Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Engineering (3195)
- Physical Sciences and Mathematics (3070)
- Computer Sciences (1278)
- Physics (959)
- Electrical and Computer Engineering (886)
-
- Aerospace Engineering (784)
- Operations Research, Systems Engineering and Industrial Engineering (735)
- Operational Research (419)
- Business (409)
- Optics (349)
- Signal Processing (343)
- Oceanography and Atmospheric Sciences and Meteorology (283)
- Computer Engineering (243)
- Atomic, Molecular and Optical Physics (209)
- Electrical and Electronics (209)
- Environmental Sciences (194)
- Applied Mathematics (190)
- Civil and Environmental Engineering (189)
- Aviation (186)
- Statistics and Probability (183)
- Information Security (181)
- Social and Behavioral Sciences (170)
- Atmospheric Sciences (167)
- Navigation, Guidance, Control and Dynamics (167)
- Materials Science and Engineering (165)
- Plasma and Beam Physics (156)
- Operations and Supply Chain Management (149)
- Electromagnetics and Photonics (142)
- Artificial Intelligence and Robotics (137)
- Engineering Physics (125)
- Keyword
-
- #antcenter (259)
- Machine learning (95)
- #csra (72)
- Algorithms (60)
- Kalman filtering (52)
-
- Computer networks--Security measures (51)
- Image processing (50)
- Neural networks (Computer science) (50)
- Computer security (47)
- Software engineering (47)
- Decision making (45)
- Target acquisition (45)
- Global Positioning System (44)
- Optimization (41)
- Adaptive optics (40)
- Neural networks (40)
- #ctisr (38)
- Remote sensing (36)
- Computer vision (35)
- Drone aircraft (35)
- Synthetic aperture radar (34)
- #afcec (33)
- Artificial intelligence (31)
- Atmospheric turbulence (30)
- Genetic algorithms (29)
- Mathematical optimization (29)
- Flight control (28)
- Object-oriented programming (Computer science) (28)
- Wireless communication systems (28)
- Deep learning (27)
- Publication Year
- Publication
- Publication Type
- File Type
Articles 31 - 60 of 5596
Full-Text Articles in Entire DC Network
Uranium Chemical Compound Classification Using Sub-Images And Statistical Machine Learning For Nuclear Forensics, Lee C. Lambert, Brett J. Borghetti, Abigail A. Bickley
Uranium Chemical Compound Classification Using Sub-Images And Statistical Machine Learning For Nuclear Forensics, Lee C. Lambert, Brett J. Borghetti, Abigail A. Bickley
Faculty Publications
Uranium particle analysis from Scanning Electron Microscope (SEM) imagery is a crucial tool in nuclear forensics. The particle morphology lexicon proposed by Tamasi et al. in J Radioanal Nucl Chem 307, 1611–1619 (2016) follows a standardized, manual identification process to identify particle morphology features. The present work seeks to mirror this methodology using computer feature selection from the scikit-image Python library rather than human classification. Using a random forest classifier, a 56% overall uranium true positive classification accuracy (a 39.6% balanced classification accuracy) was achieved on a test set outperforming a naïve (chance) model by 48%. The methodology introduced splits …
Spline-Based Factor-Graph Optimization With High-Grade Inertial Sensors, Kyle Leland, Clark N. Taylor, David Woodburn, Randal Beard
Spline-Based Factor-Graph Optimization With High-Grade Inertial Sensors, Kyle Leland, Clark N. Taylor, David Woodburn, Randal Beard
Faculty Publications
Inertial measurement units (IMUs) are central to global navigation satellite system-based and alternative navigation solutions. This paper combines three lines of research to explore a novel methodology for using inertial sensors: factor graphs, spline-based trajectory estimation, and high-grade inertial sensing. Spline-based factor-graph trajectory estimation is increasingly used in the literature, especially for asynchronous or high-rate sensors. However, prior models neglect the impact of the Earth’s rotation, which is significant for high-grade IMUs. We extend spline-based factor graphs to incorporate accelerometer and gyroscope models that account for the Earth’s rotation. We apply this approach to simulated data from high-grade inertial sensors …
Proposed Methodology For Correcting Fourier-Transform Infrared Spectroscopy Field-Of-View Scene-Change Artifacts, Kody A. Wilson, Michael L. Dexter, Benjamin F. Akers, Anthony L. Franz
Proposed Methodology For Correcting Fourier-Transform Infrared Spectroscopy Field-Of-View Scene-Change Artifacts, Kody A. Wilson, Michael L. Dexter, Benjamin F. Akers, Anthony L. Franz
Faculty Publications
Fourier-transform spectrometers are widely used for spectral measurements. Changes in the field of view during measurement introduce oscillations into the measured spectra known as scene-change artifacts. Field-of-view changes also introduce uncertainty about which target the measured spectrum represents. Though scene-change artifacts are often present in dynamic data, their significance is disputed in the current literature. This work presents a theoretical framework and experimental validation for scene-change artifacts. Field-of-view changes introduce variable interferogram offsets, which standard processing techniques assume are constant. The error between the interferogram offset and its estimate is Fourier-transformed, yielding scene-change artifacts, often confused with noise, in the …
A Comparison Of Modeled Daytime E Regions From E-Probed And Pyiri With Ionosonde Observations, Daniel J. Emmons, Cornelius C. J. H. Salinas, Dong L. Wu, Nimalan Swarnalingam, Eugene V. Dao, Jorge L. Chau, Yosuke Yamazaki, Kyle E. Fitch, Victoriya V. Forsythe
A Comparison Of Modeled Daytime E Regions From E-Probed And Pyiri With Ionosonde Observations, Daniel J. Emmons, Cornelius C. J. H. Salinas, Dong L. Wu, Nimalan Swarnalingam, Eugene V. Dao, Jorge L. Chau, Yosuke Yamazaki, Kyle E. Fitch, Victoriya V. Forsythe
Faculty Publications
While the F region is the primary focus of many ionospheric models because it contains the peak electron density, the E region is an important region for ionospheric conductivities and high-frequency radio propagation. This study analyzes modeled E regions from the newly developed PyIRI and E-PROBED models. A long-term comparison of E region predictions from E-PROBED and PyIRI with ionosonde observations is performed for three sites spanning low- (Fortaleza, Brazil), mid- (El Arenosillo, Spain), and high-latitudes (Gakona, Alaska). Modeled foE and hmE trends are compared against a combination of manually-scaled and automatically-scaled ionograms using ARTIST-5 for the period 2009–2024 for …
Amp: Single-Shot Ultra-Wide Fisheye-To-Cubemap Pnp Pose Estimation, Ryan M. Raettig, Richard R. Nyquist, Scott L. Nykl, Clark N. Taylor, Christine M. Schubert Kabban
Amp: Single-Shot Ultra-Wide Fisheye-To-Cubemap Pnp Pose Estimation, Ryan M. Raettig, Richard R. Nyquist, Scott L. Nykl, Clark N. Taylor, Christine M. Schubert Kabban
Faculty Publications
Estimating the position and orientation of a rigid object from an image is critical for situational awareness in robotics and autonomous systems. This study explores relative pose estimation using an ultra-wide fisheye camera for unmanned aircraft inspection vehicles. Ultra-wide fisheye lenses introduce radial distortion and capture features beyond the rectilinear image plane, rendering rectilinear Perspective-n-Point (PnP) algorithms inadequate. Designing a bespoke ultra-wide fisheye localization algorithm requires consideration of both the feature detection method and the pose estimator itself. This study proposes a novel method that combines (1) a fisheye-to-cubemap reprojection, (2) a You Only Look Once (YOLO) convolutional neural network …
Statistical Overview Of Long-Lived Active Regions Observed Across Multiple Carrington Rotations, Emily I. Mason, Kara L. Kniezewski
Statistical Overview Of Long-Lived Active Regions Observed Across Multiple Carrington Rotations, Emily I. Mason, Kara L. Kniezewski
Student Publications
The study of solar active regions (ARs) is of central importance to a range of fundamental science, as well as the practical applications of space weather. Active region emergence and life cycles are two areas of particular interest, yet the lack of consistent full-Sun observations has made long-term studies of active regions difficult. Here, we present results from a study to identify and characterize long-lived active regions (LLARs), defined as those which were observed during at least two consecutive Carrington rotations and which did not undergo significant successive flux emergence once the decay phase began. Such active regions accounted for …
Air Force Institute Of Technology Research Report 2023, Air Force Institute Of Technology
Air Force Institute Of Technology Research Report 2023, Air Force Institute Of Technology
AFIT Documents
This report summarizes the research activities of the Air Force Institute of Technology's Graduate School of Engineering and the Graduate School of Logistics and Acquisition Management. It describes research interests and faculty expertise; list student theses/dissertations; identifies research sponsors and contributions; and outlines the procedure for contacting either school.
Piezoelectric Energy Harvesting From Roadways: Challenges, Advances, And Future Directions, Heba Gaber, Mohamed Abdelraheem
Piezoelectric Energy Harvesting From Roadways: Challenges, Advances, And Future Directions, Heba Gaber, Mohamed Abdelraheem
Faculty Publications
As the global demand for renewable energy intensifies, piezoelectric energy harvesting from roadways has emerged as a promising avenue for sustainable power generation. This systematic literature review analyzes 61 peer-reviewed studies to assess the feasibility, performance, and potential of integrating piezoelectric systems into roadway infrastructure. While technology faces challenges, such as high installation costs, limited energy output, and a scarcity of thorough economic evaluations, findings suggest it holds considerable promise as a supplementary renewable energy source. The review analyzes the operational characteristics and efficiencies of various piezoelectric transducers, identifies key factors influencing system performance, and evaluates recent technological advances. It …
Applying Machine Learning Methods To Laser Acceleration Of Protons: Synthetic Data For Exploring The High Repetition Rate Regime, John J. Felice, Ronak Desai, Nathaniel Tamminga, Joseph R. Smith, Alona Kryshchenko, Christopher M. Orban, Michael L. Dexter, Anil K. Patnaik
Applying Machine Learning Methods To Laser Acceleration Of Protons: Synthetic Data For Exploring The High Repetition Rate Regime, John J. Felice, Ronak Desai, Nathaniel Tamminga, Joseph R. Smith, Alona Kryshchenko, Christopher M. Orban, Michael L. Dexter, Anil K. Patnaik
Faculty Publications
Advances in ultra‐intense laser technology have increased repetition rates and average power for chirped‐pulse laser systems, which offer a promising solution for many applications including energetic proton sources. An important challenge is the need to optimize and control the proton source by varying some of the many degrees of freedom inherent to the laser‐plasma interactions. Machine learning can play an important role in this task, as our work examines. Building on our earlier work in Desai et al. 2024, we generate a large ∼1.5 million data point synthetic data set for proton acceleration using a physics‐informed analytic model that we …
Intrinsic Defects (Vacancies And Antisites) In Neutron Irradiated Cdsip2 Crystals, Timothy D. Gustafson, Elizabeth M. Scherrer, Nancy C. Giles, Kevin T. Zawilski, Peter G. Schunemann, Jonathan E. Slagle, Kent L. Averett, Larry E. Halliburton
Intrinsic Defects (Vacancies And Antisites) In Neutron Irradiated Cdsip2 Crystals, Timothy D. Gustafson, Elizabeth M. Scherrer, Nancy C. Giles, Kevin T. Zawilski, Peter G. Schunemann, Jonathan E. Slagle, Kent L. Averett, Larry E. Halliburton
Faculty Publications
Cadmium silicon phosphide (CdSiP2) is a nonlinear optical material widely used in optical parametric oscillators. Intrinsic defects (vacancies and antisites) are responsible for unwanted broad optical absorption bands in these crystals that degrade the performance of the devices. In the present work, optical absorption and electron paramagnetic resonance (EPR) spectra are acquired (at room temperature and 12 K, respectively) from a neutron-irradiated CdSiP2 crystal. After the irradiation, the crystal is highly absorbing from the band edge near 600 nm to beyond 1.3 μm because of overlapping defect-related absorption bands. Heating to 550 °C removes nearly all the …
Microarchitectural Malware Detection Via Translation Lookaside Buffer (Tlb) Events, Cristian Agredo, Daniel F. Koranek, Christine M. Schubert Kabban, Jose R. Gutierrez Del Arroyo, Scott R. Graham
Microarchitectural Malware Detection Via Translation Lookaside Buffer (Tlb) Events, Cristian Agredo, Daniel F. Koranek, Christine M. Schubert Kabban, Jose R. Gutierrez Del Arroyo, Scott R. Graham
Faculty Publications
Prior work has shown that Translation Lookaside Buffer (TLB) data contains valuable behavioral information. Many existing methodologies rely on timing features or focus solely on workload classification. In this study, we propose a novel approach to malware classification using only TLB-related Hardware Performance Counters (HPCs), explicitly excluding any dependence on timing features such as task execution duration or memory access timing. Our methodology evaluates whether TLB data alone, without any timing information, can effectively distinguish between malicious and benign programs. We test this across three classification scenarios: (1) A binary classification problem involving distinguishing malicious from benign tasks, (2) a …
Validation And Proposed Expansion Of The Data-Driven D Region Model, Kevin M. Watson
Validation And Proposed Expansion Of The Data-Driven D Region Model, Kevin M. Watson
Theses and Dissertations
Predicting ionosphere effects on radio wave propagation is critical for communications and over-the-horizon radar systems. The D region is challenging to model for several reasons, one of which is chemical complexity. Ion density changes during sunrise/sunset introduce substantial uncertainty in electron density profiles (EDPs). The Data Driven D Region (D3R) model solves electron densities through an ion chemistry model and assimilates relevant space weather inputs. This study evaluates D3R against the Faraday International Reference Ionosphere (FIRI) and measurements using Very Low Frequency (VLF) propagation paths. Space weather event impacts on D3R EDPs are evaluated during the disturbed period from 8-12 …
Nuclear Structure Of Neutron-Deficient Cesium-126 And Cesium-127, Connor M. Gautam
Nuclear Structure Of Neutron-Deficient Cesium-126 And Cesium-127, Connor M. Gautam
Theses and Dissertations
Lifetimes of seven excited states of 127Cs, including the states populating the isomer, were measured through a combination of spectroscopic methods. The spin and parity of the states leading up to the 171-μs isomeric level of 126Cs were assigned for the first time, new values were measured for the lifetimes of the two isomeric states, and new evidence was presented for the assignment of a detached sequence of gamma rays to the 126Cs nucleus.
Designing The Protocol For An Experimental Flight Simulation Study Encouraging Fuel Efficient Behavior, Thomas S. Reardon
Designing The Protocol For An Experimental Flight Simulation Study Encouraging Fuel Efficient Behavior, Thomas S. Reardon
Theses and Dissertations
This study designed and tested an experimental instrument to examine how pilots respond to fuel efficiency feedback in a flight simulator. A standardized flight plan, script, and hardware setup were created using X-Plane 12 software and physical flight simulator hardware. The chosen sortie guided participants from Monterey Regional Airport to Moffett Federal Airfield using instrument flight rules (IFR). The flight script provided step-by-step guidance to ensure consistent behavior across participants. The simulator was mapped to match real cockpit controls and allowed for precise data collection including flight time, altitude, heading, and fuel use. The goal was to support a larger …
Effect Of Workplace Design On Collaboration And Satisfaction In Space System Command, Joshua A. Hagood
Effect Of Workplace Design On Collaboration And Satisfaction In Space System Command, Joshua A. Hagood
Theses and Dissertations
This study addresses a significant knowledge gap regarding the influence of physical workplace design on employee collaboration and satisfaction with the physical environment within U.S. Space Force technical military organizations. While seminal industry research consistently demonstrates that physical design and indoor environmental quality influence employee satisfaction and collaboration (e.g., Candido et al., 2015; Sailer et al., 2021), the understanding of these impacts within military contexts remains limited. Using a quantitative post-occupancy evaluation survey, adapted from the Sustainable Post Occupancy Evaluation Survey (SPOES), multiple regression analyses revealed that physical elements collectively predict both satisfaction and collaboration. The final simplified model showed …
Trends And Predictive Modeling Of Real Estate Prices In Major Saudi Arabia Cities, Meshal S. Aldahas
Trends And Predictive Modeling Of Real Estate Prices In Major Saudi Arabia Cities, Meshal S. Aldahas
Theses and Dissertations
his research examines historical trends and explanatory modeling of real estate prices in major Saudi cities, with a focus on Riyadh, Jeddah, and Dammam. Using a mixed-methods approach, the study integrates quantitative data from 2010–2023, including housing and macroeconomic indicators, with qualitative insights drawn from over 320 survey responses that captured consumer sentiment on affordability, job security, and housing policies. A combination of descriptive statistics, ARIMA and Exponential Smoothing techniques was applied to detect long-term patterns, seasonal variations, and market shocks. Predictive modeling was conducted using Linear Regression, Decision Trees, and Neural Networks, with results showing that job security consistently …
Exact And Approximate Conformal Inference For Multi-Output Regression, Chancellor Johnstone, Eugene Ndiaye
Exact And Approximate Conformal Inference For Multi-Output Regression, Chancellor Johnstone, Eugene Ndiaye
Faculty Publications
It is common in machine learning to estimate a response y given covariate information x . However, these predictions alone do not quantify any uncertainty associated with said predictions. One way to overcome this deficiency is with conformal inference methods, which construct a set containing the unobserved response with a prescribed probability. Unfortunately, even with a one-dimensional response, conformal inference is computationally expensive despite recent encouraging advances. In this paper, we explore multi-output regression, delivering exact derivations of conformal inference p-values when the predictive model can be described as a linear function of y . Additionally, we introduce a multivariate …
Comparative Analysis Of Different Magnetic Anomaly Datasets Using Navigation Performance With Flight Test Data, Aaron P. Nielsen, Brandon M. Blakely, Patrick Duff
Comparative Analysis Of Different Magnetic Anomaly Datasets Using Navigation Performance With Flight Test Data, Aaron P. Nielsen, Brandon M. Blakely, Patrick Duff
Faculty Publications
Magnetic Anomaly Navigation (MagNav) is a map-based method of navigation which relies on accurately obtaining the anomaly field to a high level of precision to achieve good navigation results. This requires utilizing high quality sensors, accurately modeling disturbance fields from the aircraft & other sources, and creating high-fidelity maps. Aeromagnetic survey data or marine track survey data must be processed into a product that can be used as a reference for a magnetic navigator and a variety of techniques can be utilized for this processing. The data collection for different survey types reflects choices typically made to study the underlying …
Impacts Of Climate Disruption On Mobility Aircraft Performance In The Pacaf Region, Hannah M. Dauterman
Impacts Of Climate Disruption On Mobility Aircraft Performance In The Pacaf Region, Hannah M. Dauterman
Theses and Dissertations
This thesis investigates the projected impacts of climate disruption on the performance and fuel management of the C-17 Globemaster III, a critical mobility aircraft in the Pacific Air Forces (PACAF) region. As rising global temperatures reduce air density, the performance of aircraft is compromised, resulting in increased fuel consumption, as well as the potential for extended runway requirements and diminished cargo capacity. Using climate projection data from Coupled Model Intercomparison Project Phase 6 (CMIP6), this research analyzes future air temperature trends and their implications for C-17 fuel consumption. Results suggest that by 2049, the U.S. Air Force may incur an …
Electrical Characterization Of Germanium Tin Alloys And Devices For Space Reliability, Kevin K. Choe
Electrical Characterization Of Germanium Tin Alloys And Devices For Space Reliability, Kevin K. Choe
Theses and Dissertations
GeSn (germanium tin) alloys are potentially well suited for near-mid infrared space optoelectronic applications. Alloys of GeSn have similar properties to group III-V and mercury-cadmium-telluride semiconductors and are compatible with cost-effective complementary metal oxide semiconductor (CMOS) manufacturing technology. Recent progress in non-equilibrium remote plasma-enhanced chemical vapor deposition (RPECVD) has enabled the crystalline growth of GeSn with Sn concentrations of up to 10% without Sn surface segregation. Several experimental studies in previous literature report CVD- or molecular beam epitaxy (MBE)-grown GeSn alloys achieving a direct bandgap with 6%-9% Sn content. This novel growth technique opens opportunities for a cost-effective, next-generation optical …
Automation Of Lcmc Logistics Processes: A Delphi Approach, Kline M. Alt
Automation Of Lcmc Logistics Processes: A Delphi Approach, Kline M. Alt
Theses and Dissertations
As the U.S. Air Force confronts growing complexity in system acquisition, the implementation of digital models in system design and logistics process management allows the incorporation of digital tools and the possibility for automation of portions of logistics processes. This thesis investigates where these technologies can be most effectively integrated within the Air Force Life Cycle Management Center logistics enterprise (AFLCMC). Using a three round Delphi study, AFLCMC logistics subject matter expert (SME) opinions were solicited from program-level senior logisticians, program managers to identify high-need areas, key success factors, and potential barriers to adoption. Quantitative consensus from Likert-scale and ordinal …
Designing An Experiment To Create And Evaluate Behavioral Changes In Air Force Pilots' Fuel Efficiency, Jackson Macias
Designing An Experiment To Create And Evaluate Behavioral Changes In Air Force Pilots' Fuel Efficiency, Jackson Macias
Theses and Dissertations
Fuel represents over 70% of the logistical resupply demand within the Department of Defense, with the United States Air Force accounting for most of that consumption. While prior fuel efficiency efforts have primarily focused on technical upgrades, this research explores how behavioral interventions can influence pilot decision-making and operational energy outcomes. Using the Theory of Planned Behavior (TPB) as a guiding framework, this study investigates the effects of targeted behavioral strategies on pilots’ attitudes, subjective norms, perceived behavioral control, intentions, and actual fuel-efficient behaviors. A quasi-experimental design was applied through a controlled pilot study using simulator flights. Six participants were …
Multi-Fidelity Machine Learning Modeling For Aerodynamic Response Prediction Of Aerospace Vehicles, Ethan S. Jackman
Multi-Fidelity Machine Learning Modeling For Aerodynamic Response Prediction Of Aerospace Vehicles, Ethan S. Jackman
Theses and Dissertations
Hypersonic vehicle design requires understanding complex aerodynamic phenomena across the full flight regime. This study presents a novel MF surrogate modeling methodology that enables the prediction the full field response across a vehicle’s surface. A Space-Filling Curve (SFC) is used to convert unstructured data into 1D vectors. The a Convolutional Autoencoder is used with transfer learning to reduce the dimensionality of the data. An Emulator-Embedded Neural Network (E2NN) combines multi-fidelity data for fast, accurate predictions. A benchmark analytical example and hypersonic application are used to evaluate the methodology. Using various numbers of samples and sampling strategies it is found that …
Low-Cost Transfers For Cislunar Liaison Navigation, Ka'eo J. Swartzmiller
Low-Cost Transfers For Cislunar Liaison Navigation, Ka'eo J. Swartzmiller
Theses and Dissertations
CubeSats have an inherent limitation on volume due to their small form factor. Naturally, this extends to the capacity of on-board ΔV, thus limiting the maneuverability of the satellites. This limited maneuverability makes it extremely important to be intentional when planning out mission trajectories. The cislunar region subjects these trajectories to the gravitational forces of both the Earth and the Moon, making it all the more necessary to deliberately plan out maneuvers. The Circular Restricted Three Body Problem (CR3BP) provides a simpler model for estimating the motion of spacecraft within the cislunar region, allowing for the gravitational forces to be …
Investigating The Impact Of Forest Vegetation On Nuclear Weapon Prompt Radiation Energy Deposition, Paul A. Clement
Investigating The Impact Of Forest Vegetation On Nuclear Weapon Prompt Radiation Energy Deposition, Paul A. Clement
Theses and Dissertations
This work seeks to answer the unstudied questions “Does a layer of vegetation impact the prompt radiation energy deposition in the soil from an atmospheric nuclear detonation?” and “If yes, by how much?” A new methodology was developed to repeatably automate and streamline a process of generating a three-dimensional geometry for subsequent radiation transport simulations and statistical analysis. The methodology streamlined three diverse applications: a three-dimensional mesh generator, a radiation transport simulation code, and a sensitivity analysis & uncertainty quantification software. The methodology was tested by simulating the quantitative influence that vegetation has on changing the energy deposition into the …
Spin State Of Positronium In Two Dimensions, Emille Bryant
Spin State Of Positronium In Two Dimensions, Emille Bryant
Theses and Dissertations
We investigate the spin state of the electron-positron system positronium to determine experimental criteria that can identify a positronium anyon. Anyons have been posited to be the basis for a truly fault-tolerant quantum computer, but they have not been indisputably observed in experimental systems. Through the analysis of the fully relativistic symmetry group of fermions and bosons in three dimensions, we investigate the symmetry of its subgroups to determine that positronium in two dimensions behaves as a scalar with respect to rotations. We conclude that positronium in two dimensions has an arbitrary relative spin orientation of annihilation photons and only …
Feasibility Evaluation Of Secure Offline Large Language Models With Retrieval-Augmented Generation For Cpu-Only Inference, Erick Tyndall, Torrey J. Wagner, Colleen Gayheart, Alexandre Some, Brent T. Langhals
Feasibility Evaluation Of Secure Offline Large Language Models With Retrieval-Augmented Generation For Cpu-Only Inference, Erick Tyndall, Torrey J. Wagner, Colleen Gayheart, Alexandre Some, Brent T. Langhals
Faculty Publications
Recent advances in large language models and retrieval-augmented generation, a method that enhances language models by integrating retrieved external documents, have created opportunities to deploy AI in secure, offline environments. This study explores the feasibility of using locally hosted, open-weight large language models with integrated retrieval-augmented generation capabilities on CPU-only hardware for tasks such as question answering and summarization. The evaluation reflects typical constraints in environments like government offices, where internet access and GPU acceleration may be restricted. Four models were tested using LocalGPT, a privacy-focused retrieval-augmented generation framework, on two consumer-grade systems: a laptop and a workstation. A technical …
Impact Of Retrieval Augmented Generation And Large Language Model Complexity On Undergraduate Exams Created And Taken By Ai Agents, Erick S. Tyndall, Colleen Gayheart, Alexandre Some, Joseph Genz, Torrey J. Wagner, Brent T. Langhals
Impact Of Retrieval Augmented Generation And Large Language Model Complexity On Undergraduate Exams Created And Taken By Ai Agents, Erick S. Tyndall, Colleen Gayheart, Alexandre Some, Joseph Genz, Torrey J. Wagner, Brent T. Langhals
Faculty Publications
The capabilities of large language models (LLMs) have advanced to the point where entire textbooks can be queried using retrieval-augmented generation (RAG), enabling AI to integrate external, up-to-date information into its responses. This study evaluates the ability of two OpenAI models, GPT-3.5 Turbo and GPT-4 Turbo, to create and answer exam questions based on an undergraduate textbook. 14 exams were created with four true-false, four multiple-choice, and two short-answer questions derived from an open-source Pacific Studies textbook. Model performance was evaluated with and without access to the source material using text-similarity metrics such as ROUGE-1, cosine similarity, and word embeddings. …
Computer-Automated Systems And Methods For Using Language Models To Generate Text Based On Reading Errors, Scott Sosso, Siyu Chen, Ciara Figliuolo, Jack Mostow, Marlies Goes
Computer-Automated Systems And Methods For Using Language Models To Generate Text Based On Reading Errors, Scott Sosso, Siyu Chen, Ciara Figliuolo, Jack Mostow, Marlies Goes
AFIT Patents
A computer-implemented system and method generate personalized text based on statistics derived from input received from a user representing the user's attempts to decode graphemes into phonemes. Such statistics may be measured and recorded at the grapheme-phoneme level, and may include substitutions, insertions, deletions, and correct utterances of phonemes by the user when reading text. A language model may be trained based on characteristics of the user, such as the user's age and/or reading grade level, and the personalized text may be generated after such training of the language model. Generating the personalized text may include generating a text creation …
The Effects Of I-127 On A High-Granularity Lii(Eu) Bonner Sphere Spectrometer Response Matrix, Adam Card, Andrew W. Decker
The Effects Of I-127 On A High-Granularity Lii(Eu) Bonner Sphere Spectrometer Response Matrix, Adam Card, Andrew W. Decker
Student Publications
The measurement of neutron energy spectra using a Bonner Sphere Spectrometer (BSS) requires spectrum unfolding. One necessary component of spectrum unfolding is an accurate neutron response matrix, which describes the energy shift experienced by neutrons when passing through different moderation configurations prior to detection. Leveraging the recently-released ENDF/B-VIII.0 cross-section library, this work details the development of a new LiI(Eu) scintillator response matrix that features improved energy binning granularity as well as increased isotopic and statistical accuracy. Using MCNP6.2, detector responses were modeled at 105 discrete log-equi-spaced incident neutron energies from 1.000 × 10−9 to 2.512 × 101 MeV …