Data Science Commons^™

Predicting 30-Day Unplanned Icu Readmissions Using Deep Learning And Natural Language Processing Techniques: A Mimic Iv Data Analysis, David Licerio

Computational and Data Sciences (MS) Theses

We design and implement a multi-stage modeling approach focused on predicting unplanned 30-day all- cause intensive care unit (ICU) hospital readmissions using the Medical Information Mart for Intensive Care (MIMIC IV) dataset. Structured data consisting of demographic information, comorbidities, lab results, and vital signs are combined with features extracted from medical text data consisting of patients’ diagnoses, procedures, and discharge notes and further engineered using several methods, including Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and word embeddings.

We sequentially implement three distinct Dense Neural Networks (DNNs) combined with the LightGBM gradient-boosting framework. Our model attained a 5-fold cross-validated …

Traffic Analysis Of Cities In San Bernardino County, Sai Kalyan Ayyagari

Electronic Theses, Projects, and Dissertations

This research offers an in-depth analysis of vehicular traffic within San Bernardino County, California, aiming to spotlight congestion areas and suggest improvements for more efficient and sustainable transportation. Leveraging 2021 data from StreetLight Data, traffic patterns in 15 key cities were examined based on their population sizes, covering various vehicle types to dissect dynamics and flow. The methodology focused on analyzing trip purposes and metrics to calculate Vehicle Miles Traveled (VMT) and its influence on congestion and environmental factors.

Findings indicate considerable disparities in traffic volume, purposes, and timings across different urban areas, with population density and intercity connections significantly …

Truck Traffic Analysis In The Inland Empire, Bhavik Khatri

Electronic Theses, Projects, and Dissertations

This study undertakes a meticulous examination of truck traffic within the Inland Empire, focusing on the distribution and dynamics of medium and heavy-duty vehicles, to advocate for the region's transition to electric trucks. Utilizing advanced spatial analysis and data from Streetlight Data, it segments the region into six subregions, revealing distinct traffic patterns and environmental impacts. Notably, the research uncovers that the North Center and West zones, integral to the logistics and warehousing sectors, exhibit the highest traffic volumes, significantly influencing air quality and infrastructure.

Quantitative results from 2021 illustrate a pronounced disparity in truck activity: medium-weight vehicles accounted for …

Code For Care: Hypertension Prediction In Women Aged 18-39 Years, Kruti Sheth

Electronic Theses, Projects, and Dissertations

The longstanding prevalence of hypertension, often undiagnosed, poses significant risks of severe chronic and cardiovascular complications if left untreated. This study investigated the causes and underlying risks of hypertension in females aged between 18-39 years. The research questions were: (Q1.) What factors affect the occurrence of hypertension in females aged 18-39 years? (Q2.) What machine learning algorithms are suited for effectively predicting hypertension? (Q3.) How can SHAP values be leveraged to analyze the factors from model outputs? The findings are: (Q1.) Performing Feature selection using binary classification Logistic regression algorithm reveals an array of 30 most influential factors at an …

Interpreting Shift Encoders As State Space Models For Stationary Time Series, Patrick Donkoh

Electronic Theses and Dissertations

Time series analysis is a statistical technique used to analyze sequential data points collected or recorded over time. While traditional models such as autoregressive models and moving average models have performed sufficiently for time series analysis, the advent of artificial neural networks has provided models that have suggested improved performance. In this research, we provide a custom neural network; a shift encoder that can capture the intricate temporal patterns of time series data. We then compare the sparse matrix of the shift encoder to the parameters of the autoregressive model and observe the similarities. We further explore how we can …

Multimodal Stylometry: A Novel Approach For Authorship Identification., Glory O. Adebayo

Electronic Theses and Dissertations

This dissertation introduces multimodal stylometry, a novel approach to authorship identification that integrates text and source code features for a comprehensive understanding of an author's unique style. Traditional stylometric methods have primarily focused on either text stylometry or source code stylometry, thereby neglecting the potential insights that multimodality may provide. This research aims to bridge this gap by proposing a framework that combines textual and source code data to enhance the accuracy and reliability of authorship identification. The study begins by reviewing existing literature on authorship identification and stylometry, highlighting the limitations of unimodal approaches. Leveraging recent advancements in multimodal …

Computational Linguistics And Multilingualism: A Comparative Analysis With Spanish And English Data, Evelyn Lawrie

Student Scholar Symposium Abstracts and Posters

Computational linguistics is an increasingly ubiquitous field, serving as the basis for artificial intelligence and machine translation. It aims to analyze the syntax and semantics of individual words and phrases. While there have been in-depth advancements in computational linguistics strategies for the English language, others have not been developed as thoroughly. This lack of emphasis on multilingualism has contributed to the disappearance of Hispanic perspectives in the digital world. Especially those of indigenous heritage, as the decline of many indigenous languages has been exacerbated by the lack of digital translation services. Sentiment analysis is a branch of computational linguistics that …

Representation Learning For Generative Models With Applications To Healthcare, Astronautics, And Aviation, Van Minh Nguyen

Theses and Dissertations

This dissertation explores applications of representation learning and generative models to challenges in healthcare, astronautics, and aviation.

The first part investigates the use of Generative Adversarial Networks (GANs) to synthesize realistic electronic health record (EHR) data. An initial attempt at training a GAN on the MIMIC-IV dataset encountered stability and convergence issues, motivating a deeper study of 1-Lipschitz regularization techniques for Auxiliary Classifier GANs (AC-GANs). An extensive ablation study on the CIFAR-10 dataset found that Spectral Normalization is key for AC-GAN stability and performance, while Weight Clipping fails to converge without Spectral Normalization. Analysis of the training dynamics provided further …

Evaluation Of An End-To-End Radiotherapy Treatment Planning Pipeline For Prostate Cancer, Mohammad Daniel El Basha, Court Laurence, Carlos Eduardo Cardenas, Julianne Pollard-Larkin, Steven Frank, David T. Fuentes, Falk Poenisch, Zhiqian H. Yu

Dissertations and Theses (Open Access)

Radiation treatment planning is a crucial and time-intensive process in radiation therapy. This planning involves carefully designing a treatment regimen tailored to a patient’s specific condition, including the type, location, and size of the tumor with reference to surrounding healthy tissues. For prostate cancer, this tumor may be either local, locally advanced with extracapsular involvement, or extend into the pelvic lymph node chain. Automating essential parts of this process would allow for the rapid development of effective treatment plans and better plan optimization to enhance tumor control for better outcomes.

The first objective of this work, to automate the treatment …

Design And Application Of Smart Systems To Address Analytical Problems, Lucas B. Ayres

All Dissertations

This dissertation is a multidisciplinary effort that integrates low-cost analytical instrumentation, redox chemistry, and artificial intelligence to overcome existing limitations in the fields of wearable sensing technology, Deep Eutectic Solvents (DES), and antioxidant chemistry. The overall goal behind each implemented strategy is to enhance the accuracy, efficiency, and accessibility of analytical processes and technologies. A general overview of the thesis, along with the research outcomes is included in Chapter One. The theoretical framework of this dissertation is presented in Chapter Two. Chapter Three describes the development of a wearable platform (sensor and instrumentation) to rapidly detect (~20 minutes) S. aureus …

Establishing “The Fossil Record”: A Database Of Vertebrate Paleontological Sites Across The State Of Tennessee, Sarah Mclaurine

Electronic Theses and Dissertations

Fossil localities across the state of Tennessee and the data related to those sites were compiled from Tennessee Division of Geology Bulletin 84, titled “Tennessee’s Prehistoric Vertebrates,” and stored in a Microsoft Access geodatabase housed by the Department of Collections at the East Tennessee State University Museum of Natural History located at the Gray Fossil Site. Included in the database are forms to enter new site localities, view information about those already entered, view and add data to a master faunal list for the state, view sites repository information and store and add documents that are key-word searchable from the …

Bacteria Synergized With Pd-1 Blockade Enhance Positive Feedback Loop Of Cancer Cells-M1 Macrophages-T Cells In Glioma, Qi Chen, Yuyi Zheng, Xiaojie Chen, Yuan Xing, Jiajie Zhang, Xinyi Yan, Qi Zhang, Di Wu, Zhong Chen

Faculty, Staff and Student Publications

Cancer immunotherapy is an attractive strategy because it stimulates immune cells to target malignant cells by regulating the intrinsic activity of the immune system. However, due to lacking many immunologic markers, it remains difficult to treat glioma, a representative "cold" tumor. Herein, to wake the "hot" tumor immunity of glioma, Porphyromonas gingivalis (Pg) is customized with a coating to create an immunogenic tumor microenvironment and further prove the effect in combination with the immune checkpoint agent anti-PD-1, exhibiting elevated therapeutic efficacy. This is accomplished not by enhancing the delivery of PD-1 blockade to enhance the effect of immunotherapy, but by …

A Framework That Explores The Cognitive Load Of Cs1 Assignments Using Pausing Behavior, Joshua O. Urry

All Graduate Theses and Dissertations, Fall 2023 to Present

Pausing behavior in introductory Computer Science (CS1) courses has been related to a student’s performance in the course and could be linked to a student’s cognitive load, or assignment difficulty. Having an objective measure of the cognitive load would be beneficial to course instructors as it would help them design assignments that are not too difficult. Two studies are presented in this work. The first study uses Cognitive Load Theory and Vygotsky’s Zone of Proximal Development as a theoretical framework to analyze pause times between keystrokes to better understand what types of assignments need more educational support than others. The …

Sports Science: An Entrepreneurial Venture, Nicole J. Jones

Senior Honors Projects

In sports science, ensuring maximum athlete safety and optimizing data utilization are pivotal yet leave room for further work. My project, Unbeaten SafeWare, addresses these critical issues by focusing on two primary concerns: preventing heat-related and cardiac illnesses, which are significant causes of athlete fatalities, and enhancing the transparency and utility of sports data. This initiative involves developing a shirt integrated with sensors to monitor vital signs and an athlete management system to handle data input, storage, analysis, and accessibility for athletes.

The project has advanced through the efforts of a multidisciplinary team, which includes biomedical engineering undergraduates, two faculty …

Denoising Diffusion Probabilistic Models Based Accelerated Mri, Alexander Francis Bugielski

Theses and Dissertations

Magnetic Resonance Imaging (MRI) is a cornerstone in obtaining intricate visualizations of anatomy and physiological processes within the human body. However, its extensive scan duration not only causes patient discomfort but also increases the likelihood of motion-induced artifacts in the images. To address such a challenge, this study investigates deep neural network models for reconstructing high-resolution MRI images from noisy and significantly undersampled data in a supervised learning manner. Specifically, it compares three models: a conventional U-Net, a self-attentive U-Net, and an innovative probabilistic diffusion model that builds upon the self-attentive U-Net architecture. These models are evaluated on their ability …

Study On A Strong Polymer Gel By The Addition Of Micron Graphite Oxide Powder And Its Plugging Of Fracture, Bin Shi, Guangming Zhang, Lei Zhang, Chengjun Wang, Zhonghui Li, Fangping Chen

Faculty, Staff and Student Publications

It is difficult to plug the fracture water channeling of a fractured low-permeability reservoir during water flooding by using the conventional acrylamide polymer gel due to its weak mechanical properties. For this problem, micron graphite powder is added to enhance the comprehensive properties of the acrylamide polymer gel, which can improve the plugging effect of fracture water channeling. The chemical principle of this process is that the hydroxyl and carboxyl groups of the layered micron graphite powder can undergo physicochemical interactions with the amide groups of the polyacrylamide molecule chain. As a rigid structure, the graphite powder can support the …

Alterations In Brain Morphometric Networks And Their Relationship With Memory Dysfunction In Patients With Type 2 Diabetes Mellitus, Rye Young Kim, Yoonji Joo, Eunji Ha, Haejin Hong, Chaewon Suh, Youngeun Shim, Hyeonji Lee, Yejin Kim, Jae-Hyoung Cho, Sujung Yoon, In Kyoon Lyoo

Faculty, Staff and Student Publications

Cognitive dysfunction, a significant complication of type 2 diabetes mellitus (T2DM), can potentially manifest even from the early stages of the disease. Despite evidence of global brain atrophy and related cognitive dysfunction in early-stage T2DM patients, specific regions vulnerable to these changes have not yet been identified. The study enrolled patients with T2DM of less than five years’ duration and without chronic complications (T2DM group, n=100) and demographically similar healthy controls (control group, n=50). High-resolution T1-weighted magnetic resonance imaging data were subjected to independent component analysis to identify structurally significant components indicative of morphometric networks. Within these networks, the groups’ …

Comprehensive Analysis Of Bulk And Single-Cell Transcriptomic Data Reveals A Novel Signature Associated With Endoplasmic Reticulum Stress, Lipid Metabolism, And Liver Metastasis In Pancreatic Cancer, Xiaohong Liu, Bo Ren, Yuan Fang, Jie Ren, Xing Wang, Minzhi Gu, Feihan Zhou, Ruiling Xiao, Xiyuan Luo, Lei You, Yupei Zhao

Faculty, Staff and Student Publications

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a lethal malignancy with high probability of recurrence and distant metastasis. Liver metastasis is the predominant metastatic mode developed in most pancreatic cancer cases, which seriously affects the overall survival rate of patients. Abnormally activated endoplasmic reticulum stress and lipid metabolism reprogramming are closely related to tumor growth and metastasis. This study aims to construct a prognostic model based on endoplasmic reticulum stress and lipid metabolism for pancreatic cancer, and further explore its correlation with tumor immunity and the possibility of immunotherapy.

METHODS: Transcriptomic and clinical data are acquired from TCGA, ICGC, and GEO …

Cradle Explorer: Casfer Interactive Platform For Data And Model Visualization, Olatunde D. Akanbi, Vibha S. Mandayam, Haiping Ai, Arafath Nihar, Erika I. Barcelos, Laura S. Bruckman, Jeffrey Yarus, Yinghui Wu, Huichun (Judy) Zhang, Roger H. French

Student Scholarship

No abstract provided.

An Investigation Into The Causes Of Home Field Advantage In Professional Soccer, Paige E. Tomer

Mathematics, Statistics, and Computer Science Honors Projects

Home-field advantage is the sporting phenomenon in which the home team outperforms the away team. Despite its widespread occurrence across sports, the underlying reasons for home-field advantage remain uncertain. In this paper, we employ a range of statistical methods to explore the causal relationships of potential determinants of home-field advantage. We measure home-field advantage using match outcomes and differential metrics (e.g., differences in yellow cards received). In an attempt to narrow the research disparity between men’s and women’s sports, we utilize data from the National Women’s Soccer League (NWSL) and the English Premier League (EPL) to investigate potential causes of …

Develop An Interactive Python Dashboard For Analyzing Ezproxy Logs, Andy Huff, Matthew Roth, Weiling Liu

Faculty and Staff Scholarship

This paper describes the development of an interactive dashboard in Python with EZproxy log data. Hopefully, this dashboard will help improve the evidence-based decision-making process in electronic resources management and explore the impact of library use.

The Impact Of Family Functioning Factors On Smartphone Addiction And Phubbing Among Muslim Adolescents In Thailand, Yejin Kim, Wanchai Dhammasaccakarn, Kasetchai Laeheem, Idsaratt Rinthaisong

Faculty, Staff and Student Publications

BACKGROUND: While there is research on protective factors against smartphone addiction (SA) and phubbing, which impact adolescents' physical, psychological, interpersonal, and academic well-being, focused studies on these issues among Thai Muslim students in Southern Thailand remain scarce.

OBJECTIVES: To bridge this gap, this research aimed to explore the influence of five family functioning factors-discipline, communication and problem-solving (CPS), relationship, emotional status, and family support-guided by family systems theory and the McMaster Model, on SA and phubbing.

METHODS: Data from 825 Thai Muslim adolescent secondary school students (Female N = 459 (55.7%), M

RESULTS: Significant connections were identified between family functioning …

Uconn Baseball Reliever Lane Optimization Tool, Jason Bartholomew

Honors Scholar Theses

The building of a tool to be utilized by UConn’s Division I baseball team that will generate a game plan for when different relievers should be used against different parts of the opponent’s lineup to achieve the lowest total expected value of runs allowed for the remainder of the game based on game situations and matchup probabilities. The tool will also examine and determine situations that may be vital enough to the outcome of the game to bring in a better reliever normally saved for later in the game.

Virtual Reality As An Adjunct To Behavior Therapy: A Systematic Literature Review, Alya Alharrasi

Honors Theses

The World Health Organization (WHO) projects that by 2030, mental disorders will become the primary source of global disease burden [1]. Anxiety-related disorders, including specific phobias, post-traumatic stress disorder (PTSD), and various forms of general or specific anxiety, are the most rapidly growing mental health disorders worldwide [2]. In the United States (US), over 1 in 10 American youths are experiencing depression, resulting in a severe impact on their personal, academic, or professional encounters and social engagements [3]. Similarly, anxiety disorders affect up to one-third of the US population during their lifetime [4].

Due to the growth of mental health …

Data Engineering: Building Software Efficiency In Medium To Large Organizations, Alessandro De La Torre

Whittier Scholars Program

The introduction of PoetHQ, a mobile application, offers an economical strategy for colleges, potentially ushering in significant cost savings. These savings could be redirected towards enhancing academic programs and services, enriching the educational landscape for students. PoetHQ aims to democratize access to crucial software, effectively removing financial barriers and facilitating a richer educational experience. By providing an efficient software solution that reduces organizational overhead while maximizing accessibility for students, the project highlights the essential role of equitable education and resource optimization within academic institutions.

An Assessment On The Influence Of Aridity And Vegetation Cover On Land Surface Temperatures: Case Of Dodoma Urban District, Tanzania, Carolyne Vincent Mbirika

Research, Papers & Creative Work

This study examines the influence of aridity and vegetation cover on land surface temperature (LST) in Dodoma Urban District, Tanzania, a semi-arid environment experiencing rapid urban growth. Using Landsat 9 satellite imagery (30 m resolution) for October 2023, key environmental variables including the Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), and LST were derived and analyzed using ArcGIS Pro. The study applies remote sensing techniques and spatial analysis to examine the relationships between vegetation, moisture availability, and surface temperature patterns. The results reveal substantial spatial variation across the study area, with NDVI values ranging from -0.17 to …

Subject Analysis Ex Machina: Developing A Subject Heading Recommendation Service For Jmu Libraries, Steven W. Holloway

Libraries

Results of a 2022 evaluation of ANNIF, open-source software designed to generate controlled vocabulary subject headings, using James Madison University Libraries resources.

Nurse Anesthetists’ Perceptions And Experiences Of Managing Emergence Delirium: A Qualitative Study, Yi Xin, Fu-Cai Lin, Chen Huang, Bin He, Ya-Ling Yan, Shuo Wang, Guang-Ming Zhang, Rui Li

Faculty, Staff and Student Publications

BACKGROUND: This study employs a descriptive phenomenological approach to investigate the challenges anesthesia nurses face in managing emergence delirium (ED), a common and complex postoperative complication in the post-anesthesia care unit. The role of nurses in managing ED is critical, yet research on their understanding and management strategies for ED is lacking.

AIM: To investigate anesthetic nurses' cognition and management experiences of ED in hopes of developing a standardized management protocol.

METHODS: This study employed a descriptive phenomenological approach from qualitative research methodologies. Purposeful sampling was utilized to select 12 anesthetic nurses from a tertiary hospital in Shanghai as research …

Visualizing Nfl Player Metrics, Jayson Rhea

Campus Research Month

This project is dedicated to reshaping the exploration of NFL player data. Tailored for sports analysts and fantasy football managers, the goal is to deliver convenience through seamless data navigation and precise filtering through an interactive dashboard. In contrast to the static formats found on the NFL website and ESPN, this dynamic interface offers interactive visualizations, empowering users to effortlessly compare data. These comparisons can be used draw quick conclusions about player performance.

Dashboard To Quickly Estimate The Cost And Duration Of An Nyc Green Taxi Trip, Isaac Braun

Campus Research Month

Before hailing a New York City (NYC) taxi, residents and tourists do not easily know how much the trip will cost them or how long it may take. Taxis are still heavily used, even with the increase of ride-hailing services like Uber, and a new system has yet to be built to provide customers with these two metrics before taking a trip. This project aims to give riders a quick way to estimate a ride’s cost and duration through an interactive dashboard that allows filtering by pickup and drop-off neighborhoods. This is accomplished by analyzing three years of public data …