Digital Commons Network^™

Ai Model For Predicting Asthma Prognosis In Children, Elham Sagheb, Chung-Il Wi, Katherine S King, Bhavani Singh Agnikula Kshatriya, Euijung Ryu, Hongfang Liu, Miguel A Park, Hee Yun Seol, Shauna M Overgaard, Deepak K Sharma, Young J Juhn, Sunghwan Sohn

Faculty, Staff and Student Publications

BACKGROUND: Childhood asthma often continues into adulthood, but some children experience remission. Utilizing electronic health records (EHRs) to predict asthma prognosis can aid health care providers and patients in developing effective prioritized care plans.

OBJECTIVE: We aimed to develop artificial intelligence (AI) models using various clinical variables extracted from EHRs to predict childhood asthma prognosis (remission vs no remission) in different age groups.

METHODS: We developed AI models utilizing patients' EHRs during the first 6, 9, or 12 years of their lives to predict their asthma prognosis status at ages 6 to 9, 9 to 12, or 12 to 15 …

Modeling Language And Vision At Human Scales, Clayton Fields

Boise State University Theses and Dissertations

The impressive results that have recently been achieved in natural language processing and artificial intelligence have been primarily driven by the introduction of the transformer deep learning architecture, increasingly large models with many parameters and using enormous datasets. The size of models and their training data requirements present costly demands that freeze many researchers out of training with cutting edge models. Beyond these practical implications, current methods learn from text alone, without the rich array of sensory information that human beings use in learning language. This means that language models are often incapable of reasoning about the concrete world that …

Leveraging Machine Learning And Deep Learning Techniques For Voter Registration Fraud Detection, Nahid Anwar

Boise State University Theses and Dissertations

The primary objective of this research is to develop an advanced framework for detecting voter registration anomalies, with a specific focus on fraud detection, using the Idaho Voter Registration Election Dataset. The data set contains both anonymized real voter data and synthetically generated fraudulent instances, allowing for a comprehensive examination of potential vulnerabilities in voter registration systems. The real data was obtained from the Idaho Secretary of State's office. The initial part of the research involved data analysis and identification of misinformation and potential disinformation using statistical analysis and approximate string matching algorithms. Subsequently, we have created the aforementioned anonymized …

Advancing Snow Water Equivalent Monitoring With Machine Learning And L-Band Interferometric Synthetic Aperture Radar (Insar) Data, Ibrahim Olalekan Alabi

Boise State University Theses and Dissertations

Seasonal snow is a critical freshwater resource for an estimated 2 billion people worldwide. Yet, accurately measuring the amount of water sitting in a snowpack, referred to as snow water equivalent (SWE), over large, often mountainous regions has posed a long-standing challenge. Ground-based measurements of SWE are precise but sparse, while remote sensing techniques like passive microwave sensors struggle with coarse resolution and signal saturation in deep snow. Due to the challenges of direct SWE measurement, snow depth has emerged as an alternative pathway to SWE estimation. SWE is strongly correlated with snow depth, and by leveraging this relationship, we …

Implementing And Evaluating An Ai-Powered Visual Decision Support System To Improve Antibiotic Usage Among Physicians With A Built-In Early Warning System, Akua Sekyiwaa Osei-Nkwantabisa

Theses and Dissertations

The widespread misuse and excessive prescription of antibiotics have played a pivotal role in the emergence and proliferation of antibiotic-resistant bacteria, posing a critical global public health crisis. Addressing this challenge necessitates innovative solutions that enhance antimicrobial stewardship. This study presents the development and implementation of a visual decision support system designed to monitor and optimize antibiotic usage among healthcare providers. The proposed system integrates advanced machine learning algorithms with real-time data analytics to provide a dynamic, evidence-based decision support tool. Specifically, a neural network model was developed after evaluating multiple machine learning approaches, including Random Forest, Logistic Regression and …

Graph Based Deep Reinforcement Learning Aided By Transformers For Multi-Agent Cooperation, Michael S. Elrod

All Theses

Mission planning for a fleet of cooperative autonomous drones in applications that involve serving distributed target points, such as disaster response, environmental monitoring, and surveil- lance, is challenging, especially under partial observability, limited communication range, and uncertain environments. Traditional path-planning algorithms struggle in these scenarios, particu- larly when prior information is not available. To address these challenges, I propose an innovative framework that integrates Graph Neural Networks (GNNs), Deep Reinforcement Learning (DRL), and transformer-based mechanisms for enhanced multi-agent coordination and collective task ex- ecution. My approach leverages GNNs to model agent-agent and agent-goal interactions through adaptive graph construction, enabling efficient …

Creating Talking Points For Client Advisers At Banks To Promote Sustainable Investing, Wewe Zi Yi, Pradeep Varakantham, Alan Megargel

Research Collection School Of Computing and Information Systems

Environmental, social and governance (ESG) factors have become key nonfinancial factors for investors to evaluate companies with respect to understanding material risks and growth opportunities. While not mandatory, companies are providing ESG reports that outline progress in different ESG metrics (six broad metrics and 15 specific ones). Client advisers (CAs) read these reports to identify key metrics of interest to investors. Given the number of companies and investment products, however, it is not feasible for CAs to read all the reports, which can sometimes run into tens or hundreds of pages). The authors have developed multiple frameworks building on leading …

Developing End-To-End Imitation Learning For Asteroid Proximity Operations, Patrick David Quinn

Theses and Dissertations

Asteroid exploration remains a popular topic in the scientific community, however hurdles still exist for controlling spacecraft within the asteroid environment. Communication delays often require the usage of limited onboard computing hardware for navigation. Additionally, long mission timelines must be accommodated with highly efficient fuel use. Considering these issues, it is apparent that any guidance, navigation, and control (GNC) system in these spacecraft should emphasize both computational and fuel efficiency in its design. Furthermore, the integration of a robust state estimation system is necessary for the successful deployment of such systems. The development of a controller aiming to address these …

Advancing Multi-Agent Robotics Simulations Through Heterogeneous Reinforcement Learning In Isaaclab, Jacob R. Haight

All Graduate Theses and Dissertations, Fall 2023 to Present

Robots increasingly operate in collaborative teams across domains such as search-and- rescue, warehouse automation, and autonomous driving—scenarios that demand advanced coordination strategies enabled by multi-agent reinforcement learning (MARL). However, existing simulation frameworks often struggle to balance realism, speed, and scalability, especially when supporting diverse, heterogeneous robot teams. This research extends Isaac Lab, a high-performance robotics simulator, by integrating heterogeneous-agent reinforcement learning (HARL) capabilities. The result is a flexible and GPU-accelerated platform for training both homogeneous and heterogeneous robot teams in complex, physics-based environments. These enhancements significantly narrow the gap between simulation and real-world deployment for multi-robot systems.

Towards Advancing Streamflow And Peak Flow Prediction With Machine Learning: Identifying Infrastructure At Risk, Sudan Pokharel

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

Due to climate change and its impact, the need for adaptive strategies for natural disaster mitigation and resource management has never been more urgent. Central to this is water resource management, which is essential for sustainable human activities, ecological balance, and the mitigation of natural hazards like floods. Streamflow is a crucial element of water resource management and plays a vital role in planning and building water infrastructure, implementing emergency response plans, supporting flood mitigation initiatives, and regulating agricultural and industrial use. However, accurate prediction of streamflow still remains a challenge due to the complex non-linear and non-stationary interaction between …

Probing The 'Mev Gap': Discovery And Characterization Of Persistent And Transient Mev-Gev Gamma-Ray Sources With The Fermi Large Area Telescoope, Scott Joffre

All Dissertations

The MeV Gap is a moniker for the energy regime E~0.1-100 MeV that has lacked sensitive observations for the last 20 years. This is not out of scientific disinterest, but observational challenges. The only instrument currently available to make observations in the MeV Gap is the Fermi Large Area Telescope (LAT). For the first time ever, Fermi-LAT has been leveraged to push its observational capabilities to its absolute lower energy limit to end this 20-year observational gap. Observing the MeV sky is imperative for identifying some of the most luminous galaxies in the Universe known as blazars. The brightest blazars …

Beyond Regex – Heuristic-Based Secret Detection, Jesse Burdick-Pless

Theses

Accidental token or credential leakage presents a significant concern within digital environments. Current detection methods of such secrets employ ruleset-based techniques to identify secret information. These methods use pattern recognition within strings (i.e., regex rules) to pinpoint characteristics that resemble various types of secrets. However, regex does not allow for detection of secrets that lack specific patterns, such as passwords. This research addresses the possibility of using heuristics and machine learning to develop a reliable and accurate method for determining if a given string is merely a piece of inconsequential data or a leaked secret requiring timely attention, without the …

Achieving Fairness In Zoning Laws With Machine Learning, William Schimitsch

College Honors Program

Zoning is a powerful regulatory tool that determines how municipalities use and develop land. The goal of zoning is to classify land use (e.g., residential, commercial, industrial) to maximize compatibility among neighboring parcels. Local zoning decisions, however, are made by small-sized boards, often through an opaque process, which raises concerns about bias and fairness. In the United States, zoning has historically prioritized single-family housing and thus created economic barriers that limit access to certain communities. Given the task of classifying land use and the wealth of geographical, demographic, and infrastructural data describing each parcel, the problem of bias in zoning …

Energy Forecasting Inaccuracies And Their Direct Impact On Grid Performance, Rashed Khalid Alboom

Theses

Accurate energy forecasting is critical for the stability, efficiency, and cost-effectiveness of modern power grids, particularly as renewable energy sources like solar and wind become more prominent. The variability of these sources presents challenges for traditional forecasting models, which struggle with non-linearity, external dependencies, and evolving grid conditions. These limitations lead to operational inefficiencies, grid instability, and increased financial risks. This study investigates the effectiveness of traditional statistical models, advanced machine learning techniques, and hybrid forecasting approaches to enhance prediction accuracy and grid performance. Using real-world datasets from Kaggle, including historical energy generation, consumption, pricing, and weather variables, this research …

Predicting The Probability Of Crime Related Danger In Los Angeles, Joshua Oghenetega Okpako

Theses

This thesis examines the use of advanced machine learning to predict crime danger in Los Angeles, where 2023 violent crime rates (503 per 100,000) surpass the national average (363.8 per 100,000). Rooted in theories like social disorganization and victim vulnerability, it addresses the lack of combined victim-centric modeling by focusing on three questions: (1) Do blended ensemble models outperform individual models in predicting crime danger? (2) Can unsupervised learning techniques enhance supervised models’ accuracy through label generation or augmentation? (3) How can we interpret accurate machine learning models' decision-making processes? Using historical crime data from Los Angeles (2020–2025) and various …

Using Machine Learning To Detect Vault (Anti-Forensic) Apps, Michael N. Johnstone, Wencheng Yang, Mohiuddin Ahmed

Research outputs 2022 to 2026

Content hiding, or vault applications (apps), are designed with a secondary, often concealed purpose, such as encrypting and storing files. While these apps may serve legitimate functions, they unequivocally present significant challenges for law enforcement. Conventional methods for tackling this issue, whether static or dynamic, prove inadequate when devices—typically smartphones—cannot be modified. Additionally, these methods frequently require prior knowledge of which apps are classified as vault apps. This research decisively demonstrates that a non-invasive method of app analysis, combined with machine learning, can effectively identify vault apps. Our findings reveal that it is entirely possible to detect an Android vault …

Deep Learning Algorithms For Traffic Flow Predictions, Adegoke Ojeniyi, Prince Pal Singh, Ankita Vashisht, Swati Kumari, Karan Karan

AUIQ Technical Engineering Science

Given the growing complexity of urban transportation systems, precise traffic flow forecasting is essential for reducing not only issues of congestion but also, for boosting road safety and enhancing mobility management. This study integrates Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Long Short-Term Memory (LSTM), and Recurrent Neural Networks (RNN) to present a hybrid deep learning framework for traffic prediction. Of these, the CNN-LSTM model is a reliable option for real-time traffic forecasting since it successfully captures both spatial and temporal dependencies, resulting in superior predictive performance. The dataset used to assess the framework includes 48,120 records from a traffic monitoring …

Investigating The Impact Of Waterhead, Time And Temperature On Dam Displacement: Application Of Computer Aided Models, Maaz Abdullah

AUIQ Technical Engineering Science

Dam displacement is a crucial indicator for assessing the safety of a concrete dam through structural health monitoring. Since the displacement data exhibits a non-linear and complex relationship with influencing factors like waterhead, time and temperature, machine learning models are deployed to accurately predict dam displacement. Furthermore, the limited availability of monitored data in the majority of the dams renders the studies conducted with a large number of observations valueless. In order to address the aforementioned issues, this study proposes a feature selection approach to predict dam displacement by examining the ability of four ensemble machine learning models on different …

Investigating The Differential Effects Of Smote Variants On Class Imbalance And Exploring Their Applicability To A Thalassemia Prediction Model, Hussam Mezher Merdas, Ayad Hameed Mousa

AUIQ Technical Engineering Science

Researchers work around the clock on many datasets provided by various institutions. These researchers strive to come up with highly efficient Artificial Intelligence models. Often, researchers face the problem of imbalance in the distribution of classes in a particular feature in the selected dataset, which creates an Artificial Intelligence model biased towards one class at the expense of another class that is no less important than the first. On the other hand, thalassemia is a disease that affects people of different ages. The degree of disease varies according to the thalassemia class. This study proposes an improved Machine Learning model …

Algorithms For Fast Fire Risk Prediction And Real-Time Data Processing, Mirzoyan Mirzaaxmedovich Kamilov, Tolaniddin Ramziddinovich Nurmukhamedov, Oybek Zokirovich Koraboshev, Bakhodir Saydullayevich Achilov

Chemical Technology, Control and Management

Ensuring fire safety in facilities with high fire risk is one of the pressing problems of modern society. Nowadays, there is a great need for accurate and effective prediction systems for fire prevention and rapid response. Since traditional methods do not provide the ability to quickly analyze and predict in real time, the development of algorithms and modern approaches using modern technologies is of great importance. This article analyzes fire risk prediction algorithms, their principles of operation and effectiveness, and considers methods for assessing and predicting fire risk using Artificial Intelligence (AI), Machine Learning (ML), and Big Data technologies. The …

The Attitudes And Perspectives Of Laboratory Professionals On The Use Of Machine Learning Combined With Maldi For Viral Identification: A Qualitative Study, Grace Johnson

Honors Projects

The use of matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) with machine learning (ML) has been proposed by numerous studies as a novel approach for viral identification. However, the development and implementation of this instrumentation is still in its early stages, and laboratory professionals' perspectives on its feasibility, accuracy, implementation, and effect on current laboratory operating procedures remain underexplored.

This study aimed to investigate laboratory professionals’ attitudes and opinions regarding the use of MALDI-TOF-MS coupled with machine learning for viral identification, focusing on perceived benefits, barriers, and factors that would affect participants’ opinions on implementation.

A qualitative descriptive research …

Real-Time Active-Learning Method For Audio-Based Anomalous Event Identification And Rare Events Classification For Audio Events Detection, Farkhund Iqbal, Ahmed Abbasi, Ahmad Almadhor, Shtwai Alsubai, Michal Gregus

All Works

Introduction: Audio event detection, the application of scientific methods to analyze audio recordings, can be helpful in examining and analyzing audio recordings to preserve, analyze, and interpret sound evidence. Furthermore, it can be helpful in safety and compliance, security, surveillance, maintenance, and predictive analysis. Audio event detection aims to recover meaningful information from audio recordings, such as determining the authenticity of the recording, identifying the speakers, and reconstructing conversations. However, filtering out noise for better accuracy in audio event detection is a major challenge. A greater sense of public security can be achieved by developing automated event detection systems that …

Fractal Dimension And Entropy Analysis Of Medical Images For Knn-Based Disease Classification, Krishna Mahapatra, Selvakumar R

Baghdad Science Journal

The study of medical image-based disease detection has witnessed a notable surge in interest and success with computational methods. This work proposes a novel framework to detect diseases at earlier stages from medical images, using mathematical model and Machine Learning. Introduce two new quantitative measures for COVID-19 and Tumor disease detection: image uncertainty based on Shannon entropy and image complexity based on fractal dimension. Our result demonstrated that in COVID-19 positive images exhibited skewed pixel distribution due to the hazy regions resulting in lower entropy values for diseased cases compared to healthy ones. The second quantity, fractal dimension was measured …

The Conditioning Of Reservoir Computing And Ng-Rc For Forecasting And The Effects Of Temporal Overparameterization, Daniel Jensen

Theses and Dissertations

Reservoir computing and "Next-generation reservoir computing" built on nonlinear vector autoregression are algorithms for predicting time series given past observations. Both algorithms have been successful in predicting some chaotic dynamical systems, but this success is not theoretically well understood. This paper considers the conditioning of both algorithms and the nature of the solutions found. With either algorithm, the least squares problem which is solved to give parameters as a function of the time series data is ill-conditioned, leading to parameter non-identifiability. Both algorithms fall into the class of "sloppy models." Standard practice to regularize either algorithm includes a bias towards …

Using Generative Artificial Intelligence To Improve Software-Defined Network Security: A Brief Survey, Anthony Smith

Honors Theses

This paper aims to explore various approaches to using generative artificial intelligence (GenAI) to improve network security in software-defined networking. While software-defined networks provide a more programmable infrastructure, they are not immune to network security threats. Through a combination of Software-Defined Networking (SDN) technologies and generative AI, it is possible to facilitate improved SDN security approaches that promise enhanced network efficiency and protection. Among these approaches, generative adversarial networks (GAN) based models can be employed to generate adversarial traffic samples to train the proposed AI engines proven to be effective in detecting malicious network traffic. Additionally, generative artificial intelligence can …

Improving Efficiency Of Wind Flow Modeling For Wildfire Applications Using Analytical Parameterization And Neural Networks, Laura Jane Housley

Theses and Dissertations

We model wind velocity fields for applications in wildfire modeling. We improve the accuracy of the mass-conserving WindNinja solver without compromising efficient temporal complexity. We consider two approaches: the parameterization method and the neural network method. In the parameterization method, we analyze eddies in the wake of obstacles by parameterizing cavity zones as inspired by the research by Kaplan & Dinar in 1996. Kaplan & Dinar parameterize cavity zones around rectangular buildings, and we approximate a continuous landscape with rectangular buildings in order to extend this parameterization to complex terrains. In the neural network method, we train a U-net CNN …

Securing Edge-Iiot Networks: A Comprehensive Ensemble-Based Ddos Detection System, Fariba Laiq, Feras Al-Obeidat, Adnan Amin, Fernando Moreira

All Works

As the number of Internet of Things (IoT) devices increases daily due to the rapid growth in technology, every device and network is vulnerable to attacks because it is exposed to the internet. Denial of Service (DoS) is a prevalent type of intrusion on the IoT network in which the server becomes down due to flooding requests. Distributed Denial of Service (DDoS) is a special type of DoS attack where the network of malicious computers called botnet consumes the target's system resources by flooding the requests. Edge computing is closely related to Industrial Internet of Things (IIoT), and industry 4.0. …

An Intercomparison Of Wall Fluxes In A Turbulent Thermal Convection Chamber: Direct Numerical Simulations And Wall-Modeled Large-Eddy Simulations Enhanced By Machine Learning, Aaron Wang, Silvio Schmalfuß, Kamal Kant Chandrakar, Hadi Zanganeh Kia, Fan Yang, Mikhail Ovchinnikov, Raymond A. Shaw, Yunsoo Choi

Michigan Tech Publications

Thermal convection in a closed chamber is driven by a warm bottom, a cold top, and side walls at various temperatures. Although wall fluxes are the source of convection energy, accurately modeling these fluxes (i.e., the wall model) is challenging. In large-eddy simulations (LESs), many wall models are traditionally derived from the canonical boundary layer, which may be unsuitable for thermal convection bounded by both horizontal and vertical walls. This study conducts a model intercomparison of dry convection in a cubic-meter chamber using three direct numerical simulations (DNSs) and four LESs with different wall models. The LESs employ traditional wall …

Data-Driven Survival Modeling For Breast Cancer Prognostics: A Comparative Study With Machine Learning And Traditional Survival Modeling Methods, Theophilus Gyedu Baidoo, Hansapani Rodrigo

School of Mathematical & Statistical Sciences Faculty Publications

Background This investigation delves into the potential application of data-driven survival modeling approaches for prognostic assessments of breast cancer survival. The primary objective is to evaluate and compare the ability of machine learning (ML) models and conventional survival analysis techniques, to identify consistent key predictors of breast cancer survival outcomes.

Methods This study employs data-driven survival modeling approaches to predict breast cancer survival, including survival-specific methods such as the Cox Proportional Hazards (CPH) model, Random Survival Forests (RSF), and Cox Proportional Deep Neural Networks (DeepSurv), as well as machine learning models like Random Forests (RF), XGBoost, Support Vector Machines (SVM) …

Enhancing Animal Shelter Operations With Time Series And Machine Learning, Sakava L. Kiv, Donald L. Anderson, Shivam Negi, Jacquelyn Cheun

SMU Data Science Review

Enhancing animal shelter operations through machine learning involves employing a variety of advanced techniques aimed at increasing efficiency, promoting animal welfare, and optimizing resource allocation. This paper explores predictive analytics for adoption rates using regression models to estimate the likelihood of adoption based on historical data, encompassing variables such as breed, health status, and previous adoption trends. Additionally, classification algorithms are utilized to categorize animals by adoption probability, facilitating better resources and marketing prioritization. Clustering algorithms are employed to group animals according to behavior patterns and/or physical health, enabling tailored medical care and enrichment activities that improve their mental and …