Digital Commons Network^™

The Importance Of Text Representation For Neural Networks Through Natural Language Processing Techniques, William Parsley

Data Science Undergraduate Honors Theses

Text representation is a fundamental aspect of natural language processing (NLP) when it comes to the performance of neural networks. Free-form text fields are being utilized in more and more industries. Anything from a description of an item on a web store to tracking service events to military-grade aircraft is being collected in free-form text. The goal of the thesis is to highlight best practices and discuss trends in data to prepare text for a neural network. It will demonstrate various techniques for representing free-form text in the context of neural networks, focusing on data preparation decisions, embedding techniques, and …

The Effects Of Using Machine Translators On The Performance Of Second Language Learners, Kasey Myer

University Honors College

With the rise of technology has also come the development of various online language translators and artificial intelligence that are often utilized by individuals learning a second language. However, there is a wide range of quality between the different machine translation tools, and many people tend to be under the impression that it is inferior to the quality of interpretations provided by human translators. This paper considers the positives and negatives of machine translation as a tool for second language learning. Variations between the input and output languages on a grammatical and cultural level are analyzed. Machine translation is compared …

A Study Of Cybersecurity Landscape In The United States: Trend, Regional Variations, And Socioeconomic Factors, Trang Thi Thu Horn

All-Inclusive List of Electronic Theses and Dissertations

The Internet has become an essential part of our daily lives. Cyberspace has emerged significantly with an enormous number of users, creating a lucrative hunting field for cybercriminals. The exponential growth of internet users and online activities, along with the increased sophistication of cybercrimes, is raising significant global concerns for individuals, organizations, and governments. This research aims to explore the cybersecurity landscape in the United States, investigate regional variations, and the potential impact of the COVID-19 pandemic on the number of cybercrimes. The study utilizes a mixed research method approach, including historical analysis and a Delphi study. Historical analysis studied …

Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu

Theses and Dissertations

This research introduces ASR-net(Ancient Script Recognition), a groundbreaking system that automatically digitizes ancient Indus seals by converting them into coded text, similar to Optical Character Recognition for modern languages. ASR-net, with an 95% success rate in identifying individual symbols, aims to address the crucial need for automated techniques in deciphering the enigmatic Indus script. Initially Yolov3 is utilized to create the bounding boxes around each graphemes present in the Indus Valley Seal. In addition to that we created M-net(Mahadevan) model to encode the graphemes. Beyond digitization, the paper proposes a new research challenge called the Motif Identification Problem (MIP) related …

The Future Of Brain Tumor Diagnosis: Cnn And Transfer Learning Innovations, Shengyuan Wang

Mathematics, Statistics, and Computer Science Honors Projects

For the purpose of improving patient survival rates and facilitating efficient treatment planning, brain tumors need to be identified early and accurately classified. This research investigates the application of transfer learning and Convolutional Neural Networks (CNN) to create an automated, high-precision brain tumor segmentation and classification framework. Utilizing large-scale datasets, which comprise MRI images from open-accessible archives, the model exhibits the effectiveness of the method in various kinds of tumors and imaging scenarios. Our approach utilizes transfer learning techniques along with CNN architectures strengths to tackle the intrinsic difficulties of brain tumor diagnosis, namely significant tumor appearance variability and difficult …

The Perspectives Of Using Desmos For Students’ Conceptual Understanding And Procedural Fluency To Solve Linear Equations, Larmel Dimatulac Madrilejos

Theses and Dissertations

The study examines the perspectives of using the Desmos calculator of Algebra I students' conceptual understanding and procedural fluency to write, graph, and solve linear equations in Algebra I STAAR. While the students have continuously used technology for mathematics assessment, emergent bilingual students in South Texas still need help passing high-stakes testing. The framework of the study is grounded in the theory of mathematical education (knowledge of mathematics educators to teach), the theory of mathematical learning (understanding how students learn mathematics), and social constructivism. The study seeks ways to teach all students, mainly the minority, to learn …

Enabling And Optimizing Multi-Modal Sense-Making For Human-Ai Interaction Tasks, Dulanga Kaveesha Weerakoon Weerakoon Mudiyanselage

Dissertations and Theses Collection (Open Access)

The rapid pace of adoption of mixed-reality in tandem with advances in NLP and computer vision have opened up unprecedented opportunities for more naturalistic interaction interfaces which underpin Human-AI collaborative applications such as spatial computing and interactive conversational agents. One notable example is the emergence of interactive virtual assistants, which facilitate more natural communication of instructions and queries through modalities like voice and text. This trend is driving the development of innovative ubiquitous, mixed-reality computing applications. Such interactive, natural communication is also critical to support advances in human-robot interactive co-working, across a variety of industrial, commercial and home environments. Conventional …

Towards Explainable Harmful Meme Detection Through Multimodal Debate Between Large Language Models, Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao Yang

Research Collection School Of Computing and Information Systems

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models …

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important …

Exploring Graph Neural Networks In Reinforcement Learning: A Comparative Study On Architectures For Locomotion Tasks, Gaukhar Nurbek

Theses and Dissertations

Deep Reinforcement learning (DRL) has gained importance in optimizing control policies, while Graph Neural Networks (GNNs) offer a robust approach for modeling complex relationships within systems represented as graphs. This thesis investigates the integration of DRL and GNNs to optimize control policies for robotic tasks, with a focus on locomotion. It compares static and dynamic GNN architectures for control policy predictions, revealing their strengths and limitations in adapting to locomotion predictions. The study assesses the impact of model structure complexity on GNNs' predictive capabilities, showcasing how intricate model structure can maximize GNNs' potential in capturing spatial and relational dependencies when …

Dynamic Storytelling Algorithms Using Contextual Aspects Of A Large Language Model, Alireza Pasha Nouri

Open Access Theses & Dissertations

Storytelling is a set of algorithms used to create narratives by connecting documents in a sequencethat accurately reflects the evolution of events and entities within a particular topic or theme. Early storytelling algorithms face challenges in encoding the progression and interconnections of information between consecutive texts, given that the conventional approaches rely primarily on connecting document pairs based on content overlap. They often neglect critical linguistic features, such as word contexts, semantics, the roles words play across different documents, and attention to the historical contexts of the underlying documents. Many existing storytelling models frequently produce story chains that, while connected …

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 …

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue …

Intriguing Properties Of Data Attribution On Diffusion Models, Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin

Research Collection School Of Computing and Information Systems

Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training samples, ensuring that data contributors are fairly compensated or credited. Several theoretically motivated methods have been proposed to implement data attribution, in an effort to improve the trade-off between computational scalability and effectiveness. In this work, we conduct extensive experiments and ablation studies on attributing diffusion models, specifically focusing on DDPMs trained on CIFAR-10 and CelebA, as well as a Stable Diffusion model LoRA-finetuned on ArtBench. …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

On The Feasibility Of Simple Transformer For Dynamic Graph Modeling, Yuxia Wu, Yuan Fang, Lizi Liao

Research Collection School Of Computing and Information Systems

Dynamic graph modeling is crucial for understanding complex structures in web graphs, spanning applications in social networks, recommender systems, and more. Most existing methods primarily emphasize structural dependencies and their temporal changes. However, these approaches often overlook detailed temporal aspects or struggle with long-term dependencies. Furthermore, many solutions overly complicate the process by emphasizing intricate module designs to capture dynamic evolutions. In this work, we harness the strength of the Transformer’s self-attention mechanism, known for adeptly handling long-range dependencies in sequence modeling. Our approach offers a simple Transformer model, called SimpleDyG, tailored for dynamic graph modeling without complex modifications. We …

Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges, Ce Zhang, Menglin Yang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Text documents are usually connected in a graph structure, resulting in an important class of data named text-attributed graph, e.g., paper citation graph and Web page hyperlink graph. On the one hand, Graph Neural Networks (GNNs) consider text in each document as general vertex attribute and do not specifically deal with text data. On the other hand, Pre-trained Language Models (PLMs) and Topic Models (TMs) learn effective document embeddings. However, most models focus on text content in each single document only, ignoring link adjacency across documents. The above two challenges motivate the development of text-attributed graph representation learning, combining GNNs …

Automatic Grading Of Short Answers Using Large Language Models In Software Engineering Courses, Nguyen Binh Duong Ta, Yi Meng Chai

Research Collection School Of Computing and Information Systems

Short-answer based questions have been used widely due to their effectiveness in assessing whether the desired learning outcomes have been attained by students. However, due to their open-ended nature, many different answers could be considered entirely or partially correct for the same question. In the context of computer science and software engineering courses where the enrolment has been increasing recently, manual grading of short-answer questions is a time-consuming and tedious process for instructors. In software engineering courses, assessments concern not just coding but many other aspects of software development such as system analysis, architecture design, software processes and operation methodologies …

Space Transformation For Open Set Recognition, Atefeh Mahdavi

Theses and Dissertations

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In OSR, only a limited number of known classes are available at the time of training the model and the possibility of unknown classes never seen at training time emerges in the test environment. In such a setting, the unknown classes and their risk should be considered in the algorithm. Such systems require not only to identify and discriminate instances that belong to the source domain (i.e., the seen known classes contained in the training dataset) but also to reject unknown …

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 …

Low-Resource Icd Coding Of Discharge Summaries, Ashton Williamson

All Theses

Medical coding is the process by which standardized medical codes are assigned to patient health records. This is a complex and challenging task that typically requires an expert human coder to review health records and assign codes from a classification system based on a standard set of rules. Considering the downstream use of these codes in statistical analysis, billing, and patient care, improving the accuracy and efficiency of the medical coding process through automation could have a far-reaching impact on the healthcare domain. Since health records typically consist of a large proportion of free-text documents, this problem has traditionally been …

Advancing Mobile Sensing In Dynamic Environments, Weichen Wang

Dartmouth College Ph.D Dissertations

This thesis presents a comprehensive exploration of enhancing mobile sensing capabilities to address various aspects of human behavior, mental health, personality, social functioning and beyond. We redesign the StudentLife app to improve its sensing efficiency and dependability, enabling support for multi-year-long studies. By adopting new app design, this study addresses the technical challenges of continuous sensing and enhances system robustness. The work is organized into several key studies that collectively aim to expand the scope of mobile sensing in diverse and complex environments.

The first study broadens the scope of mobile sensing to assess personality traits, exploring the potential of …

Supporting Text And Data Analysis Across Campus From The Academic Library, Amy Kirchhoff, Hejin Shin Phd

Digital Initiatives Symposium

The ability to comprehend and communicate with text-based data is essential to future success in academics and employment, as evidenced in a recent survey from Bloomberg Research Services which shows that nearly 97% of survey respondents now use data analytics in their companies and 58% consider data and text mining a business analytics tool (https://www.sas.com/content/dam/SAS/bp_de/doc/studie/ba-st-the-current-state-of-business-analytics-2317022.pdf). This has fueled a substantial growth in text analysis research (involving the use of technology to analyze un- and semi-structured text data for valuable insights, trends, and patterns) across disciplines and a corresponding demand on academic libraries to support text analysis pedagogy and text analysis …

A Discussion On Estimation Of The Best Constant For Spherical Restriction Inequalities, Hongyi Liu

Mathematics, Statistics, and Computer Science Honors Projects

The restriction conjecture asks for a meaningful restriction of the Fourier transform of a function to a sufficiently curved lower dimensional manifold. It then conjectures certain size estimates for this restriction in terms of the size of the original function. It has been proven in 2 dimensions, but it is open in dimensions 3 and larger, and is an area of much recent active effort. In our study, instead of aiming to prove the restriction conjecture, we target understanding its worst-case scenarios within known estimates. Specifically, we investigate the extension operator applied to antipodally concentrating profiles, examining the ratio of …

Maternal Care Utilization And Provision During The Covid-19 Pandemic: Voices From Minoritized Pregnant And Postpartum Women And Maternal Care Providers In Deep South, Ran Zhang, Tiffany Byrd, Shan Qiao Ph.D., Myriam E. Torres Phd, Msph, Xiaoming Li Ph.D., Jihong Liu Sc.D.

Faculty Publications

Background

The COVID-19 pandemic has significantly affected maternal care services especially for minoritized individuals, creating challenges for both service users (i.e., African American and Hispanic pregnant/postpartum women) and maternal care providers (MCPs). Guided by a socioecological framework, this study aims to investigate the experiences of African American and Hispanic pregnant and postpartum women, as well as MCPs, in accessing and providing maternal care services during the COVID-19 pandemic in the Deep South.

Methods

We conducted semi-structured interviews with 19 African American women, 20 Hispanic women, and 9 MCPs between January and August 2022. Participants were recruited from Obstetrics and Gynecology …

Russian Verbs Of Sound’S Web-Scraping Results From The A.A. Zalizniak Grammatical Dictionary And The Russian National Corpus. Multi-Dimensional Scaling Techniques And Visualization Strategies, John Simmons, Irina V. Ivliyeva

Graduate Student Research & Creative Works

This project aims to enhance web extraction techniques pertaining to a specific lexical-semantic group of Russian verbs of sounds, which undergo semantic modifications at the word-formation level (affixation). Additionally, it seeks to organize search results in a manner conducive to linguistic research using Multi-Dimensional Scaling (MDS) techniques and novel visualization strategies.

The primary objective in this phase of the research was to gather, consolidate, analyze, and present a comprehensive index of all forms of verbs of sound sourced from the A.A. Zalizniak Grammatical Dictionary of the Russian language, hyperlink each verbal form in this index with the Russian National Corpus …

Indigenous Communities Are Disproportionately Burdened By Environmental Contamination, Rae Cade, Danlin Yu, Kyle Whyte, Pankaj Lal, Cortni Borgerson

Student Research Symposium

Indigenous populations are disproportionately affected by both environmental pollution and health disparities resulting in mortality rates 60% higher than their white counterparts. Previous research has revealed instances of pollution from facilities which have caused severe health issues in Indigenous communities. Despite this, widespread geographic studies of the spatial correlation between Environmental Justice (EJ) and Indigenous populations remain lacking. This chapter examines whether Indigenous people in the northeastern United States are inequitably burdened by contamination. I find that Indigenous people are disproportionately exposed to 21 superfund contaminants, regardless of state or federal recognition. The sources of these contaminants varied, ranging from …

"Who Wrote The Epistle, God Only Knows": A Statistical Authorial Analysis Of Hebrews In Comparison With Pauline And Lukan Literature, Benjamin J. Erickson

Senior Honors Theses

The authorship of Hebrews has been a point of contention for scholars for the past two millennia. While the epistle is traditionally attributed to Paul, many scholars assert that it carries thematic, structural, and stylistic differences from the remainder of his extant epistles; therefore, many other possible authors have been proposed. Of these, only Luke has other New Testament writings. Therefore, this project conducts a statistical comparison of Hebrews to the Pauline and Lukan corpora using stylometric authorial analysis methods. This analysis demonstrates that Hebrews is stylistically closer to Lukan literature than Pauline (but not to a significant degree), and …

Ur-94 Emohydra: Multimodal Emotion Classification Using Heterogenous Modality Fusion, William A Stigall

C-Day Computing Showcase

Affective computing is a field of growing importance, as human society becomes more integrated with machines. Human feelings are both complex and multi-modal, expressed through various methods and nuances in behavior. In this work we introduce EmoHydra, a multi-modal model created through the fusion of three top-level models fine-tuned on text, vision, and speech respectively. Despite heterogenous heads performing well on the unseen data, as well as generalizing well to other benchmarks, logit concatenation proves to be ineffective at predicting Multimodal data, therefore we implement Multi-Head Attention as our fusion mechanism.

Gpr-16 Attention Driven Framework For Detecting Mental Illness Causes From Social Media, Abm Adnan Azmee, Dinesh Chowdary Attota, Francis E Nweke

C-Day Computing Showcase

Mental health is a critical aspect of our overall well-being. Mental illness refers to conditions that impact an individual's psychological state, resulting in considerable distress, and limitations in functioning day-to-day tasks. Due to the progress of technology, social media has merged as the platform, for individuals to share their thoughts and emotions. The psychological state of individuals can be accessed with the help of data from these platforms. However, it is challenging for conventional machine learning models to analyze the diverse linguistic contexts of social media data. In this work, we propose a novel attention-driven deep framework to overcome these …