Digital Commons Network^™

Machine Learning Based Medical Ultrasound Image Classification And Grad-Cam Interpretation, Victoria C. Hemphill

All Theses

This work takes a step in creating a diagnostic tool for the classification decision process of Achilles tendinopathy using ultrasound images. An attention-based multiple instance learning model is developed to classify the images. Typically, doctors capture multiple ultrasound images of the Achilles tendon during a study to determine a complete diagnosis. Multiple instance models adopt this behavior by providing a single label for a set of instances (images). The images are grouped into ”bags” at the study level and passed into the model. The MIL model then uses its attention property to assign an importance score to each image to …

Use Of A Preliminary Artificial Intelligence-Based Laryngeal Cancer Screening Framework For Low-Resource Settings: Development And Validation Study, Shao Wei Sean Lam, Min Hun Lee, Michael Dorosan, Samuel Altonji, Hiang Khoon Tan, Walter T. Lee

Research Collection School Of Computing and Information Systems

Background: Early-stage diagnosis of laryngeal cancer significantly improves patient survival and quality of life. However, the scarcity of specialists in low-resource settings hinders the timely review of flexible nasopharyngoscopy (FNS) videos, which are essential for accurate triage of at-risk patients.Objective: We introduce a preliminary AI-based screening framework to address this challenge for the triaging of at-risk patients in low-resource settings. This formative research addresses multiple challenges common in high-dimensional FNS videos: (1) selecting clear, informative images; (2) deriving regions within frames that show an anatomical landmark of interest; and (3) classifying patients into referral grades based on the FNS video …

Unveiling Insights From Complexity: Advanced Computational Techniques For High-Dimensional Medical Data, Devin P. Eddington

All Graduate Theses and Dissertations, Fall 2023 to Present

Healthcare generates vast amounts of data daily, from genetic profiles to hospital records, but much of it remains untapped due to its complexity. This dissertation develops new computational tools to unlock this data’s potential, aiming to improve patient care and medical research. Five projects tackle different challenges: Project 1 creates Deep MAGIC, a method to fill in missing genetic and image data accurately, vital for understanding diseases like cancer. Project 2 analyzes how the COVID-19 pandemic disrupted surgeries, finding a 27% drop and temporary complication rises in 2020, guiding future crisis planning. Projects 3 and 4 study kidney disease trials, …

Comparative Analysis Of Sequential And Non-Sequential Modeling Techniques For Ddos Attack Detection With Explainable Ai, Vincent Agbenyeavu

Theses and Dissertations

Cybersecurity is known today as one of the greatest challenges of the modern era. Among the various types of cyber-attacks that threaten our security, the Distributed Denial of Service (DDoS) attack is among some of the most common, effective, and well-recognized attack strategies. Since this form of attack is meant to disrupt the availability factor covertly, it can be detrimental to the targeted machines and difficult to discover. Because of that, there have been several approaches, as well as solutions that have been devised to detect it as accurately and efficiently as possible. In this study, four sequential data modeling …

Low-Cost Monitoring And Fingerprinting Of High-Powered Electric Systems, Kwabena Buamono Aboagye-Otchere

Theses and Dissertations

Electric motors are vital to industry, transport, and energy, yet their maintenance challenges persist. While traditional reactive maintenance leads to costly downtime and safety risks, predictive maintenance, especially through IoT and machine learning offers early fault detection and operational efficiency. However, this shift introduces security concerns due to unintended magnetic emissions from motors. These emissions, though useful for non-intrusive monitoring, can be exploited to eavesdrop on sensitive industrial processes. This dissertation explores the dual nature of magnetic emissions: their value in motor diagnostics and their potential as a security vulnerability. It demonstrates how emissions can identify motors, monitor health, and …

Computational Learning Across Biological And Industrial Systems: Bayesian And Segmentation Models For Epigenomic And Manufacturing Data, Prosenjit Roy

All Theses

In this thesis, we made a complete dual-domain investigation using a machine learning approach into two different scientific areas which were epigenetic analysis of seal species and pore identification in the work of additive manufacturing. The study showcased the flexibility and strength of modern computational tools in addressing complicated issues in various biological and industrial systems. We further investigated the epigenetics by using the Bayesian Neural Network and other machine learning methods to conduct a study on the DNA methylation pattern within three pinniped species (the northern elephant seal, Hawaiian monk seal, and Weddell seal) with perfect precision on species …

Freqllm: Frequency-Aware Large Language Models For Time Series Forecasting, Shunan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently shown promise in Time Series Forecasting (TSF) by effectively capturing intricate time-domain dependencies. However, our preliminary experiments reveal that standard LLM-based approaches often fail to capture global correlations, limiting predictive performance. We found that embedding frequency-domain signals smooths weight distributions and enhances structured correlations by clearly separating global trends (low-frequency components) from local variations (high-frequency components). Building on these insights, we propose FreqLLM, a novel framework that integrates frequency-domain semantic alignment into LLMs to refine prompts for improved time series analysis. By bridging the gap between frequency signals and textual embeddings, FreqLLM effectively captures …

Exploring Rehabilitation Therapists' Knowledge And Perspectives On The Use Of Artificial Intelligence And Machine Learning For Persons Poststroke, Hannah Clark, Mia Delvecchio, Min Hun Lee, Elena D. Brown, Kaia Mikula, Robert Halyama, Kasey Stepansky

Research Collection School Of Computing and Information Systems

Research Objectives: The use of technology such as robotics, gaming systems, self-monitoring apps, or other sensor-based devices in standard practice is infrequent. Due to the rapid development of artificial intelligence (AI) and machine learning (ML) applications, it is important to look at how therapists perceive AI/ML, and design applications with potential barriers in mind. to support future integration into practice. The purpose of this research project is to gain rehabilitation therapists’ perspectives on AI/ML in post-stroke assessment and intervention.Design: This ongoing study uses a mixed methods design with surveys and focus groups. Participants engaged in a 30-minute webinar to learn …

A Focus On Student Education: Determining Student Attitudes Towards Transparent Autograding And Developing Artificially Intelligent Tools To Help Students Succeed, Andra Rice

All Graduate Theses and Dissertations, Fall 2023 to Present

This thesis is composed of two parts both relating to helping students succeed. First, the focus is on determining how we can help students feel more comfortable using an AI tool that can provide them immediate feedback. Second, machine learning algorithms are explored in relation to tracking student tasks to encourage healthy study habits.

The development of effective autograders is key for scaling assessment and feedback. While AI based autograding systems for open-ended response questions have been found to be beneficial for providing immediate feedback, autograders are not always liked, understood, or trusted by students. Our research tested the effect …

Non-Blackbox Robust Design Of Machine Learning In Networks, Venkat Sai Suman Lamba Karanam

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Networked systems have become increasingly complex, with newer communication technologies and standards being added every day. Machine Learning (ML) and Artificial Intelligence (AI) paradigms have been adopted in networks to not only solve many fundamental problems, but also to allow seamless integration of components comprising them. The saying “let’s not reinvent the wheel” in ML/AI adoption implies that model architecture design be left for pure ML/AI researchers, while network researchers focus on input preprocessing (e.g. formatting the packet data to be fed to a model), hyperparameter fine-tuning and a trial-and-error approach to find the “best” result. …

Advancing The Utility Of Unmanned Aerial Systems (Uas)-Based Imaging Techniques In Broadacre Agriculture: A Multimodal Case Study On Table Beets, Mohammad Shahriar Saif

Theses

Efficient and sustainable food production and management are growing concerns in the context of an ever-increasing global population. It is in this context that the integration of remote sensing with advanced imaging technologies presents transformative opportunities for data-driven decision-making in agriculture. This study therefore explores the use of unmanned aerial systems (UAS) equipped with multispectral, hyperspectral, and LiDAR sensors for the non-destructive monitoring of table beet (Beta vulgaris) crop traits, with a specific focus on root yield estimation and foliar disease assessment. Table beet, a subterranean crop of increasing commercial and nutritional importance, poses unique challenges for above-canopy sensing due …

L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring …

Gene Regulatory Network Prediction Using Machine Learning, Deep Learning, And Hybrid Approaches, Sai Teja Mummadi, Md Khairul Islam, Victor Busov, Hairong Wei

Michigan Tech Publications

Construction of gene regulatory networks (GRNs) is essential for elucidating the regulatory mechanisms underlying metabolic pathways, biological processes, and complex traits. In this study, we developed and evaluated machine learning, deep learning, and hybrid approaches for constructing GRNs by integrating prior knowledge and large-scale transcriptomic data from Arabidopsis thaliana, poplar, and maize. Among these, hybrid models that combined convolutional neural networks and machine learning consistently outperformed traditional machine learning and statistical methods, achieving over 95% accuracy on the holdout test datasets. These models not only identified a greater number of known transcription factors regulating the lignin biosynthesis pathway but also …

A Survey Of Image Forensics: Exploring Forgery Detection In Image Colorization, Saurabh Agarwal, Deepak Sharma, Nancy Girdhar, Cheonshik Kim, Ki-Hyun Jung

School of Engineering, Computing and Mathematics

In today’s digital era, the rapid evolution of image editing technologies has brought about a significant simplification of image manipulation. Unfortunately, this progress has also given rise to the misuse of manipulated images across various domains. One of the pressing challenges stemming from this advancement is the increasing difficulty in discerning between unaltered and manipulated images. This paper offers a comprehensive survey of existing methodologies for detecting image tampering, shedding light on the diverse approaches employed in the field of contemporary image forensics. The methods used to identify image forgery can be broadly classified into two primary categories: classical machine …

Comparative Study Of Machine Learning Models For Predicting The Market Value Of Professional Football Players, Álvaro Salvador López

Master's Theses or Doctor of Nursing Practice

The market value of professional football players is a critical factor in decision-making for clubs, agents, and analysts. Accurate player valuation impacts transfers, contract negotiations, and financial planning. In recent years, data-driven approaches have emerged to support traditional scouting with predictive analytics. This thesis presents a comparative study of machine learning models to estimate the market value of football players based on historical performance and personal attributes.

This thesis presents a comparative study of two independently developed machine learning systems designed to predict the market value of football players for the 2020–2021 season. Both systems were trained using real data …

Classifying Heterogeneous Cooperation In Social Dilemmas: Experimental Evidence And Simulation Insights, Sining Wang

Faculty Scholarship

In this paper, we introduce a revealed strategy method to capture heterogeneous behavioral patterns in repeated public goods experiments. This method identifies an individual’s strategic type—a stable decision-making tendency in interactive settings—by analyzing behavioral profiles. We conduct a repeated public goods game to collect participants’ behavioral data and then apply both k-medians and hierarchical clustering algorithms to classify them into five distinctive types: free riders, strong cooperators, above-average conditional cooperators, below-average conditional cooperators, and hump-shaped players. These classifications are then used to construct and calibrate an agent-based simulation model. Our simulation results suggest that policies targeting how conditional cooperators respond …

Alignment Of Perceptual Similarity Metrics With Human Perception, Abhijay Ghildyal

Dissertations and Theses

Perceptual similarity metrics are used for quantitatively evaluating the similarity between two images as it would appear to human perception. These metrics aim to mimic the human visual system, providing a more accurate assessment of visual similarity. Such visual assessments are considered to be more advanced than simple pixel-wise comparisons such as ℓ_p norm distances. Thus, a human-like assessment of visual similarity, makes the metrics valuable for applications in image compression, restoration, and enhancement, where evaluating perceptual quality is crucial. Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the …

What Drives Weight Status Among Female University Students? A Machine Learning Analysis Of Sociodemographic, Dietary, And Lifestyle Determinants, Radwan Qasrawi, Abir Ajab, Leila Cheikh Ismail, Ayesha Al Dhaheri, Sharifa Alblooshi, Razan Abu Ghoush, Stephanny Vicuna Polo, Malak Amro, Suliman Thwib, Ghada Issa, Haleama Al Sabbah

All Works

Background: Obesity and underweight are increasingly common among young adult women, often resulting from complex interactions between diet, lifestyle, and socioeconomic factors. This study addresses that gap by applying machine learning to a wide range of behavioral, dietary, and demographic data. The main research question asks: What are the key factors influencing weight status among female university students, and how accurately can machine learning models identify them? We hypothesize that different factors are significantly associated with underweight, overweight, and obesity, and that machine learning can reliably detect these patterns. The aim is to identify the strongest predictors and support more …

Detecting Android Malware Based On Static Analysis Using Classification And Modified Clustering Techniques, Abdullah Allawi Al-Sraratee, Ahmed Habeeb Al-Azawei

Journal of Intelligent Informatics, Networking, and Cybersecurity

Because Android malware harms internet security, prior research proposes several different approaches to detect it accurately. However, such proposed models depend on numerous number of features to attain high accuracy. This could lead to high computation cost and potential overfitting. Furthermore, manual data labeling is labor-intensive, requiring significant human effort and skills. This research aims to: 1) extend previous literature on Android malware detection, 2) improve the accuracy of Android malware detection based on a low number of features, and 3) modify a clustering technique to group data into two different clusters to address the issue of unlabeled data. To …

Predicting Sleep And Sleep Stage In Children Using Actigraphy And Heartrate Via A Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation, Robert Weaver Med, Phd, James White, Olivia Finnegan, Hongpeng Yang, Zifei Zhong, Keagan Kiely, Catherine Jones, Yan Tong, Srihari Nelakuditi, Rahul Ghosal, David E. Brown, Russell R. Pate Ph.D., Gregory J. Welk, Massimiliano De Zambotti, Yuan Wang, Sarah Burkart, Elizabeth L. Adams Phd, Bridget Armstrong, Michael Beets Med, Mph, Phd

Faculty Publications

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years,52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred be-cause of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables(i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Machine Learning Crime Prediction Models And The Gap Between Research And Implementation: A Systematic Review, Ricardo Huamantingo, Miguel Cano-Lengua, Ciro Rodriguez

Karbala International Journal of Modern Science

A crime is an illegal or violent act committed by one individual against another. The increasing crime rate has become a major concern as it negatively affects people's quality of life and generates significant social and economic costs. This study aims to identify the most widely used machine learning (ML) models for crime prediction, determine evaluation metrics for assessing model performance, and analyze key data characteristics to enhance real-world implementation. The study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. A search string was formulated using the population, intervention, comparison, and outcomes (PICO) framework and applied …

Prediction, Comparison And Visualization Of Premium Pricing Using Machine Learning Methods, Lal S Jan, Farzan Tashfeen, Mohid Hussain, Nadi M Alresheedi, Syed Muhammad Hassan Ahmer, Nahla M Albarkati

Yanbu Journal of Engineering and Science

This study investigates the efficacy of machine learning in forecasting and comparing health insurance premiums. The all-inclusive goal line is to improve the accuracy of premium pricing and minimize the manual labor associated with the traditional methods and present data trends in a logical manner. An open-source dataset of US medical premiums has been utilized and a systematic machine learning model in python programming language has been developed. This model took into account factors like age, bmi, smoking habits, and geographical location. The XGBoost model excels other models with an RMSE value of 0.349 and an adjusted R2 of 90.1% …

Leveraging Weekly Snow Cover Time Series For Improved Glacier Monitoring And Modeling, Rainey Aberle, Ellyn M. Enderlin, David R. Rounce, Shad O'Neel, Brandon Tober, Alexandra Friel

Boise State University Publications and Presentations

Seasonal snow and ice melt strongly influence glacier mass balance, yet sparse sub-annual observations limit our understanding of seasonal dynamics. Here we construct and analyze weekly snow cover time series for 200 glaciers across western North America from 2013 to 2023 using an automated image processing pipeline. Snow cover varied widely across the region: snow minima timing varied with latitude — from August from 62 to 64N to October from 48 to 50N—and accumulation area ratios ranged from near-zero to 0.92 (median of 0.52). A comparison of snowlines from observations and the PyGEM glacier mass balance model revealed seasonally evolving …

Towards Leveraging Social Media Data For Fostering Collaborations Among Non-Profits, Monazil Chowdhury

LSU Doctoral Dissertations

Nonprofit organizations serve a crucial role in tackling a wide range of significant social, environmental, and economic issues. But it is often hard to get a clear picture of their work because their information is spread out and it is difficult to see how they are collaborating. To address this issue we developed a web-based tool to collect scattered data—from a variety of sources, such as the IRS, social media, and the Census, into one easy-to-use resource. The tool begins by taking IRS records and geocoding each nonprofit’s physical address With its coordinates. It then retrieves census tract information from …

A Machine Learning Approach To Quantitative X-Ray Diffraction Analysis, Spencer Snow Chandler

Theses and Dissertations

X-ray Powder Diffraction (XRPD) is a powerful method in material sciences that gives insights into the atomical and crystallographic structure of a material, revealing information into the material's properties and suitability for industrial and scientific application. In geology, XRPD analysis is frequently leveraged to identify and quantify the present mineral phases in an unknown mixture. Despite it's widespread use, interpreting XRPD patterns requires highly-specialized knowledge, making the analysis largely dependent upon the background experience of the analyst. To assist experts, computational methods have been developed over the years. Some of these techniques involve fitting diffraction patterns using pseudo-Voigt functions, which …

Seeking Structure In Complex Systems: From Feature Analysis To Space-Time Causal Discovery With Earth Science Applications, Jeffrey J. Nichol

Computer Science ETDs

Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. This body of research presents my investigations into data-driven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that …

Benford's Law In Basic Rnn And Long Short-Term Memory And Their Associations, Farshad Ghassemi Toosi

Department of Computer Science Publications

Benford's Law describes the distribution of numerical patterns, specifically focusing on the frequency of the leading digit in a set of natural numbers. It divides these numbers into nine groups based on their first digit, with the largest category comprising numbers beginning with 1, followed by those starting with 2, and so on. Each neuron within a neural network (NN) is associated with a numerical value called a weight, which is updated according to specific functions. This research examines the Degree of Benford's Law Existence (DBLE) across two language model methodologies: (1) recurrent neural networks (RNNs) and (2) long short-term …

Deep Learning For Absorption-Image Analysis, Jacob Morrey, Isaac Peterson, Robert H. Leonard, Joshua M. Wilson, Francisco Fonta, Matthew B. Squires, Spencer E. Olson

Space Dynamics Laboratory Publications

The quantum state of ultracold atoms is often determined through measurement of the spatial distribution of the atom cloud. Absorption imaging of the cloud is regularly used to extract this spatial information. Accurate determination of the parameters which describe the spatial distribution of the cloud is crucial to the success of many ultracold atom applications. In this work, we present modified deep learning image classification models for image regression. To overcome challenges in data collection, we train the model on simulated absorption images. We compare the performance of the deep learning models to least-squares techniques and show that the deep …

Exploring System Identification Of Non-Linear Dynamics Using The Weighted Composition Operator And The Liouville Operator, Chukwuebuka Amagwula

USF Tampa Graduate Theses and Dissertations

System identification is the process of determining mathematical models that describe the dynamics of a system from data. Dynamic Mode Decomposition (DMD) and Sparse Identification of Nonlinear Dynamical Systems (SINDy) are two distinct approaches used for this purpose.

DMD identifies dominant spatiotemporal modes and eigenvalues that describe the evo lution of a system. It assumes a near-linear representation of dynamics and is closely linked to the Koopman operator, making it ideal for analyzing fluid flows, oscillatory systems, and modal structures. The DMD method uses time series data where each data point is referred to as a snapshot and represents the …

Leveraging Machine Learning For Accurate Prediction Of Nba Player Salaries, Ye Cheng, Yan Song, Mingqi Wang

Iraqi Journal for Computer Science and Mathematics

Basketball players in the NBA are renowned for their talent, athleticism, and commitment to the game. NBA players may make enormous sums of money; however, they vary greatly. Rookie agreements begin at a lower price and go up following performance. NBA players’ pays are influenced by several factors. Because they influence games and the success of the club, exceptional players fetch larger compensation. This study employs Machine Learning (ML) techniques, including Lasso Regression and Random Forest Regression (RFR) models to analyze wage trends, enhanced by the Slime Mould Algorithm (SMA) and Artificial Rabbit Optimization (ARO) for accuracy. The goal is …