Data Science Commons^™

Rhythmedge: Enabling Contactless Heart Rate Estimation On The Edge, Zahid Hasan, Emon Dey, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy, Archan Misra

Research Collection School Of Computing and Information Systems

The primary contribution of this paper is designing and prototyping a real-time edge computing system, RhythmEdge, that is capable of detecting changes in blood volume from facial videos (Remote Photoplethysmography; rPPG), enabling cardio-vascular health assessment instantly. The benefits of RhythmEdge include non-invasive measurement of cardiovascular activity, real-time system operation, inexpensive sensing components, and computing. RhythmEdge captures a short video of the skin using a camera and extracts rPPG features to estimate the Photoplethysmography (PPG) signal using a multi-task learning framework while offloading the edge computation. In addition, we intelligently apply a transfer learning approach to the multi-task learning framework to …

Representation Learning In Finance, Ajim Uddin

Dissertations

Finance studies often employ heterogeneous datasets from different sources with different structures and frequencies. Some data are noisy, sparse, and unbalanced with missing values; some are unstructured, containing text or networks. Traditional techniques often struggle to combine and effectively extract information from these datasets. This work explores representation learning as a proven machine learning technique in learning informative embedding from complex, noisy, and dynamic financial data. This dissertation proposes novel factorization algorithms and network modeling techniques to learn the local and global representation of data in two specific financial applications: analysts’ earnings forecasts and asset pricing.

Financial analysts’ earnings forecast …

Un-Fair Trojan: Targeted Backdoor Attacks Against Model Fairness, Nicholas Furth

Theses

Machine learning models have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a single global model communicating only using local gradients, the issue of attacks become more prevalent and complex. Previously published works revolve around solving these issues both individually and jointly. However, there has been little study on the effects of attacks against model fairness. Demonstrated in this work, a flexible attack, which we call Un-Fair …

Developing A Natural Language Processing Approach For Analyzing Student Ideas In Calculus-Based Introductory Physics, Jon M. Geiger, Lisa M. Goodhew, Tor Ole B. Odden

Honors Projects

Research characterizing common student ideas about particular physics topics has made a significant impact on university-level physics teaching by providing knowledge that supports instructors to target their instruction and by informing curriculum development. This work utilizes a Natural Language Processing algorithm (Latent Dirichlet Allocation, or LDA) to categorize student ideas, with the goal of significantly expediting the process of categorizing student ideas. We preliminarily test the LDA approach by applying the algorithm to a collection of introductory physics student responses to a conceptual question about circuits, specifically attending to whether it is useful for characterizing conceptual resources, or student ideas …

Text Summarization Towards Scientific Information Extraction, Abigail Keller

College of Computing and Digital Media Dissertations

Despite the exponential growth in scientific textual content, research publications are still the primary means for disseminating vital discoveries to experts within their respective fields. These texts are predominantly written for human consumption resulting in two primary challenges; experts cannot efficiently remain well-informed to leverage the latest discoveries, and applications that rely on valuable insights buried in these texts cannot effectively build upon published results. As a result, scientific progress stalls. Automatic Text Summarization (ATS) and Information Extraction (IE) are two essential fields that address this problem. While the two research topics are often studied independently, this work proposes to …

Tissue-Specific Variations In Transcription Factors Elucidate Complex Immune System Regulation, Hengwei Lu, Yi-Ching Tang, Assaf Gottlieb

Faculty, Staff and Student Publications

Gene expression plays a key role in health and disease. Estimating the genetic components underlying gene expression can thus help understand disease etiology. Polygenic models termed "transcriptome imputation" are used to estimate the genetic component of gene expression, but these models typically consider only the cis regions of the gene. However, these cis-based models miss large variability in expression for multiple genes. Transcription factors (TFs) that regulate gene expression are natural candidates for looking for additional sources of the missing variability. We developed a hypothesis-driven approach to identify second-tier regulation by variability in TFs. Our approach tested two models …

Data Ethics: An Investigation Of Data, Algorithms, And Practice, Gabrialla S. Cockerell

Honors Projects

This paper encompasses an examination of defective data collection, algorithms, and practices that continue to be cycled through society under the illusion that all information is processed uniformly, and technological innovation consistently parallels societal betterment. However, vulnerable communities, typically the impoverished and racially discriminated, get ensnared in these harmful cycles due to their disadvantages. Their hindrances are reflected in their information due to the interconnectedness of data, such as race being highly correlated to wealth, education, and location. However, their information continues to be analyzed with the same measures as populations who are not significantly affected by racial bias. Not …

A Novel Correction For The Adjusted Box-Pierce Test, Sidy Danioko, Jianwei Zheng, Kyle Anderson, Alexander Barrett, Cyril S. Rakovski

Mathematics, Physics, and Computer Science Faculty Articles and Research

The classical Box-Pierce and Ljung-Box tests for auto-correlation of residuals possess severe deviations from nominal type I error rates. Previous studies have attempted to address this issue by either revising existing tests or designing new techniques. The Adjusted Box-Pierce achieves the best results with respect to attaining type I error rates closer to nominal values. This research paper proposes a further correction to the adjusted Box-Pierce test that possesses near perfect type I error rates. The approach is based on an inflation of the rejection region for all sample sizes and lags calculated via a linear model applied to simulated …

Inferring Dynamics Of Biological Systems, Tracey G. Oellerich

Biology and Medicine Through Mathematics Conference

No abstract provided.

Cardiovascular Disease Prevention Education Using A Virtual Environment In Sexual-Minority Men Of Color With Hiv: Protocol For A Sequential, Mixed Method, Waitlist Randomized Controlled Trial, S Raquel Ramos, Constance Johnson, Gail Melkus, Trace Kershaw, Marya Gwadz, Harmony Reynolds, Allison Vorderstrasse

Faculty, Staff and Student Publications

Background: It is estimated that 70% of all deaths each year in the United States are due to chronic conditions. Cardiovascular disease (CVD), a chronic condition, is the leading cause of death in ethnic and racial minority males. It has been identified as the second most common cause of death in persons with HIV. By the year 2030, it is estimated that 78% of persons with HIV will be diagnosed with CVD.

Objective: We propose the first technology-based virtual environment intervention to address behavioral, modifiable risk factors associated with cardiovascular and metabolic comorbidities in sexual-minority men of color with HIV. …

An Observational Retrospective Study Of Adverse Events And Behavioral Outcomes During Pediatric Dental Sedation, Kawtar Zouaidi, Gregory Olson, Helen H Lee, Elsbeth Kalenderian, Muhammad F Walji

Faculty, Staff and Student Publications

Purpose: The purpose of this study was to examine a university-based dental electronic health records (EHR) database to identify sedation-related adverse events (AEs) and assess patients' behavioral outcomes during routine pediatric dental sedations (PDSs) in a dental school clinic.

Methods: A database was screened for patients younger than 18 years old who had received dental sedation in 2019. The qualifying EHRs were then accessed and sedations were reviewed for AEs, which were categorized using a 12-point classification system and the Tracking and Reporting Outcomes of Procedural Sedation Tool. Patient behaviors were assessed using provider progress notes and categorized as presence/ …

Real Time Call-Flagging System To Respond To Suicidal Ideation In Call Centers, Vishnu Menon, Joseph Carrigan, Charles Floeder, Thomas Walton, Devin Mcguire

Honors Program: Senior Projects (Public)

The 2021-2022 Signature Performance Design Studio team developed a live audio call-flagging system that enables faster responses and new response pathways to veteran crises by call service representatives and their management team. Using a custom made deep learning model, live audio streaming server, and Teams broadcasting add-on, the system empowers Signature Performance call service representatives to make quicker and more well informed decisions to provide veteran’s the best care possible.

An Evidence-Based Lexical Pattern Approach For Quality Assurance Of Gene Ontology Relations, Rashmie Abeysinghe, Yuntao Yang, Mason Bartels, W Jim Zheng, Licong Cui

Faculty, Staff and Student Publications

Gene Ontology (GO) is widely used in the biological domain. It is the most comprehensive ontology providing formal representation of gene functions (GO concepts) and relations between them. However, unintentional quality defects (e.g. missing or erroneous relations) in GO may exist due to the large size of GO concepts and complexity of GO structures. Such quality defects would impact the results of GO-based analyses and applications. In this work, we introduce a novel evidence-based lexical pattern approach for quality assurance of GO relations. We leverage two layers of evidence to suggest potentially missing relations in GO as follows. We first …

Relational Graph Convolutional Networks For Predicting Blood-Brain Barrier Penetration Of Drug Molecules, Yan Ding, Xiaoqian Jiang, Yejin Kim

Faculty, Staff and Student Publications

MOTIVATION: Evaluating the blood-brain barrier (BBB) permeability of drug molecules is a critical step in brain drug development. Traditional methods for the evaluation require complicated in vitro or in vivo testing. Alternatively, in silico predictions based on machine learning have proved to be a cost-efficient way to complement the in vitro and in vivo methods. However, the performance of the established models has been limited by their incapability of dealing with the interactions between drugs and proteins, which play an important role in the mechanism behind the BBB penetrating behaviors. To address this limitation, we employed the relational graph convolutional …

Impact Of Climate Oscillations/Indices On Hydrological Variables In The Mississippi River Valley Alluvial Aquifer., Meena Raju

Theses and Dissertations

The Mississippi River Valley Alluvial Aquifer (MRVAA) is one of the most productive agricultural regions in the United States. The main objectives of this research are to identify long term trends and change points in hydrological variables (streamflow and rainfall), to assess the relationship between hydrological variables, and to evaluate the influence of global climate indices on hydrological variables. Non-parametric tests, MMK and Pettitt’s tests were used to analyze trend and change points. PCC and Streamflow elasticity analysis were used to analyze the relationship between streamflow and rainfall and the sensitivity of streamflow to rainfall changes. PCC and MLR analysis …

Exploring Technology Advancement Over Time Using Lifespan As The Product Trait And Satellites As The Example Domain, Venkata Jaipal Reddy Batthula

Theses and Dissertations

This research is on trend analysis of average satellite lifetimes. Preliminary research concerned which law (Moore’s Law or Wright’s Law) is better for predicting future satellite lifetimes based on their year of failure. While that work depended on the failure dates of satellites, in this research, using data for the launch dates of satellites, I compare those with their lifetimes to better understand the curves most suitable for determining trends in satellite lifespans and understanding better, based on launch year cohort, the lifetimes of satellites currently in orbit as well as those to be launched in the future. This research …

Factors Associated With Covid-19 Death In The United States: Cohort Study, Uan-I Chen, Hua Xu, Trudy Millard Krause, Raymond Greenberg, Xiao Dong, Xiaoqian Jiang

Faculty, Staff and Student Publications

BACKGROUND: Since the initial COVID-19 cases were identified in the United States in February 2020, the United States has experienced a high incidence of the disease. Understanding the risk factors for severe outcomes identifies the most vulnerable populations and helps in decision-making.

OBJECTIVE: This study aims to assess the factors associated with COVID-19-related deaths from a large, national, individual-level data set.

METHODS: A cohort study was conducted using data from the Optum de-identified COVID-19 electronic health record (EHR) data set; 1,271,033 adult participants were observed from February 1, 2020, to August 31, 2020, until their deaths due to COVID-19, deaths …

Novel Instance-Level Weighted Loss Function For Imbalanced Learning, Trent Geisler

Doctor of Data Science and Analytics Dissertations

Binary classification using imbalanced datasets remains a challenge. Typically, supervised learning algorithms minimize the binary cross-entropy objective function to determine the final parameter estimates. This objective function assumes an equal class distribution between the minority (i.e. events) and majority (i.e. non-events) classes, which almost never exists in real-world modeling. In the imbalanced data setting, the equal class distribution is grossly violated, and the resulting parameter estimates are biased toward the majority class. To overcome the bias and improve model generalization, we focus on modifying the original binary cross-entropy objective function by uniquely weighting each minority class observation. We base our …

Prioritization Of Risk Genes In Multiple Sclerosis By A Refined Bayesian Framework Followed By Tissue-Specificity And Cell Type Feature Assessment, Andi Liu, Astrid M Manuel, Yulin Dai, Zhongming Zhao

Faculty, Staff and Student Publications

BACKGROUND: Multiple sclerosis (MS) is a debilitating immune-mediated disease of the central nervous system that affects over 2 million people worldwide, resulting in a heavy burden to families and entire communities. Understanding the genetic basis underlying MS could help decipher the pathogenesis and shed light on MS treatment. We refined a recently developed Bayesian framework, Integrative Risk Gene Selector (iRIGS), to prioritize risk genes associated with MS by integrating the summary statistics from the largest GWAS to date (n = 115,803), various genomic features, and gene-gene closeness.

RESULTS: We identified 163 MS-associated prioritized risk genes (MS-PRGenes) through the Bayesian framework. …

Building An Artificial Intelligence Framework For Hypertension Diagnosis: A Use Case Of The Problem List Curation, Ketemwabi Yves Shamavu

Theses & Dissertations

Hypertension is the world's leading factor in cardiovascular disease. Forty-seven percent or close to one in two Americans aged 18 and older are affected. It predicts approximately a thousand deaths per day. Based on recent statistics from the Centers for Disease Control and Prevention, one in three patients with hypertension does not know they are hypertensive. Seventy-five percent of hypertensive patients have uncontrolled hypertension - meaning that they are not treated to target. While there is extensive literature on hypertension diagnosis and management, there is an apparent gap in understanding and acknowledging that a person is hypertensive. Moreover, blood pressure …

Trophish: Building A Global Database Of Freshwater Trophic Interactions, Jacob M. Ridgway

Honors Thesis

Freshwater management and research frequently use the trophic data of freshwater fishes. Despite this fact, it is difficult to perform a simple search of dietary information for any one fish species. FishBase represents, to our knowledge, the largest compilation of freshwater dietary information to date. However, it excludes a large portion of the ecological literature due to its development taking place prior to the creation of most modern scientific search engines. Our project (TroPhish) is building upon FishBase by digitizing approximately 130 years of data from the fish predation literature. Data from the primary and grey (e.g. theses, dissertations, reports) …

Generating A Dataset For Comparing Linear Vs. Non-Linear Prediction Methods In Education Research, Jack Mauro, Elena Martinez, Anna Bargagliotti

Honors Thesis

Machine learning is often used to build predictive models by extracting patterns from large data sets. Such techniques are increasingly being utilized to predict outcomes in the social sciences. One such application is predicting student success. Machine learning can be applied to predicting student acceptance and success in academia. Using these tools for education-related data analysis, may enable the evaluation of programs, resources and curriculum. Currently, research is needed to examine application, admissions, and retention data in order to address equity in college computer science programs. However, most student-level data sets contain sensitive data that cannot be made public. To …

Computational Approaches To Facilitate Automated Interchange Between Music And Art, Rao Hamza Ali

Computational and Data Sciences (PhD) Dissertations

Recently, there has been a tremendous increase in generating and synthesizing music and art using various computational techniques. An area that is still under-researched, however, is how one medium can be converted into the other, while maintaining the overall aesthetics. Over the last few centuries, artists, composers, and scholars, have attempted to use substitute one form of art for the other: by proposing techniques where music notes are synonymous to colors, by inventing instruments that combine the aesthetics of music and visual art, and by incorporating the two media in live performances. A widely accepted computational approach, for the conversion, …

How Blockchain Solutions Enable Better Decision Making Through Blockchain Analytics, Sammy Ter Haar

Information Systems Undergraduate Honors Theses

Since the founding of computers, data scientists have been able to engineer devices that increase individuals’ opportunities to communicate with each other. In the 1990s, the internet took over with many people not understanding its utility. Flash forward 30 years, and we cannot live without our connection to the internet. The internet of information is what we called early adopters with individuals posting blogs for others to read, this was known as Web 1.0. As we progress, platforms became social allowing individuals in different areas to communicate and engage with each other, this was known as Web 2.0. As Dr. …

Causalmodels: An R Library For Estimating Causal Effects, Joshua Wolff Anderson

Computational and Data Sciences (MS) Theses

Free and open source software for statistical modeling and machine learning have advanced productivity in data science significantly. Packages such as SciPy in Python and caret in R provide fundamental tools for statistical modeling and machine learning in the two most popular programming languages used by data scientists. Unfortunately, robust tools similar to these are limited in terms of causal inference. The tools in R that exist lack consistent and standardized methodologies and inputs. R lacks a comprehensive package that offers traditional causal inference methods such as standardization, IP weighting, G-estimation, outcome regression, and propensity matching in one common package. …

Data And Algorithmic Modeling Approaches To Count Data, Andraya Hack

Honors College Theses

Various techniques are used to create predictions based on count data. This type of data takes the form of a non-negative integers such as the number of claims an insurance policy holder may make. These predictions can allow people to prepare for likely outcomes. Thus, it is important to know how accurate the predictions are. Traditional statistical approaches for predicting count data include Poisson regression as well as negative binomial regression. Both methods also have a zero-inflated version that can be used when the data has an overabundance of zeros. Another procedure is to use computer algorithms, also known as …

Intraday Algorithmic Trading Using Momentum And Long Short-Term Memory Network Strategies, Andrew R. Whitinger Ii

Undergraduate Honors Theses

Intraday stock trading is an infamously difficult and risky strategy. Momentum and reversal strategies and long short-term memory (LSTM) neural networks have been shown to be effective for selecting stocks to buy and sell over time periods of multiple days. To explore whether these strategies can be effective for intraday trading, their implementations were simulated using intraday price data for stocks in the S&P 500 index, collected at 1-second intervals between February 11, 2021 and March 9, 2021 inclusive. The study tested 160 variations of momentum and reversal strategies for profitability in long, short, and market-neutral portfolios, totaling 480 portfolios. …

Attempting To Predict The Unpredictable: March Madness, Coleton Kanzmeier

Theses/Capstones/Creative Projects

Each year, millions upon millions of individuals fill out at least one if not hundreds of March Madness brackets. People test their luck every year, whether for fun, with friends or family, or to even win some money. Some people rely on their basketball knowledge whereas others know it is called March Madness for a reason and take a shot in the dark. Others have even tried using statistics to give them an edge. I intend to follow a similar approach, using statistics to my advantage. The end goal is to predict this year’s, 2022, March Madness bracket. To achieve …

New Debiasing Strategies In Collaborative Filtering Recommender Systems: Modeling User Conformity, Multiple Biases, And Causality., Mariem Boujelbene

Electronic Theses and Dissertations

Recommender Systems are widely used to personalize the user experience in a diverse set of online applications ranging from e-commerce and education to social media and online entertainment. These State of the Art AI systems can suffer from several biases that may occur at different stages of the recommendation life-cycle. For instance, using biased data to train recommendation models may lead to several issues, such as the discrepancy between online and offline evaluation, decreasing the recommendation performance, and hurting the user experience. Bias can occur during the data collection stage where the data inherits the user-item interaction biases, such as …

New Accurate, Explainable, And Unbiased Machine Learning Models For Recommendation With Implicit Feedback., Khalil Damak

Electronic Theses and Dissertations

Recommender systems have become ubiquitous Artificial Intelligence (AI) tools that play an important role in filtering online information in our daily lives. Whether we are shopping, browsing movies, or listening to music online, AI recommender systems are working behind the scene to provide us with curated and personalized content, that has been predicted to be relevant to our interest. The increasing prevalence of recommender systems has challenged researchers to develop powerful algorithms that can deliver recommendations with increasing accuracy. In addition to the predictive accuracy of recommender systems, recent research has also started paying attention to their fairness, in particular …