blue Stimulated Emission From Cs Alkali Vapor Pumped Using Two-Photon Absorption And Four-Wave Mixing, Ricardo C. Davila, Christopher A. Rice, Nathan B. Terry, Glen P. Perram

Faculty Publications

Stimulated emission on the ultraviolet and blue transitions in Cs has been achieved by pumping via two-photon absorption and four-wave mixing for the pump transition 6²S½ → 8²D_3/2,5/2. The emission performance of the optically pumped cesium vapor laser operating in ultraviolet and blue has been extended to 650 nJ/pulse for 387 nm, 1 to 3 μ J / pulse for 388 nm, 200 nJ/pulse for 455 nm, and 500 nJ/pulse for 459 nm. Emission performance improves dramatically as the cesium vapor density is increased, and no scaling limitations associated with energy pooling or …

Machine Visual Perception From Sim-To-Real Transfer Learning For Autonomous Docking Maneuvers, Derek Worth, Jeffrey Choate, Ryan M. Raettig, Scott L. Nykl, Clark N. Taylor

Faculty Publications

This paper presents a comprehensive approach to enhancing autonomous docking maneuvers through machine visual perception and sim-to-real transfer learning. By leveraging relative vectoring techniques, we aim to replicate the human ability to execute precise docking operations. Our study focuses on autonomous aerial refueling as a use case, demonstrating significant advancements in relative navigation and object detection. We introduce a novel method for aligning digital twins using fiducial targets and motion capture data, which facilitates accurate pose estimation from real-world imagery. Additionally, we develop cost-efficient annotation automation techniques for generating high-quality You Only Look Once training data. Experimental results indicate that …

Mitigating Code Reuse Attacks On Risc-V Binaries: Minimizing Gadget Availability Using The Compressed Extension, Heitor Vieira

Theses and Dissertations

Embedded systems are vital in civilian and military applications, requiring high performance and security. The open RISC-V Instruction Set Architecture (ISA) offers significant advantages, including security through community review and strategic independence in microchip supplies. Brazil’s recent partnership with RISC-V highlights its potential for national technological sovereignty. However, RISC-V is not inherently resistant to code reuse attacks (CRAs), highlighting the need to integrate security measures early in development. The RISC-V Compressed extension, while beneficial for optimizing performance and code flexibility, introduces security trade-offs. As RISC-V adoption grows, particularly in critical systems, addressing these security challenges from the start is crucial …

Temporal Metadata Analysis: A Learning Classifier System Approach, Michael C. Todd, Gilbert L. Peterson

Faculty Publications

Digital forensics is a complex field that requires expert knowledge (EK) and specialized tools to collect, analyze, and report on digital evidence. Temporal metadata analysis is particularly challenging, requiring expert knowledge to understand and interpret underlying traces and associate them with their source. This paper introduces Digital Trace Inspector (DTI), a Learning Classifier System (LCS)-based decision support tool for temporal metadata analysis. DTI leverages a binary Michigan-style LCS to locate and group corroborating temporal digital traces of targeted user activity. Rules are built from expert-created atomics encoded as feature vectors using patterns defined in a structured EK rule framework. The …

Dual-Channel Side Channel Attack: Improved Aes Key Decryption By Combining Power And Electromagnetic Side Channels With Convolutional Neural Networks, Sean P. O'Neill

Theses and Dissertations

This research introduces a novel DL approach for SCA that combines power consumption and EM signals to enhance encryption key deduction by leveraging a dual-channel CNN architecture. A new dataset, consisting of simultaneous power and EM signal collections during 128-bitAES encryption, was developed to train and evaluate the model’s effectiveness. The combined approach achieved an 88% reduction in traces needed, from 50 traces to 6, for encryption key classification, outperforming traditional methods such as random forest, DPA, DEMA,and individual side channel CNN models. These findings highlight the potential of integrating multiple side channels in SCA to improve performance without the …

Applying Machine‐Learning Methods To Laser Acceleration Of Protons: Lessons Learned From Synthetic Data, Ronak Desai, Thomas Zhang, J. J. Felice, Ricky Oropeza, Joseph R. Smith, Alona Kryshchenko, Chris Orban, Michael L. Dexter, Anil K. Patnaik

Faculty Publications

In this study, we consider three different machine-learning methods—a three-hidden-layer neural network, support vector regression, and Gaussian process regression—and compare how well they can learn from a synthetic data set for proton acceleration in the Target Normal Sheath Acceleration regime. The synthetic data set was generated from a previously published theoretical model by Fuchs et al. 2005 that we modified. Once trained, these machine-learning methods can assist with efforts to maximize the peak proton energy, or with the more general problem of configuring the laser system to produce a proton energy spectrum with desired characteristics. In our study, we focus …

Strategies To Alleviate Flickering: Bayesian And Smoothing Methods For Deep Learning Classification In Video, Noah Miller, Glen Ryan Drumm, Lance Champagne, Bruce A. Cox, Trevor Bihl

Faculty Publications

Excerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations.

Time Domain Spectral Lidar Enabled By Cascaded Raman In A Hydrogen-Filled Transmitter, Richard K. Martin, Trevor L. Courtney, Arielle M. Adams, Daniel E. Leaird, Luke Ausley, Christian K. Keyser

Faculty Publications

We introduce what we believe to be novel spectral light detection and ranging (LiDAR) architectures that enable ultra-compact systems by a transition from spectral signal processing in space (gratings) to processing in time. The architectures leverage temporal dispersion and the unique spectro-temporal waveforms produced from the cascaded Raman scattering generated in the (H₂) filled hollow core fiber. The characterized Raman source yields as many as six Raman orders from 1.06-1.70 μm; their unique spectro-temporal waveforms are measured. System performance simulations based on measured Raman waveforms show that high accuracy measurement of range and reflectivity are possible with proper …

Limitations Of Beam-Control Compensation, Matthew Kalensky, Darren Getts, Matthias T. Banet, Derek J. Burrell, Milo W. Hyde, Mark F. Spencer

Faculty Publications

In this paper, we use wave-optics simulations to explore the limitations of beam-control compensation. We evaluate performance in terms of the normalized power in a diffraction-limited bucket for the cases of no beam-control compensation, perfect phase compensation, and perfect full-field compensation. From these results, we are able to arrive at the following conclusions: (1) without any form of beam-control compensation, performance begins to degrade when D/r₀ > 1; (2) with perfect phase compensation, performance begins to degrade when D/r₀ > 1 and (λ/r₀)/θ₀ > 1; and (3) with perfect full-field compensation, performance begins to degrade when D/r_{0 …}

Inferring Tlb Configuration With Performance Tools, Cristian Agredo, Tor J. Langehaug, Scott R. Graham

Faculty Publications

Modern computing systems are primarily designed for maximum performance, which inadvertently introduces vulnerabilities at the micro-architecture level. While cache side-channel analysis has received significant attention, other Central Processing Units (CPUs) components like the Translation Lookaside Buffer (TLB) can also be exploited to leak sensitive information. This paper focuses on the TLB, a micro-architecture component that is vulnerable to side-channel attacks. Despite the coarse granularity at the page level, advancements in tools and techniques have made TLB information leakage feasible. The primary goal of this study is not to demonstrate the potential for information leakage from the TLB but to establish …

Constraining Accreted Neutron Star Crust Shallow Heating With The Inferred Depth Of Carbon Ignition In X-Ray Superbursts, Zachary P. Meisel

Faculty Publications

Evidence has accumulated for an as-yet unaccounted for source of heat located at shallow depths within the accreted neutron star crust. However, the nature of this heat source is unknown. I demonstrate that the inferred depth of carbon ignition in X-ray superbursts can be used as an additional constraint for the magnitude and depth of shallow heating. The inferred shallow heating properties are relatively insensitive to the assumed crust composition and carbon fusion reaction rate. For low-accretion rates, the results are weakly dependent on the duration of the accretion outburst, so long as accretion has ensued for enough time to …

Rubrics Informed By The Cognitive Theory Of Multimedia Learning That Support Research On Personalized Learning Paths, Sean A. Mochocki, Mark G. Reith, Jonathan Zemmer

AFIT Documents

Personalized Learning Paths (PLP)s are a popular area of research in E-Learning where sequences of Learning Materials (LM)s and activities are returned based on a learner profile, the LM metadata, and a knowledge structure that describes the relationship between the underlying topics. Unfortunately, PLP researchers tend to not use an empirically supported cognitive science framework for their research, instead relying on such unsupported theories as learning styles or developing their own ad hoc approaches. While many of these researchers present and solve challenging PLP problems using a variety of algorithmic approaches, the PLP community in general would benefit from a …

Global Empirical Model Of Sporadic-E Occurrence Rates, Eli V. Parsch, Anthony L. Franz, Eugene V. Dao, Dong L. Wu, Nimalan Swarnalingam, Cornelius C. J. H. Salinas, Daniel J. Emmons

Faculty Publications

Intense ionization enhancements in the Earth’s ionosphere, known as sporadic-E (E_s), can degrade and severely disrupt the propagation of radio signals. Although many previous studies have analyzed the characteristics and morphologies of sporadic-E, few efforts have attempted to model global E_s occurrence rates (ORs) at high time resolutions. This study develops a global empirical model of blanketing sporadic-E occurrence rates using a Karhunen–Loéve Expansion (KLE) of a global OR climatology built with Global Navigation Satellite System radio occultation (GNSS-RO) and ionosonde observations. Using an fbE ≥ threshold of 3 MHz, the model outputs a blanketing sporadic-E …

Personalized Learning Path Problem Variations: Computational Complexity And Ai Approaches, Sean A. Mochocki, Mark Reith, Brett J. Borghetti, Gilbert L. Peterson, John Jasper, Laurence D. Merkle

Faculty Publications

E-learning courses often suffer from high dropout rates and low student satisfaction. One way to address this issue is to use personalized learning paths (PLPs), which are sequences of learning materials that meet the individual needs of students. However, creating PLPs is difficult and often involves combining knowledge graphs (KGs), student profiles, and learning materials. Researchers typically assume that the problem of creating PLPs belong to the nondeterministic polynomial (NP)-hard class of computational problems. However, previous research in this field has neither defined the different variations of the PLP problem nor formally established their computational complexity. Without clear definitions of …

Numerically Efficient Coherent Mode Representations For Partially Coherent Beams With Separable Phases, Milo W. Hyde, Carolina Rickenstorff

Faculty Publications

We present a method to numerically compute the coherent mode representations (CMRs) for partially coherent beams with separable phases. This special class of random light field has the ability to self-focus and is resistant to turbulence-induced degradation, making it potentially useful in applications such as optical communications. We validate our method by generating (in simulation) two such sources from the literature using their computed CMRs. Lastly, we conclude with a summary of our approach and a discussion of potential applications.

Predictability Limit Of The 2021 Pacific Northwest Heatwave From Deep‐Learning Sensitivity Analysis, P. Trent Vonich, Gregory J. Hakim

Faculty Publications

The traditional method for estimating weather forecast sensitivity to initial conditions uses adjoint models, which are limited to short lead times due to linearization around a control forecast. The advent of deep‐learning frameworks enables a new approach using backpropagation and gradient descent to iteratively optimize initial conditions, minimizing forecast errors. We apply this approach to the June 2021 Pacific Northwest heatwave using the GraphCast model, yielding over 90% reduction in 10‐day forecast errors over the Pacific Northwest. Similar improvements are found for Pangu‐Weather model forecasts initialized with the GraphCast‐derived optimal, suggesting that model error is an unimportant part of the …

Closed-Loop Adaptive Optics In The Presence Of Speckle And Weak Scintillation, Derek J. Burrell, Mark F. Spencer, Ronald G. Driggers

Faculty Publications

In this paper, we show that speckle averaging helps to improve adaptive-optics (AO) performance in closed loop as a result of reduced measurement error associated with a Shack–Hartmann wavefront sensor (SHWFS); however, this reduction is rendered ineffective with increasing beacon anisoplanatism. We do so operating in a weak-scintillation regime, where the SHWFS offers robust performance, and using in-plane translation of the illuminated rough surface to accomplish frame-to-frame speckle diversity. Understanding these trade-space limitations is critical when performing AO with non-cooperative, extended-source beacons.

Using Machine Learning To Predict State Compliance With International Legal Obligations For Registration Of Space Objects: Comparative Performance Of Logistic Regression And Dense Neural Network Models, Jonathan K. Sawmiller

Student Publications

Approximately 12% of satellites and other objects launched into outer space have not been registered with the United Nations (UN) as required by international law. To predict whether States will register a launched space object and understand what factors influence a registration decision, data from a UN online index of space objects was used to train and select the best machine learning model. After preparation, the dataset had 1938 datapoints with 11 features, with categorical features simplified and converted to binary.

Multiple variations of classical logistic regression models were compared to multiple variations of dense neural network models. The best …