Physical Sciences and Mathematics Commons^™

Scaling Epa-Rimm With Multicore System Management Interrupt Handlers, Alexander K. Freed

Dissertations and Theses

Continuous runtime integrity measurement mechanisms (RIMMs) can be used for timely detection of kernel and hypervisor rootkits. Researchers have proposed running RIMMs in privileged execution environments, such as the x86 architecture’s System Management Mode (SMM), to detect interference from rootkits that have gained control of the host operating system. However, the extended amount of time in SMM required to perform inspections can cause severe disruption to the host. A previously proposed RIMM design called EPA-RIMM addresses this by decomposing long inspections across multiple System Management Interrupts (SMI), the interrupt used to invoke SMM.

EPA-RIMM is intended for deployment on server-class …

Data From: Machine Learning Predictions Of Electricity Capacity, Marcus Harris, Elizabeth Kirby, Ameeta Agrawal, Rhitabrat Pokharel, Francis Puyleart, Martin Zwick

Systems Science Faculty Datasets

This research applies machine learning methods to build predictive models of Net Load Imbalance for the Resource Sufficiency Flexible Ramping Requirement in the Western Energy Imbalance Market. Several methods are used in this research, including Reconstructability Analysis, developed in the systems community, and more well-known methods such as Bayesian Networks, Support Vector Regression, and Neural Networks. The aims of the research are to identify predictive variables and obtain a new stand-alone model that improves prediction accuracy and reduces the INC (ability to increase generation) and DEC (ability to decrease generation) Resource Sufficiency Requirements for Western Energy Imbalance Market participants. This …

Quantum Key-Length Extension, Joseph Jaeger, Fang Song, Stefano Tessaro

Computer Science Faculty Publications and Presentations

Should quantum computers become available, they will reduce the effective key length of basic secret-key primitives, such as blockciphers. To address this we will either need to use blockciphers with inherently longer keys or develop key-length extension techniques to amplify the security of a blockcipher to use longer keys.

We consider the latter approach and revisit the FX and double encryption constructions. Classically, FX was proven to be a secure key-length extension technique, while double encryption fails to be more secure than single encryption due to a meet-in-the-middle attack. In this work we provide positive results, with concrete and tight …

From Machine Learning To Deep Learning: A Comprehensive Study Of Alcohol And Drug Use Disorder, Banafsheh Rekabdar, David L. Albright, Haelim Jeong, Sameerah Talafha

Computer Science Faculty Publications and Presentations

This study aims to train and validate machine learning and deep learning models to identify patients with risky alcohol and drug misuse in a Screening, Brief Intervention, and Referral to Treatment (SBIRT) program. An observational cohort of 6978 adults was admitted in the western region of Alabama at three medical facilities between January and December of 2019. Data were cleaned and pre-processed using data imputation techniques and an augmented sampling data method. The primary analysis involved the multi-class classification of alcohol and drug misuse. Our study shows that accurate identification of alcohol and drug use screening instrument scores was best …

A Simpler Machine Learning Model For Acute Kidney Injury Risk Stratification In Hospitalized Patients, Yirui Hu, Kunpeng Liu, Kevin Ho, David Riviello, Jason Brown, Alex R. Chang, Gurmukteshwar Singh, H. Lester Kirchner

Computer Science Faculty Publications and Presentations

Background: Hospitalization-associated acute kidney injury (AKI), affecting one-in-five inpatients, is associated with increased mortality and major adverse cardiac/kidney endpoints. Early AKI risk stratification may enable closer monitoring and prevention. Given the complexity and resource utilization of existing machine learning models, we aimed to develop a simpler prediction model. Methods: Models were trained and validated to predict risk of AKI using electronic health record (EHR) data available at 24 h of inpatient admission. Input variables included demographics, laboratory values, medications, and comorbidities. Missing values were imputed using multiple imputation by chained equations. Results: 26,410 of 209,300 (12.6%) inpatients developed AKI during …

Motion-Adjustable Neural Implicit Video Representation, Long Mai, Feng Liu

Computer Science Faculty Publications and Presentations

Implicit neural representation (INR) has been successful in representing static images. Contemporary image-based INR, with the use of Fourier-based positional encoding, can be viewed as a mapping from sinusoidal patterns with different frequencies to image content. Inspired by that view, we hypothesize that it is possible to generate temporally varying content with a single image-based INR model by displacing its input sinusoidal patterns over time. By exploiting the relation between the phase information in sinusoidal functions and their displacements, we incorporate into the conventional image-based INR model a phase-varying positional encoding module, and couple it with a phase-shift generation module …

Proceedings Of The Rust-Edu Workshop, Bart Massey

Rust-Edu Workshop

The 2022 Rust-Edu Workshop was an experiment. We wanted to gather together as many thought leaders we could attract in the area of Rust education, with an emphasis on academic-facing ideas. We hoped that productive discussions and future collaborations would result. Given the quick preparation and the difficulties of an international remote event, I am very happy to report a grand success. We had more than 27 participants from timezones around the globe. We had eight talks, four refereed papers and statements from 15 participants. Everyone seemed to have a good time, and I can say that I learned a …

System Dynamics Modeling For Traumatic Brain Injury: Mini-Review Of Applications, Erin S. Kenzie, Elle L. Parks, Nancy Carney, Wayne Wakeland

Systems Science Faculty Publications and Presentations

Traumatic brain injury (TBI) is a highly complex phenomenon involving a cascade of disruptions across biomechanical, neurochemical, neurological, cognitive, emotional, and social systems. Researchers and clinicians urgently need a rigorous conceptualization of brain injury that encompasses nonlinear and mutually causal relations among the factors involved, as well as sources of individual variation in recovery trajectories. System dynamics, an approach from systems science, has been used for decades in fields such as management and ecology to model nonlinear feedback dynamics in complex systems. In this mini-review, we summarize some recent uses of this approach to better understand acute injury mechanisms, recovery …

Quantum Algorithms For Attacking Hardness Assumptions In Classical And Post‐Quantum Cryptography, J.-F. Biasse, X. Bonnetain, E. Kirshanova, A. Schrottenloher, Fang Song

Computer Science Faculty Publications and Presentations

In this survey, the authors review the main quantum algorithms for solving the computational problems that serve as hardness assumptions for cryptosystem. To this end, the authors consider both the currently most widely used classically secure cryptosystems, and the most promising candidates for post-quantum secure cryptosystems. The authors provide details on the cost of the quantum algorithms presented in this survey. The authors furthermore discuss ongoing research directions that can impact quantum cryptanalysis in the future.

Learning From Machines: Insights In Forest Transpiration Using Machine Learning Methods, Morgan Tholl

Dissertations and Theses

Machine learning has been used as a tool to model transpiration for individual sites, but few models are capable of generalizing to new locations without calibration to site data. Using the global SAPFLUXNET database, 95 tree sap flow data sites were grouped using three clustering strategies: by biome, by tree functional type, and through use of a k-means unsupervised clustering algorithm. Two supervised machine learning algorithms, a random forest algorithm and a neural network algorithm, were used to build machine learning models that predicted transpiration for each cluster. The performance and feature importance in each model were analyzed and compared …

Toward Analyzing The Diversity Of Extractive Summaries, Aaron David Hudson

Dissertations and Theses

As the amount of text generated across the internet continues to increase, developing methods for processing that text to glean valuable insights is paramount. Automatic text summarization is one such method that aims to provide a concise and representative summary of input text, allowing users access to the most salient points from a large amount of textual data. However, in working with these summaries, especially those generated from social media data, questions arise about not only the quality of a summary, but also its ability to reflect the diversity of user perspectives. This work examines the quality of summaries with …

Unpaired Style Transfer Conditional Generative Adversarial Network For Scanned Document Generation, David Jonathan Hawbaker

Dissertations and Theses

Neural networks are a powerful machine learning tool, especially when trained on a large dataset of relevant high-quality data. Generative adversarial networks, image super resolution and most other image manipulation neural networks require a dataset of images and matching target images for training. Collecting and compiling that data can be time consuming and expensive. This work explores an approach for building a dataset of paired document images with a matching scanned version of each document without physical printers or scanners. A dataset of these document image pairs could be used to train a generative adversarial network or image super resolution …

Snerf: Stylized Neural Implicit Representations For 3d Scenes, Thu Nguyen-Phuoc, Feng Liu, Lei Xiao

Computer Science Faculty Publications and Presentations

This paper presents a stylized novel view synthesis method. Applying state-of-the-art stylization methods to novel views frame by frame often causes jittering artifacts due to the lack of cross-view consistency. Therefore, this paper investigates 3D scene stylization that provides a strong inductive bias for consistent novel view synthesis. Specifically, we adopt the emerging neural radiance fields (NeRF) as our choice of 3D scene representation for their capability to render high-quality novel views for a variety of scenes. However, as rendering a novel view from a NeRF requires a large number of samples, training a stylized NeRF requires a large amount …

Reducing Opioid Use Disorder And Overdose Deaths In The United States: A Dynamic Modeling Analysis, Erin J. Stringfellow, Tse Yang Lim, Keith Humphreys, Catherine Digennero, Celia Stafford, Elizabeth Beaulieu, Jack Homer, Wayne Wakeland, Multiple Additional Authors

Systems Science Faculty Publications and Presentations

Opioid overdose deaths remain a major public health crisis. We used a system dynamics simulation model of the U.S. opioid-using population age 12 and older to explore the impacts of 11 strategies on the prevalence of opioid use disorder (OUD) and fatal opioid overdoses from 2022 to 2032. These strategies spanned opioid misuse and OUD prevention, buprenorphine capacity, recovery support, and overdose harm reduction. By 2032, three strategies saved the most lives: (i) reducing the risk of opioid overdose involving fentanyl use, which may be achieved through fentanyl-focused harm reduction services; (ii) increasing naloxone distribution to people who use opioids; …

Making Curry With Rice: An Optimizing Curry Compiler, Steven Libby

Dissertations and Theses

In this dissertation we present the RICE optimizing compiler for the functional logic language Curry. This is the first general optimizing compiler for a functional logic language. Our work is based on the idea of compiling through program transformations, which we have adapted from the functional language compiler community. We also present the GAS system for generating new program transformations, which uses the power of functional logic programming to provide a flexible framework for describing transformations. This allows us to describe and implement a wide range of optimizations including inlining, shortcut deforestation, unboxing, and case shortcutting, a new optimization we …

Scenario Acceleration Through Automated Modelling: A Method And System For Creating Traceable Quantitative Future Scenarios Based On Fcm System Modeling And Natural Language Processing, Christopher W.H. Davis

Dissertations and Theses

Scenario planning is used extensively in strategic planning because it helps leaders broaden their perspectives and make better decisions by presenting possible futures in story form. Some of the benefits of using scenarios include breaking away from groupthink, creating better products, acceleration of organization learning and reducing bias. Product development teams, particularly for digital products, are gaining more autonomy in organizations and tend to manage risk by undergoing very short development iterations on their products while leaning on their consumers for feedback -- a process known as agile development. This method tends to limit the perspective of the team and …

National Climate Data Graphical Plotting Software Review, Melissa Barnes

University Honors Theses

This is a review of an undergraduate Computer Science Capstone project. The paper discusses the development process, what software tools were used, the challenges faced during the development process, and what the software does. The software described in this paper is a python program that utilizes United States county-scoped climate and drought data from the National Climate Data Center to create visualizations and mathematical calculations. The software has an interactive user interface that displays various graphs, heat maps and calculated values. Elevation and population data estimates for populated areas in most counties is also provided. Users may select any set …

The Power Of The Collective: A Multi Agent-Based Modeling Approach To Nuclear Radiation Localization, Benjamin Totten, Christof Teuscher

Student Research Symposium

Gamma radiation is a very high frequency, very dangerous electromagnetic wave that has a chance of being emitted after radioactive decay. Radiation source localization, or locating the previously unknown source of nuclear radiation, in a rapid and efficient manner is critically important, but challenging. We aim to create an architecture for multiple, fully independent agents that cooperate to localize sources faster than existing single-agent architectures, without compromising accuracy. Using Agent-Based Modeling and Deep Reinforcement Learning, agents are enabled to make decisions based on other agents' behaviors while maintaining programmatic autonomy. We hypothesize that radiation sources can be localized faster using …

Growing Reservoir Networks Using The Genetic Algorithm Deep Hyperneat, Nancy L. Mackenzie

Student Research Symposium

Typical Artificial Neural Networks (ANNs) have static architectures. The number of nodes and their organization must be chosen and tuned for each task. Choosing these values, or hyperparameters, is a bit of a guessing game, and optimizing must be repeated for each task. If the model is larger than necessary, this leads to more training time and computational cost. The goal of this project is to evolve networks that grow according to the task at hand. By gradually increasing the size and complexity of the network to the extent that the task requires, we will build networks that are more …

Extending Tensor Virtual Machine To Support Deep-Learning Accelerators With Convolution Cores, Yanzhao Wang, Fei Xie

Computer Science Faculty Publications and Presentations

Deep-learning accelerators are increasingly popular. There are two prevalent accelerator architectures: one based on general matrix multiplication units and the other on convolution cores. However, Tensor Virtual Machine (TVM), a widely used deep-learning compiler stack, does not support the latter. This paper proposes a general framework for extending TVM to support deep-learning accelerators with convolution cores. We have applied it to two well-known accelerators: Nvidia's NVDLA and Bitmain's BM1880 successfully. Deep-learning workloads can now be readily deployed to these accelerators through TVM and executed efficiently. This framework can extend TVM to other accelerators with minimum effort.

Sl-Cyclegan: Blind Motion Deblurring In Cycles Using Sparse Learning, Ali Syed Saqlain, Li-Yun Wang, Zhiyong Liu

Computer Science Faculty Publications and Presentations

In this paper, we introduce an end-to-end generative adversarial network (GAN) based on sparse learning for single image motion deblurring, which we called SL-CycleGAN. For the first time in image motion deblurring, we propose a sparse ResNet-block as a combination of sparse convolution layers and a trainable spatial pooler k-winner based on HTM (Hierarchical Temporal Memory) to replace non-linearity such as ReLU in the ResNet-block of SL-CycleGAN generators. Furthermore, we take our inspiration from the domain-to-domain translation ability of the CycleGAN, and we show that image deblurring can be cycle-consistent while achieving the best qualitative results. Finally, we perform extensive …

Using Intrinsically-Typed Definitional Interpreters To Verify Compiler Optimizations In A Monadic Intermediate Language, Dani Barrack

Dissertations and Theses

Compiler optimizations are critical to the efficiency of modern functional programs. At the same time, optimizations that unintentionally change the semantics of programs can systematically introduce errors into programs that pass through them. The question of how to best verify that optimizations and other program transformations preserve semantics is an important one, given the potential for error introduction. Dependent types allow us to prove that properties about our programs are correct, as well as to design data types and interpreters in such a way that they are correct-by-construction. In this thesis, we explore the use of dependent types and intrinsically-typed …

Classifying Dead Code In Software Development, Arman Alavizadeh

University Honors Theses

Dead code pervades as an issue in the world of software development as a source of many famous software disasters such as the ARIANE 5 rocket failure and chemical bank withdrawal error. Defining dead code on narrow levels of granularity has not been fully explored, yet is crucial to better our understanding of dead code. Here we will be starting a discussion on how to approach classifying dead code via comparing dead code research specific to an industry segment. Research will be compared primarily by methodology and limitations. Dead code subtype classifications are gleaned from research comparisons and can serve …

A New Agent-Based Model Offers Insight Into Population-Wide Adoption Of Prosocial Common-Pool Behavior, Garry Sotnik, Thaddeus Shannon, Wayne Wakeland

Systems Science Faculty Publications and Presentations

New theoretical agent-based model of population-wide adoption of prosocial common-pool behavior with four parameters (initial percent of adopters, pressure to change behavior, synergy from behavior, and population density); dynamics in behavior, movement, freeriding, and group composition and size; and emergence of multilevel group selection. Theoretical analysis of model’s dynamics identified six regions in model’s parameter space, in which pressure-synergy combinations lead to different outcomes: extinction, persistence, and full adoption. Simulation results verified the theoretical analysis and demonstrated that increases in density reduce number of pressure-synergy combinations leading to population-wide adoption; initial percent of contributors affects underlying behavior and final outcomes, …

An Automated Zoom Class Session Analysis Tool To Improve Education, Jack Arlo Cannon Ii

Dissertations and Theses

The recent shift towards remote education has presented new challenges for instructors with respect to teaching evaluation. Students in traditional classrooms send signals to instructors which provide feedback for the effectiveness of a given lecture. Virtual learning environments lack some of these communication channels and require new ways of collecting feedback. This work presents a suite of analysis tools for the virtual instructor. Given the transcript and video files for a Zoom meeting, this tool summarizes student sentiment and speaking characteristics. Sentiment scores are derived using state of the art Natural Language Processing (NLP) models. The video file is used …

Rate Maximization In A Uav Based Full-Duplex Multi-User Communication Network Using Multi-Objective Optimization, Syed Muhammad Hashir, Sabyasachi Gupta, Gavin Megson, Ehsan Aryafar, Joseph Camp

Computer Science Faculty Publications and Presentations

In this paper, we study an unmanned-aerial-vehicle (UAV) based full-duplex (FD) multi-user communication network, where a UAV is deployed as a multiple-input–multiple-output (MIMO) FD base station (BS) to serve multiple FD users on the ground. We propose a multi-objective optimization framework which considers two desirable objective functions, namely sum uplink (UL) rate maximization and sum downlink (DL) rate maximization while providing quality-of-service to all the users in the communication network. A novel resource allocation multi-objective-optimization-problem (MOOP) is designed which optimizes the downlink beamformer, the beamwidth angle, and the 3D position of the UAV, and also the UL power of the …

Reconstructability Analysis: Discrete Multivariate Modeling, Martin Zwick

Systems Science Faculty Publications and Presentations

An introduction to Reconstructability Analysis for the Discrete Multivariate Modeling course and for other purposes.