Data Science Commons^™

Generalizing Parkinson’S Disease Detection Using Keystroke Dynamics: A Self-Supervised Approach, Shikha Tripathi, Alejandro Acien, Ashley A Holmes, Teresa Arroyo-Gallego, Luca Giancardo

Faculty, Staff and Student Publications

Objective: Passive monitoring of touchscreen interactions generates keystroke dynamic signals that can be used to detect and track neurological conditions such as Parkinson's disease (PD) and psychomotor impairment with minimal burden on the user. However, this typically requires datasets with clinically confirmed labels collected in standardized environments, which is challenging, especially for a large subject pool. This study validates the efficacy of a self-supervised learning method in reducing the reliance on labels and evaluates its generalizability.

Materials and methods: We propose a new type of self-supervised loss combining Barlow Twins loss, which attempts to create similar feature representations with reduced …

Big Life-Science: Study Of Omics From Microscopic To Mesoscopic Scales, Jiarui Wu

Bulletin of Chinese Academy of Sciences (Chinese Version)

The human genome project at the turn of the century opened a new era of life science research and formed various omics characterized by holistic high-throughput research. The initial omics research was mainly carried out at the molecular level, such as genomics, transcriptomics, proteomics, etc., showing a new paradigm of data-driven research. With the development of research technologies, the omics research has risen to the mesoscopic level, the representative is the “Human Cell Atlas” project launched in 2017. At present, researchers have been able to carry out omics research at the level of tissues, organs, and even individuals, and resulted …

Brain Science And Brain-Inspired Intelligence In Intelligent Era, Xu Zhang

Bulletin of Chinese Academy of Sciences (Chinese Version)

With intelligence technology as the core technology and intelligent computing power as the productive force, the intelligent era has once again pushed brain science to the forefront of world science and technology. Brain science is the science that studies the nature and rule of cognition and intelligence of human, animal, and machine. A comprehensive analysis of the structure and functional connection rule of the nervous system will eventually draw the functional connectivity map of the brain. In the past decade, neuroscience research has been committed to systematically analyzing the types of neurons and neural structural connections of the nervous system, …

Advances In Data-Driven Life Sciences Research, Haiping Jiang, Chunchun Gao, Wenhao Liu, Yungui Yang, Xin Li

Bulletin of Chinese Academy of Sciences (Chinese Version)

The field of life sciences is rapidly evolving, driven by advancements in experimental techniques and vast biological big data which gradually arise and play an increasingly important role in life science research. First of all, biological big data has diversity and complexity, including genomic data, epigenomic data, proteomic data and other types. These data provide researchers with more comprehensive information and help reveal the laws behind life phenomena. Second, new data-driven developments and applications in life sciences cover many fields such as gene editing, precision medicine, drug development, etc., providing unprecedented possibilities for human health and quality of life. However, …

Technology Innovation Is The Key To Future Space Science Missions, Ji Wu

Bulletin of Chinese Academy of Sciences (Chinese Version)

Space science is one of the important space activities of China together with space technology and space application. Although it is a space program aimed at scientific discovery and breakthrough, with the development of technology and the increasing number of achievements received in the past, space science missions require more and more technological innovation to achieve their goals. This study first reviews the development trend of space science missions since their birth, then analyzes the cultivation process of space science mission proposals with technological innovation and the responsibilities of the chief scientist leading such tasks, and finally analyzes and proposes …

Promoting Ecosystem Based Marine Management Through A Marine Ecological Classification And Zoning System, Wenhai Lu, Xiao Li, Meng Cui

Bulletin of Chinese Academy of Sciences (Chinese Version)

Ecosystem based ocean management is an important means of building marine ecological civilization. The current marine ecological classification and zoning in China comprehensively sorts out the types and natural geographical characteristics of marine ecosystems, divided the Chinese seas and adjacent waters into several levels of ecological spatial units according to different scales, effectively characterizes the geographical distribution features of marine biological communities and their habitats, and provides effective support for ecosystem based marine management. This study analyzed the practical significance of marine ecological classification and zoning. Based on a review of the development of marine ecological classification and zoning, this …

The Long-Term Effects Of Blood Urea Nitrogen Levels On Cardiovascular Disease And All-Cause Mortality In Diabetes: A Prospective Cohort Study, Hongfang Liu, Xiaoqin Xin, Jinghui Gan, Jungao Huang

Faculty, Staff and Student Publications

BACKGROUND: The long-term effects of blood urea nitrogen(BUN) in patients with diabetes remain unknown. Current studies reporting the target BUN level in patients with diabetes are also limited. Hence, this prospective study aimed to explore the relationship of BUN with all-cause and cardiovascular mortalities in patients with diabetes.

METHODS: In total, 10,507 participants with diabetes from the National Health and Nutrition Examination Survey (1999-2018) were enrolled. The causes and numbers of deaths were determined based on the National Death Index mortality data from the date of NHANES interview until follow-up (December 31, 2019). Multivariate Cox proportional hazard regression models were …

Dual-Domain Clustering Of Spatiotemporal Infectious Disease Data, Samuel R. Thornton, Erin C.S. Acquesta, Patrick D. Finley, Mansoor A. Haider

Biology and Medicine Through Mathematics Conference

No abstract provided.

Towards Machine Proficiency With Semantic Underspecification, Zachary S. Gottesman

Dartmouth College Master’s Theses

Human natural language communication frequently relies on extra-linguistic information to fill in gaps in the linguistic signal left by semantic underspecification, or the omission of details that can be inferred from prior knowledge or other modalities. Underspecification is particularly common in conversations between acquaintances, since these interlocutors share context. Underspecification is a key and beneficial feature of natural language that improves efficiency, although it can cause communication to fail if it is not resolved correctly. For language models to communicate effectively and in a human-like fashion, they must learn how to recognize and utilize underspecified language. This thesis argues that …

The Classification Of Internet Memes Through Supervised And Unsupervised Machine Learning Algorithms, William H. Little

Symposium of Student Scholars

Memes, those captivating internet phenomena, effortlessly deliver online entertainment. By leveraging time-series data from Google Trends, we can vividly illustrate and dissect the dynamic trends in meme popularity. Previous studies have discerned four distinct post-peak popularity patterns— "smoothly decaying," "spikey decaying," "leveling off," and "long-term growth"—and elegantly modeled these using ordinary differential equations.

This research introduces a programmatic approach that harnesses both supervised and unsupervised machine learning algorithms. The dataset, now expanded to over 2000 elements, becomes the canvas for exploration. The K-means algorithm identifies clusters, which then serve as labels for the supervised SVC algorithm. The overarching goal is …

Characteristics Based Factor Models - Comparison Of Estimation Procedures, Henri Ohl

McKelvey School of Engineering Graduate Student Theses & Dissertations

Understanding cross-sectional and time series variation of asset returns is fundamental in finance, particularly in asset pricing. This thesis explores the integration of factor theory with machine learning to deepen our comprehension of these dynamics. Characteristics based factor models offer a systematic framework for quantifying an asset's underlying risk-return structure, leveraging time-varying conditional information on model parameters carried by firm-specific characteristics. These models serve as valuable tools for discerning the driving components of an asset's expected excess return. Recent research established a novel methodology for consistent parameter estimation within this framework, only requiring a large cross-section but not a long …

Capturing Higher-Order Relationships Through Information Decomposition, Aobo Lyu

McKelvey School of Engineering Graduate Student Theses & Dissertations

Mutual information between two random variables is a well-studied notion, whose understanding is fairly complete. Mutual information between one random variable and a pair of other random variables, however, is a far more involved notion. Specifically, Shannon's mutual information does not capture fine-grained interactions between those three variables, resulting in limited insights in complex systems. To capture these fine-grained higher-order interactions among variables, Williams and Beer proposed a framework called Partial Information Decomposition (PID) to decompose this mutual information to information atoms, called unique, redundant, and synergistic, and proposed several operational axioms that these atoms must satisfy. This conceptual …

An Examination Of Behavior Of Youtube Commenters, John E. Leonard

Computer Science ETDs

YouTube comments are a unique form of social media, as viewers mainly interact with other viewers through comments sections, and cannot choose to interact with specific people. This lack of control over which comments are presented to them forces users to view spam.

Multiple general patterns of behavior were found in the dataset of YouTube comments. For example, most users posted just after a video’s publication. In addition, users tended to watch videos in the evening over the early morning.

A novel method was found for quantifying the likelihood of coordinated accounts being controlled by one person using time sharing. …

Online Temporal Data Mining And Learning: Pursuing Enhanced Efficiency And Robust Algorithms, Sheng Zhong

Computer Science ETDs

Time series data mining and learning serve as a cornerstone across various domains, including finance, healthcare, and science. Recent advancements in network and sensor technologies have ignited an increasing interest in real-time temporal data mining and learning techniques. Various tasks benefit from these techniques, such as environmental monitoring, event detection, anomaly identification, and forecasting. However, these techniques still face significant challenges in the online environment settings, encompassing aspects like efficiency, accuracy, robustness, and scarcity of labeled data. This dissertation presents four innovative solutions: FilCorr, DCT-MASS, FewSig, and BitLINK to overcome these challenges. We evaluate each method and showcase their practical …

How Financial Beliefs And Behaviors Influence The Financial Health Of Individuals Struggling With Opioid Use Disorder, James R Langabeer, Francine R Vega, Marylou Cardenas-Turanzas, A Sarah Cohen, Karima Lalani, Tiffany Champagne-Langabeer

Faculty, Staff and Student Publications

The surge in opioid use disorder (OUD) over the past decade escalated opioid overdoses to a leading cause of death in the United States. With adverse effects on cognition, risk-taking, and decision-making, OUD may negatively influence financial well-being. This study examined the financial health of individuals diagnosed with OUD by reviewing financial beliefs and financial behaviors. We evaluated quality of life, perceptions of financial condition during active use and recovery, and total debt. We distributed a 20-item survey to 150 individuals in an outpatient treatment program for OUD in a large metropolitan area, yielding a 56% response rate. The results …

Mitochondria Regulate Proliferation In Adult Cardiac Myocytes, Gregory B Waypa, Kimberly A Smith, Paul T Mungai, Vincent J Dudley, Kathryn A Helmin, Benjamin D Singer, Clara Bien Peek, Joseph Bass, Lauren Nelson, Sanjiv J Shah, Gaston Ofman, J Andrew Wasserstrom, William A Muller, Alexander V Misharin, G R Scott Budinger, Hiam Abdala-Valencia, Navdeep S Chandel, Danijela Dokic, Elizabeth Bartom, Shuang Zhang, Yuki Tatekoshi, Amir Mahmoodzadeh, Hossein Ardehali, Edward B Thorp, Paul T Schumacker

Faculty, Staff and Student Publications

Newborn mammalian cardiomyocytes quickly transition from a fetal to an adult phenotype that utilizes mitochondrial oxidative phosphorylation but loses mitotic capacity. We tested whether forced reversal of adult cardiomyocytes back to a fetal glycolytic phenotype would restore proliferative capacity. We deleted Uqcrfs1 (mitochondrial Rieske iron-sulfur protein, RISP) in hearts of adult mice. As RISP protein decreased, heart mitochondrial function declined, and glucose utilization increased. Simultaneously, the hearts underwent hyperplastic remodeling during which cardiomyocyte number doubled without cellular hypertrophy. Cellular energy supply was preserved, AMPK activation was absent, and mTOR activation was evident. In ischemic hearts with RISP deletion, new cardiomyocytes …

High-Density Genetic Map Construction And Qtl Mapping Of A Zigzag-Shaped Stem Trait In Tea Plant (Camellia Sinensis), Dingding Liu, Yuanyuan Ye, Rongjin Tang, Yang Gong, Si Chen, Chenyu Zhang, Piao Mei, Jiedan Chen, Liang Chen, Chunlei Ma

Faculty, Staff and Student Publications

The highly unique zigzag-shaped stem phenotype in tea plants boasts significant ornamental value and is exceptionally rare. To investigate the genetic mechanism behind this trait, we developed BC1 artificial hybrid populations. Our genetic analysis revealed the zigzag-shaped trait as a qualitative trait. Utilizing whole-genome resequencing, we constructed a high-density genetic map from the BC1 population, incorporating 5,250 SNP markers across 15 linkage groups, covering 3,328.51 cM with an average marker interval distance of 0.68 cM. A quantitative trait locus (QTL) for the zigzag-shaped trait was identified on chromosome 4, within a 61.2 to 97.2 Mb range, accounting for a phenotypic …

A Nlp Approach To Automating The Generation Of Surveys For Market Research, Anav Chug

Honors College Theses

Market Research is vital but includes activities that are often laborious and time consuming. Survey questionnaires are one possible output of the process and market researchers spend a lot of time manually developing questions for focus groups. The proposed research aims to develop a software prototype that utilizes Natural Language Processing (NLP) to automate the process of generating survey questions for market research. The software uses a pre-trained Open AI language model to generate multiple choice survey questions based on a given product prompt, send it to a targeted email list, and also provides a real-time analysis of the responses …

Evaluating Neuroimaging Modalities In The A/T/N Framework: Single And Combined Fdg-Pet And T1-Weighted Mri For Alzheimer’S Diagnosis, Peiwang Liu

McKelvey School of Engineering Graduate Student Theses & Dissertations

With the escalating prevalence of dementia, particularly Alzheimer's Disease (AD), the need for early and precise diagnostic techniques is rising. This study delves into the comparative efficacy of Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) and T1-weighted Magnetic Resonance Imaging (MRI) in diagnosing AD, where the integration of multimodal models is becoming a trend. Leveraging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we employed linear Support Vector Machines (SVM) to assess the diagnostic potential of these modalities, both individually and in combination, within the AD continuum. Our analysis, under the A/T/N framework's 'N' category, reveals that FDG-PET consistently outperforms T1w-MRI across …

Adapting And Evaluating A Theory-Driven, Non-Pharmacological Intervention To Self-Manage Pain, Jennifer Kawi, Chao Hsing Yeh, Lauren Grant, Johannes Thrul, Hulin Wu, Paul J Christo, Lorraine S Evangelista

Faculty, Staff and Student Publications

BACKGROUND: The existing literature has limited detail on theory-driven interventions, particularly in pain studies. We adapted Bandura's self-efficacy framework toward a theory-driven, non-pharmacological intervention using auricular point acupressure (APA) and evaluated participants' perceptions of this intervention on their pain self-management. APA is a non-invasive modality based on auricular acupuncture principles.

METHODS: We mapped our study intervention components according to Bandura's key sources of self-efficacy (performance accomplishments, vicarious experience, verbal persuasion, and emotional arousal) to facilitate the self-management of pain. Through a qualitative study design, we conducted virtual interviews at one and three months after a 4-week APA intervention among 23 …

Developing And Validating A Nomogram For Early Predicting The Need For Intestinal Resection In Pediatric Intussusception, Yuan-Yang Yu, Jia-Jie Zhang, Ya-Ting Xu, Zheng-Xiu Lin, Shi-Kun Guo, Zhong-Rong Li, Hui-Ya Huang, Xiao-Zhong Huang

Faculty, Staff and Student Publications

PURPOSE: Develop and validate a nomogram for predicting intestinal resection in pediatric intussusception suspecting intestinal necrosis.

PATIENTS & METHODS: Children with intussusception were retrospectively enrolled after a failed air-enema reduction in the outpatient setting and divided into two groups: the intestinal resection group and the non-intestinal resection group. The enrolled cases were randomly selected for training and validation sets with a split ratio of 3:1. A nomogram for predicting the risk of intestinal resection was visualized using logistic regression analysis with calibration curve, C-index, and decision curve analysis to evaluate the model.

RESULTS: A total of 547 cases were included …

Toward The Integration Of Behavioral Sensing And Artificial Intelligence, Subigya K. Nepal

Dartmouth College Ph.D Dissertations

The integration of behavioral sensing and Artificial Intelligence (AI) has increasingly proven invaluable across various domains, offering profound insights into human behavior, enhancing mental health monitoring, and optimizing workplace productivity. This thesis presents five pivotal studies that employ smartphone, wearable, and laptop-based sensing to explore and push the boundaries of what these technologies can achieve in real-world settings. This body of work explores the innovative and practical applications of AI and behavioral sensing to capture and analyze data for diverse purposes. The first part of the thesis comprises longitudinal studies on behavioral sensing, providing a detailed, long-term view of how …

Surmounting Challenges In Aggregating Results From Static Analysis Tools, Dr. Ann Marie Reinhold, Brittany Boles, A. Redempta Manzi Muneza, Thomas Mcelroy, Dr. Clemente Izurieta

Military Cyber Affairs

Aggregation poses a significant challenge for software practitioners because it requires a comprehensive and nuanced understanding of raw data from diverse sources. Suites of static-analysis tools (SATs) are commonly used to assess organizational security but simultaneously introduce significant challenges. Challenges include unique results, scales, configuration environments for each SAT execution, and incompatible formats between SAT outputs. Here, we document our experiences addressing these issues. We highlight the problem of relying on a single vendor's SAT version and offer a solution for aggregating findings across multiple SATs, aiming to enhance software security practices and deter threats early with robust defensive operations.

Artificial Intelligence And Music: Analysis Of Music Generation Techniques Via Deep Learning And The Implications Of Ai In The Music Industry, David Bryce

Honors Projects in Data Science

The use of artificial intelligence (AI) is quickly gaining relevancy in creative fields, and its emergence into the music industry comes with many unique implications. This paper examines the technical processes of creating music with AI and machine learning, the relationship between music and emotion, and finally the implications and ethical considerations for AI generated music in creative industries. As part of this project, a generative deep learning model (Music Variational Autoencoder) is explored and applied to generate music using a pre-trained training set of piano rolls. The AI reconstructions are based on self-made 4 measure electronic instrumental tracks. 46 …

Data Analysis Project For Preferred Credit Inc., Emily Smith, Greta Nesbit, Jack Simonet, Ignacio Sanchez-Romero

Celebrating Scholarship and Creativity Day (2018-)

This project focuses on transforming real data within PCI's operations into valuable insights through an approach of coding, data cleaning, and visualization. By leveraging advanced techniques, the project aims to uncover key trends and create visually compelling representations to aid decision-making within the company. The outcome will allow PCI stakeholders the ability to extract valuable insights, optimize processes, and drive initiatives for growth and competitive advantage in the finance industry.

Identifying High-Value Tactical Livestock Decisions On A Mixed Enterprise Farm In A Variable Environment, Michael Young, John Young, Ross S. Kingwell, Philip E. Vercoe

Animal production and livestock research articles

Context

Australia is renowned for its climate variation, featuring years with drought and years with floods, which result in significant production and profit variability. Accordingly, to maximise profitability, dryland farming systems need to be dynamically managed in response to unfolding weather conditions.

Aims

The aim of this study is to identify and quantify optimal tactical livestock management for different weather-years.

Methods

This study employed a whole-farm optimisation model to analyse a representative mixed enterprise farm located in the Great Southern region of Western Australia. Using this model, we investigated the economic significance of five key livestock management tactics. These included …

A Spatial Decision Support System For Rent Estimation Of Retail Spaces In Manhattan Using Geographically Weighted Regression And Spatial Regression, Andie M. Migden Miller

Theses and Dissertations

This report outlines an automated, three-phase Spatial Decision Support System that creates models to estimate rent of retail spaces across Manhattan. First, enrich data with predictors. Second, optimize spatially aware neighborhood-level models by combining GWR, spatial regression, and non-spatial regression. Finally, visualize results in an Esri-based WebApp.

Rosarugosides A And D From Osa Rugosa Flower Buds: Their Potential Anti-Skin-Aging Effects Intnf-Α-Induced Human Dermal Fibroblasts, Kang Sub Kim, So-Ri Son, Yea Jung Choi, Yejin Kim, Si-Young Ahn, Dae Sik Jang, Sullim Lee

Faculty, Staff and Student Publications

This present study investigated the anti-skin-aging properties of Rosa rugosa. Initially, phenolic compounds were isolated from a hot water extract of Rosa rugosa's flower buds. Through repeated chromatography (column chromatography, MPLC, and prep HPLC), we identified nine phenolic compounds (1-9), including a previously undescribed depside, rosarugoside D (1). The chemical structure of 1 was elucidated via NMR, HR-MS, UV, and hydrolysis. Next, in order to identify bioactive compounds that are effective against TNF-α-induced NHDF cells, we measured intracellular ROS production in samples treated with each of the isolated compounds (1- …

Understanding The Public Reaction To Major United States Environmental Policies Through Twitter, Ryan Giammarco

Honors Projects in Data Science

An increased focus on access to general data as well as a continued lack of usable environmental data have resulted in an odd phenomenon where the public does not have the opportunity to understand their environment on a deep level. The goal of this research is to understand, as a result, how people both talk and feel about certain environmental changes, particularly those in the realm of politics. Through word clouds and sentiment analysis performed with historical Twitter data collected between 2010 and 2022, we can identify the general trends in both conversation and feeling as they relate to a …

A Novel Correction For The Multivariate Ljung-Box Test, Minhao Huang

Computational and Data Sciences (PhD) Dissertations

This research introduces an analytical improvement to the Multivariate Ljung-Box test that addresses significant deviations of the original test from the nominal Type I error rates under almost all scenarios. Prior attempts to mitigate this issue have been directed at modification of the test statistics or correction of the test distribution to achieve precise results in finite samples. In previous studies, focused on designing corrections to the univariate Ljung-Box, a method that specifically adjusts the test rejection region has been the most successful of attaining the best Type I error rates. We adopt the same approach for the more complex, …