Digital Commons Network^™

Evaluation And Implementation Of Machine Learning Models To Predict Customer Churn In The Telecommunications Sector., Stephen Hasson

ICT

This research addresses customer churn in the Telecom industry by utilizing Machine Learning (ML) models to predict customers at risk of leaving and provide data-driven retention strategies. The study highlights the effectiveness of ML, particularly in churn prediction, while noting the need for further exploration into the ethical implications of AI, such as potential biases towards vulnerable groups. Using the CRISP-DM framework, the study develops and compares three Supervised Learning (SL) models: Random Forests (RF), LightGBM (LGBM), and XGBoost (XGB), incorporating class resampling techniques to manage data imbalance.

The findings identified five key features as the most significant predictors of …

Data Analysis Of Twitter’S Nasdaq100 Sentiments And Topics As Indicators For News Articles Retrieval: Fine-Tuning Roberta And Rag., Kagan Timur

ICT

This study investigates the combination of sentiment analysis using the VADER lexicon and semantic analysis through Latent Dirichlet Allocation (LDA) to identify real-life events, focusing on Twitter datasets. The research shows that while sentiment analysis alone may be insufficient, combining it with semantic analysis improves the process, particularly for identifying relevant news articles and understanding brand perception on social media. The study also fine-tunes the RoBERTa model for question-answering tasks, yielding significant improvements in the SQuAD evaluation metric. The exact match (EM) score rose dramatically from 2.06% to 62%, and the F1 score improved from 9.41% to 65%. A retrieval …

Responsible Natural Language Processing To Aid Employee Performance Reviews., Grace Rubinger

ICT

This research explores the use of Natural Language Processing (NLP) techniques in assessing evaluators' written appraisals during Employee Performance Reviews (EPRs), aiming to address biases inherent in traditional methods. By integrating Responsible Artificial Intelligence (AI) and foundational Large Language Models (LLMs), the study seeks to enhance the objectivity, fairness, and ethical transparency of performance evaluations. It highlights the potential of AI systems to ensure comprehensive assessments while promoting trust, ethical standards, and employee retention.

The research also aims to advance the field of AI Ethics in practical Human Resources Management (HRM) applications, particularly through NLP-driven tools. These tools are designed …

Designing Designer Bankruptcy, Michael A. Francus

Journal Articles

Today's mass torts are headed to bankruptcy. Be it Purdue Pharma 's opioids, United States of America (USA) Gymnastics' sexual abuse, Pacific Gas and Electric Company's (PG&E) wildfires, or Johnson & Johnson 's talc, masstort defendants have determined that bankruptcy-not class actions, multi district litigation, or one-off state suits-is the way to manage their mass-tort liability. But today's mass-tort bankruptcy is not the mass-tort bankruptcy of yesteryear, when the whole business filed for bankruptcy. Instead, these modern mass-tort bankruptcies are designer bankruptcies, where the defendant uses its corporate structure to choose which assets and which liabilities enter bankruptcy. To take …

Educational Adequacy: Harmonizing The Right To Education, Parents' Rights, And Educational Freedoms Under The International Covenant On Economic, Social And Cultural Rights, Jorge Barrera-Rojas

Journal Articles

This article explores the concept of educational adequacy, balancing the right to education for children and educational freedoms. Specifically, the research paper describes why States parties must meet Article 13(1) goals under the International Covenant of Economic, Social and Cultural Rights (ICESCR) but, at the same time, ensure parents’ rights and the liberty to establish and direct private educational institutions as minimum core and immediate-effect obligations. Accordingly, there is no prioritization or subordination of educational freedoms favoring the right to education, or vice versa, which constitutes a false dichotomy since the right to education and educational liberties are interrelated rights …

A Scoping Review On Mobile Health Technology For Assessment And Intervention Of Upper Limb Motor Function In Children With Motor Impairments, Md Raihan Mia, Sheikh Iqbal Ahamed, Alissa V. Fial, Samuel Nemanich

Computer Science Faculty Research and Publications

Upper limb (UL) motor dysfunctions impact residual movement in hands/shoulders and limit participation in play, sports, and leisure activities. Clinical and laboratory assessments of UL movement can be time-intensive, subjective, and/or require specialized equipment and may not optimally capture a child's motor abilities. The restrictions to in-person research experienced during the COVID-19 pandemic have inspired investigators to design inclusive at-home studies with child participants and their families. Relying on the ubiquity of mobile devices, mobile health (mHealth) applications offer solutions for various clinical and research problems. This scoping review article aimed to aggregate and synthesize existing research that used health …

Legal Matters In Web 3: A Desk Reference, Anup Malani, M. Henderson

Books

No abstract provided.

Hand Tremor Sensing And Characterisation Device, Jackie Le , '24

Senior Theses, Projects, and Awards

Parkinson’s Disease and Essential Tremor are two of the most common tremor-related conditions affecting millions of people globally. Various types of tremors, specifically in the hand, arise as symptoms characteristics to these tremor-related conditions. However, the lack of standardization and certainty between clinical tremor assessments motivates the future of medical devices to provide relevant medical diagnostics. Current literature shows promise for the ability of such devices to revolutionize home healthcare and integrate well into currently existing clinical procedures. This engineering design project aims to design a wearable medical device to detect and computationally characterise various types of tremors in Parkinson’s …

Giddy Guidance: Low-Cost 3d Aircraft With Integrated Autopilot And Stabilization, Mark Lohatepanont , '24

Senior Theses, Projects, and Awards

No abstract provided.

Sticky Charters? The Surprisingly Tepid Embrace Of Officer-Protecting Waivers In Delaware, Jens Frankenreiter, Eric L. Talley

Scholarship@WashULaw

This article investigates the reaction to a much-heralded 2022 legal reform in Delaware that permitted a corporation’s charter to exculpate its officers from monetary exposure for breaching their fiduciary duty of care. To isolate reactions to this statutory reform, we make extensive use of generative AI tools to identify and interpret charter amendments that introduce officer-facing waivers. We find a surprisingly tepid rate of uptake among Delaware corporations through the end of the first post-reform year, notwithstanding widespread predictions that corporate entities would quickly storm the exculpation exits once permitted to do so.

Our study makes two contributions to the …

Do Patents Drive Investment In Software?, James Hicks

Scholarship@WashULaw

In the wake of a quartet of Supreme Court decisions which disrupted decades of settled law, the doctrine of patentable subject matter is in turmoil. Scholars, commentators, and jurists continue to disagree sharply over which kinds of invention should be patentable. In this debate, no technology has been more controversial than software. Advocates of software patents contend that denying protection would stymie innovation in a vital industry; skeptics argue that patents are a poor fit for software, and that the social costs of patents outweigh any plausible benefits. At the core of this disagreement is a basic problem: the debate …

Measuring The Impacts Of Experiential Legal Education, Robert R. Kuehn, Peter A. Joy

Scholarship@WashULaw

Experiential legal education has become an essential component of the law school curriculum, emphasizing "learning by doing" through practical experiences in law clinics, externships, and simulation courses. This pedagogical approach offers law students the critical skills and professional values required for effective and ethical practice. Despite its recognized importance and parallels with other professional disciplines, legal education still requires minimal experiential education compared to other professions. This reluctance likely stems from lingering skepticism by some legal educators about its value, even though many stakeholders, including other educators, students, recent graduates, and other legal professionals, acknowledge its significance.

This Article is …

Arrow's Theorem And Legislative Intent, Nevin Johnson

Campbell Law Review

A number of prominent legal and political theorists have argued, on the basis of Kenneth Arrow's "impossibility" theorem, that the concept of legislative intent is irredeemably problematic. These Arrow-inspired intent skeptics most significantly argue that the presence ofintransitive legislative preferences (cycling) means there is no such thing as the "will of the majority" and hence no such thing as a coherent legislative intent. Legislative outcomes, not being attributable to the will of the majority, are instead the result of things like agenda control. Other theorists defend legislative intent against these challenges, tending to focus on contingent legislative characteristics that make …

Lawyering In The Age Of Artificial Intelligence, Jonathan H. Choi, Monahan Amy, Daniel Schwarcz

Scholarship@WashULaw

We conducted the first randomized controlled trial to study the effect of AI assistance on human legal analysis. We randomly assigned law school students to complete realistic legal tasks either with or without the assistance of GPT-4, tracking how long the students took on each task and blind-grading the results. We found that access to GPT-4 only slightly and inconsistently improved the quality of participants’ legal analysis but induced large and consistent increases in speed. AI assistance improved the quality of output unevenly—where it was useful at all, the lowest-skilled participants saw the largest improvements. On the other hand, AI …

Wavelet-Based Harmonization Of Local And Global Model Shifts In Federated Learning For Histopathological Images, W. Farzana, A. Temtam, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Federated Learning (FL) is a promising machine learning approach for development of data-driven global model using collaborative local models across multiple local institutions. However, the heterogeneity of medical imaging data is one of the challenges within FL. This heterogeneity is caused by the variation in imaging scanner protocols across institutions, which may result in weight shift among local models leading to deterioration in predictive accuracy of global model. The prevailing approaches involve applying different FL averaging techniques to enhance the performance of the global model, ignoring the distinct imaging features of the local domain. In this work, we address both …

Advancing Chronic Kidney Disease Prediction Through Machine Learning And Deep Learning With Feature Analysis, Shiddarth Dey Tusar, S. M. Ahad Ali Chowdhury, Md. Jalal Uddin Chowdhury, Rana M. Pir, H. M. Nur A. Alam, Muhammad Rezaur Rahman, Md. Nural Absar Siddiky, Muhammad Enayetur Rahman

Electrical & Computer Engineering Faculty Publications

Chronic Kidney Diesease (CKD) is a significant health issue, ranking as the fourth leading cause of mortality worldwide. The traditional diagnosis and treatment process, reliant on medical experts, is time-consuming. Therefore, thereis an urgent need for more efficient diagnostic methods to improve patient outcomes and reduce mortality rates. In this study, we employ Machine Learning (ML) and Deep Learning (DL) techniques to predict CKD based on important features. Feature analysis was performed using a correlation matrix and the LASSO algo-rithm to identify the most relevant features for model training. We evaluated several ML and DL classifiers, including Logistic Regression (LR), …

Interannual Growth-Climate Relationships Of Western Larch After Wildfire In The Northwest, Junior Burks

Undergraduate Theses, Professional Papers, and Capstone Artifacts

Montane and mixed-conifer forests in the northwestern United States are burning at rates greater than any time in recent decades, due to the combined impacts of global warming and historical and contemporary land use and land management. Western larch (Larix occidentalis) is a tree of high regional significance, exhibiting a variety of traits that make it resistant and resilient to fire. Because seedlings are more sensitive to environmental stressors than adults, the impacts of climate change are expected to be detectable first in juvenile trees. Recent research shows that the natural regeneration of western larch after wildfires has …

Understanding The Effects Of Integrated Movement Interventions On Engagement Outcomes In The High School Ela Classroom, Alexis M. Wigdorski

Undergraduate Theses, Professional Papers, and Capstone Artifacts

No abstract provided.

Supporting Dataset For The Influence Of Tile-Water On Groundwater Nitrate Concentrations Within A Saturated Riparian Buffer Zone, Aminat Tosin Abdulsalam, Eric Wade Peterson

Faculty Publications - Geography, Geology, and the Environment

In the U.S. Midwest, where fertile soils with high water retention are prevalent, the installation of tile drainage networks have become a common practice to drain excess soil water, which enhances plant growth and increases crop productivity. However, tile drainage networks coupled with the use of inorganic fertilizers have significant implications on water quality, contributing to eutrophication, leading to harmful algal blooms, and resulting in hypoxic conditions in surface water bodies. To mitigate excess nutrient exports to surface water bodies, edge-of-field practices have been introduced. One such practice is the saturated riparian buffer (SRB), which utilizes a diversion system to …

Petrologic Relationship Between Lamprophyres, Carbonatites, And Heavy Rare-Earth Element Enriched Breccias At Hicks Dome, Jarek Trela, Jared T. Freiburg, Esteban Gazel, Laurence Nuelle, Anton H. Maria, David H. Malone, John M. Molinarolo

Faculty Publications - Geography, Geology, and the Environment

New petrological, geochemical, and P–T modelling results from igneous samples clarify how carbonatite-lamprophyre magmatism, fluorite and rare earth element (REE) enrichment are petrogenetically related in southern Illinois. P–T modelling reveals that igneous rocks derive from a deep mantle carbonated source, that is consistent with trace element signatures for a fluorine-rich transition zone origin. Major element systematics suggests liquid-immiscibility with lamprophyric melts as the origin for Ca-carbonatites. Heavy REE (HREE) enrichments in Hicks Dome breccias likely formed through preferential partitioning and transport of HREE by brine-melts, exsolved from a deep carbonatite body. Brine-melts redistributed HREEs throughout the …

Transport And Fate Of Nitrate In A Saturated Buffer Zone As Assessed With A Chloride Tracer Test, Alhassan Sahad, Eric W. Peterson

Faculty Publications - Geography, Geology, and the Environment

The Upper Mississippi Basin, which includes Illinois, has highly fertile soils and experiences intensive agricultural practices. Although fertile, the soils do not drain well, resulting in the installation of tile-drainage systems. The practices of tile systems coupled with the application of nitrogen-rich fertilizers have led to the excessive export of nitrate from the agricultural fields into surface waters, contributing to eutrophication and the development of hypoxic zones in aquatic environments. Saturated riparian buffer zones (SRBs) have been proposed as a means to reduce the amount of nitrate discharged from tile-drained waters into streams. Previous works show a reduction in the …

4. Developing Media And Information Literacy Through Dialogues About Ai, Rosa Thornley, Dory Rosenberg

Teaching and Generative AI: Pedagogical Possibilities and Productive Tensions

Inviting students to dialogue about Artificial Intelligence (Al) can help to develop media and information literacy. Instead of establishing restrictive policies, we present a method for instructor-facilitated dialogues to teach students to analyze, evaluate, and interact with generative language models. This recursive inquiry process causes students to critically think about the spectrum of AI capabilities and limitations. Practicing this inquiry habit over time directs students towards intuitively questioning the Al which leads them to govern their own choices when they become rhetorically aware of emerging technologies and how it will affect their own research and writing. For instructors in higher …

1. Navigating The New Frontier Of Generative Ai In Peer Review And Academic Writing, Chris Mayer

Teaching and Generative AI: Pedagogical Possibilities and Productive Tensions

This chapter provides an overview of the current landscape and implications of Generative Al (GenAl) in higher education, particularly focusing on its role in academic writing and peer review. The emergence of GenAl tools such as ChatGPT is a transformative development in education, with widespread adoption at unprecedented speed. Large Language Models such as ChatGPT offer great potential for enhancing education and academic writing but also raise serious ethical concerns and tensions including access and usability, the perpetuation of Standard Academic English, and issues of linguistic justice. There is also the need for new approaches and pedagogies for how to …

Investigating Teacher And Student Perceptions Of The Impact Of Chatgpt In The Classroom, Esther Abla Dorgbefu

Graduate Research Theses & Dissertations

This study was an initial attempt to investigate faculty and student perceptions of the impact of ChatGPT in the classroom. The primary purpose of this study was to conduct a cost-benefit analysis of the opportunities and challenges of ChatGPT in education. The following research questions were investigated to achieve this goal: (a) What fears do faculty have about using ChatGPT in education? (b) What fears do students have about the use of ChatGPT in education? (c) What are the possible benefits and consequences of using ChatGPT from students’ perspectives? (d) What are the possible benefits and consequences of using ChatGPT …

Design And Performance Of Superconducting Switches For Nanowire Detectors In Magnetic Fields, Timothy James Draher

Graduate Research Theses & Dissertations

Superconducting nanowire devices fit a broad spectrum of applications, including particle detection and quantum computing, and their expanding use across various fields highlights their role in the hybridization of superconducting and conventional semiconductor electronics. Despite their potential, the low signal output of these devices raises challenges in scalability and integration, particularly in applications for nuclear and high-energy physics, where resilience in magnetic fields is becoming a critical optimization factor. The superconducting nanowire cryotron (nTron) addresses these issues by providing operational gain and logic switching in superconducting nanowire circuits, demonstrating adaptability to multiple materials. This dissertation focuses on modifying the conventional …

Assessing Fixed-Node Diffusion Monte Carlo For Radical Polymerization Reaction Energetics, Timothy Brian Huber

Graduate Research Theses & Dissertations

The art of quantum chemistry is grounded to the discovery of a time efficient computational method that can capture the essential physics. Historically, the Hartree-Fock method, where an electron moves in the mean field of the other electrons, has provided the orbitals used to construct a single-reference Slater determinant and thus formed the basis for molecular orbital calculations. Kohn-Sham density functionals have become overwhelmingly popular among the chemistry community due to their low computational cost. However, their prediction of thermodynamic properties important in free radical polymerization has shown difficulty due to an artificial delocalization of electron density and spin contamination …

Medium Range Prediction Of U.S. Severe Convective Storms, Robert Fritzen

Graduate Research Theses & Dissertations

Severe convective storms (SCSs) are responsible for billions of dollars of losses in the United States each year through hazards such as large hail, damaging convective wind gusts, and tornadoes. While techniques for forecasting these SCSs have improved over the years, a majority of these improvements focus on short term forecasting and nowcasting techniques. Little work has been done to analyze the recent advances in numerical weather prediction techniques, and to leverage these advances to the prediction of SCSs at the medium range (defined herein as lead-day 4--8). The primary objectives of this dissertation research are to: 1) explore the …

Uniform Convergence Of Deep Neural Networks With Lipschitz Continuous Activation Functions And Variable Widths, Yuesheng Xu, Haizhang Zhang

Mathematics & Statistics Faculty Publications

We consider deep neural networks (DNNs) with a Lipschitz continuous activation function and with weight matrices of variable widths. We establish a uniform convergence analysis framework in which sufficient conditions on weight matrices and bias vectors together with the Lipschitz constant are provided to ensure uniform convergence of DNNs to a meaningful function as the number of their layers tends to infinity. In the framework, special results on uniform convergence of DNNs with a fixed width, bounded widths and unbounded widths are presented. In particular, as convolutional neural networks are special DNNs with weight matrices of increasing widths, we put …

Weed Seed Wizard Scenario - Dormancy Shift In Barley Grass In Balaklava, South Australia, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity research reports

The Weed Seed Wizard is a national collaborative project that uses paddock management information to predict weed emergence and crop losses now and in the future.

The Weed Seed Wizard is a computer simulation tool that:

• applies to all Australian grain growing areas

• helps growers understand and manage weed seedbanks on their farms

• uses farm management records to simulate how different crop rotations, weed control techniques, irrigation, grazing and harvest management tactics can affect weed numbers, the weed seedbank and yields

• uses farm-specific management and site-specific weather

• is multi-species

See www.dpird.wa.gov.au for further information on Weed Seed Wizard.

This South …

Weed Seed Wizard Case Study - Grower From Western Australia’S Central Wheatbelt, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity research reports

The Weed Seed Wizard is a national collaborative project that uses paddock management information to predict weed emergence and crop losses now and in the future.

The Weed Seed Wizard is a computer simulation tool that:

• applies to all Australian grain growing areas

• helps growers understand and manage weed seedbanks on their farms

• uses farm management records to simulate how different crop rotations, weed control techniques, irrigation, grazing and harvest management tactics can affect weed numbers, the weed seedbank and yields

• uses farm-specific management and site-specific weather

• is multi-species

See www.dpird.wa.gov.au for further information on Weed Seed Wizard.

This case …