Physical Sciences and Mathematics Commons^™

Detecting Fake News Using Ai, Gustavo Lambert, Lucas Schultz

ICT

This is a document that presents a strategic analysis of the project “Detecting Fake News using AI”. Developed as part of the BSc (Hons) in Computing in IT at CCT College Dublin. The goal is to analyse the potential advantages, exploiting the viability and the impact of applying Artificial intelligence to check, verify and alert about misinformation found and to answer the question “How can Artificial Intelligence be leveraged to accurately detect and combat fake news while ensuring data privacy and compliance with regulations?” and “To what extent can AI-driven misinformation detection help reduce the spread of fake news on …

Development Of A Deep Learning Model For Synthetic Vs. Real Image Classification Synthetic Vs. Real Image Classification, Bernardo Gandara, Ignacio Varela

ICT

The advancement of generative AI technologies has made it increasingly difficult to distinguish synthetic images from authentic ones. This capstone project addresses the challenge by developing a binary image classification model using deep learning techniques to differentiate AI-generated images from real photographs. Guided by the CRISP-DM methodology, we employed the DeepGuardDB dataset, consisting of 13,000 balanced image samples, evenly split between real and synthetic sources. We implemented and compared three Convolutional Neural Network (CNN) architectures through transfer learning, standardising input pipelines and integrating custom classification heads. Following a performance evaluation across multiple metrics, the best-performing model was selected for further …

Three Essays On Sustainability Economics, Hélène Flore Nguemgaing

Graduate Theses, Dissertations, and Problem Reports (ETD)

As global economies face increasing resource dependencies and supply chain challenges, it becomes essential to understand the vulnerabilities that threaten economic stability. This dissertation investigates three empirical issues in agribusiness and critical minerals using econometric models to estimate the following: 1) the impact of supply chain disruptions on stock market returns during COVID-19; 2) the extraction of rare earth elements from acid mine drainage treatment by investigating the impacts of ownership and legislation in West Virginia and Pennsylvania; 3) China-to�FOBb (Free-on-Board) price transmission in rare earth elements markets: a copula-based dynamic tail dependence analysis.

The first essay evaluates how events …

Controls On Longitudinal Stream Profile Evolution In Guadalupe Mountains National Park, Samuel Schoenmann, Lisa Tranel, Eric W. Peterson, Jonathan Boyd Thayn

Faculty Publications - Geography, Geology, and the Environment

Canyons in Guadalupe Mountains National Park are excellent locations to study the discrete boundary conditions that influence longitudinal channel profile evolution including climate, tectonics, hydrology, and lithology. The Guadalupe Mountain landscape records deep earth mantle processes in combination with surficial channel erosion and incision. Knickpoints and convex segments in longitudinal river profiles document impacts of climate change, tectonics, or surface processes. This study combines field observations with an analysis of longitudinal profile slopes and residual errors to evaluate how bedrock strength can be distinguished from features created by climate change, faulting, or subsidence in Pine Springs and McKittrick Canyons within …

Spectrum Of The Lakes: Using Satellite Remote Sensing To Unveil Water Color In Minnesota's Sentinel Lakes For Water Quality Monitoring, Andrew J. Dooley, Wondwosen M. Seyoum, Catherine M. O'Reilly

Faculty Publications - Geography, Geology, and the Environment

Traditional water quality monitoring methods often face limitations of equipment costs and labor demands, requiring innovative approaches to effectively assess the ecological health of inland lakes across vast areas. This research explores the application of free, publicly available water color chromaticity analysis for midcontinent lakes in Minnesota, USA. We examined water color variations in Minnesota’s Sentinel Lakes using Landsat 8 OLI data to analyze surface reflectance samples collected from the deepest area within each lake during the late summer, corresponding to peak annual insolation and trophic activity. The median dominant visible wavelength was used to characterize water color. Results indicate …

A Conversation On Fundamental Data Literacy Concepts For Undergraduate Education, Anna Bargagliotti, Wendy Pothier, David Homa, Arshia Mathus, Keith Mccormick, Paula Payton, Brian Wright

Mathematics, Statistics and Data Science Faculty Works

As the demand for data literacy grows, integrating foundational data literacy skills into undergraduate education becomes increasingly essential. This panel presents six core themes for cultivating data literacy among undergraduate students, addressing its interdisciplinary nature. Drawing upon the collective expertise of the group, literature research, case studies, and interviews, the panel explores the need for data literacy across various disciplines and the challenges of integrating it into higher education curricula. The proposed fundamental concepts include understanding data’s role in daily life, distinguishing between inference and prediction, recognizing the potential for misleading data, exploring ethical considerations, and honing communication and storytelling …

Bounded Compactness From G(E)Up, Jonas Mureika, Roberto Casadio, Ilim Irfan Çimdiker, Octavian Micu

Physics Faculty Works

We analyse how different Generalised Uncertainty Principles could place bounds on the compactness of self-gravitating systems. By considering existing experimental bounds on the relevant parameters, we conclude that the compactness of large astrophysical objects is bounded above by the inverse of the GUP parameter, which would naturally be of order one. Conversely, the existence of black holes imposes stronger bounds on those parameters.

Multitec: A Data-Driven Multimodal Short Video Detection Framework For Healthcare Misinformation On Tiktok, Lanyu Shang, Yang Zhang, Yawen Deng, Dong Wang

Computer Science Faculty Works

With the prevalence of social media and short video sharing platforms (e.g., TikTok, YouTube Shorts), the proliferation of healthcare misinformation has become a widespread and concerning issue that threatens public health and undermines trust in mass media. This paper focuses on an important problem of detecting multimodal healthcare misinformation in short videos on TikTok. Our objective is to accurately identify misleading healthcare information that is jointly conveyed by the visual, audio, and textual content within the TikTok short videos. Three critical challenges exist in solving our problem: i) how to effectively extract information from distractive and manipulated visual content in …

Hunting And Fishing Ceos: Environmental Plunderers Or Saviors?, Thomas Covington, Steve Widler, Keven Yost

Finance Faculty Works

CEOs who participate in hunting and fishing benefit by appreciating natural environments and permanently consuming natural resources. We examine whether CEOs who hunt and fish make different environmental decisions and find that firms led by CEOs who obtain the most hunting and fishing licenses have lower environmental performance as measured by MSCI-KLD. This effect is strongest in the environmental category of climate change but also extends to pollution, waste, and the protection of natural capital. Furthermore, firms led by CEOs with the most hunting and fishing licenses are significantly more likely to pay a regulatory settlement for an environmental regulatory …

Development And Evaluation Of Machine Learning Models For Early Pediatric Sepsis Prediction, Ancita M. Andrade

Browse all Theses and Dissertations

Sepsis is a leading cause of pediatric mortality, claiming more lives in the United States annually than all childhood cancers combined. Early identification in Emergency Departments (EDs) remains challenging, as the current Phoenix criteria establishes an updated international consensus definition for sepsis, however is not designed for use as a screening tool. This study aimed to develop predictive models identifying pediatric patients at risk of sepsis within 24 hours of admission. Multiple tree-based and deep learning models were trained utilizing clinical and laboratory data from the initial four hours of presentation. Both the LightGBM and LSTM architectures demonstrated superior performance, …

Wearable Sensor Data Analysis For Machine Learning-Based Detection Of Posture And Autonomic Responses, Chaitanya Vardhini Anumula

Browse all Theses and Dissertations

This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The physiological mechanisms underlying Iyengar yoga’s therapeutic effects remain under-explored at the granular, pose-level. Using data collected from 16 participants, this research evaluates whether machine learning models can distinguish between baseline, parasympathetic-dominant, and sympathetic-dominant states based on wrist-worn sensor data. The goals were to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively capture these changes. Participants performed a sequence of yoga poses while wearing synchronized sensors measuring electrodermal activity …

Impact Of Graph Structures For Rag Outcomes In Llms, Chris Davis Jaldi

Browse all Theses and Dissertations

Explainability, interpretability and adaptability (EIA) remain three central motivations for next-generation Artificial Intelligence (AI), especially as Large Language Models (LLMs) continue to engage with ever-increasing knowledge bodies. As the landscape pushes toward controllable agentic Retrieval-Augmented Generation (RAG) systems where AI agents engage in iterative, guided reasoning, a critical question arises as to the extent to which the knowledge design itself shapes these models' reasoning behavior. This work conducts a systematic evaluation of how different conceptualizations and representation of the identical knowledge affect an LLM's path-based reasoning capabilities. Through the introduction of controlled variations along graph structural complexity, linguistic and semantic …

Re-Parameterizing Adversarial Reprogramming In Low-Dimensional Subspace For Efficient Software Vulnerability Detection, Hootan Alavizadeh

Browse all Theses and Dissertations

Software vulnerabilities are a major cause of security breaches, making effective detection critical. Traditional learning-based methods require large datasets and significant computational resources, which are often impractical due to high annotation costs and data scarcity. To address this, we propose an innovative system, RearVul, which Re-parameterizes adversarial reprogramming in a low-dimensional subspace for software vulnerability detection. Unlike conventional approaches, RearVul repurposes a pre-trained classification model using adversarial reprogramming, enabling detection with minimal modifications. It learns a universal perturbation applied to program representations, preserving the original model’s feature extraction capabilities while adapting it to a new domain. Furthermore, we introduce a …

Subjective Readiness Forecasting Using Supervised Machine Learning And Wearable Device Data, Nathaniel Michael Weiland

Browse all Theses and Dissertations

Recent advances in wearable technology allow continuous monitoring of physiological and behavioral data, opening new opportunities for real-time assessments of readiness and well-being. However, creating predictive models that generalize across diverse users remains challenging, especially in high-stakes settings like the military, where preventable injuries, illnesses, and stress-related performance declines are frequent. This research assesses the feasibility of using supervised machine learning models trained on wearable device data to predict subjective readiness indicators—recovery, stress, injury, and illness. Data from over 10,000 users in the OHWS (Optimizing the Human Weapons System) program combined daily check ins with physiological metrics from Garmin, Polar, …

Computational Assessment Of Vitrimers Self-Healing For Renewable Energy And Aerospace Structures, Walaaeldin Mohamed Ahmed Derbala

Browse all Theses and Dissertations

Self-healing polymers, particularly vitrimers, are emerging as promising candidates in the development of advanced materials for renewable energy and aerospace structures. These materials exhibit dynamic covalent bond exchange mechanisms that enable reprocess ability, damage repair, and extended operational lifetime under harsh conditions. This study presents a density functional theory (DFT)-based computational investigation of the mechanistic pathways and energetics of bond exchange reactions in model vitrimer systems. We explore transition states, energy barriers, and thermodynamic features corresponding to associative and dissociative self-healing reactions in vitrimers. The study focuses on Diaminodiphenyl disulfide (AFD), a bifunctional molecule composed of two para-substituted aminophenyl rings …

Dataset Generation For Routing Policy Study In Ad Hoc Wireless Networks, Vishnu Vishnu Priya

Browse all Theses and Dissertations

Ad Hoc wireless networks, with their decentralized architecture and dynamic topology, present challenges in reliable and energy-efficient routing. While machine learning (ML) and reinforcement learning (RL) offer promising solutions, progress is limited by the lack of realistic, high-fidelity datasets. This research introduces a simulation-based framework for generating four diverse datasets representing combinations of node mobility (mobile vs. static) and spatial distribution (random vs. clustered). Each dataset captures critical metrics such as Signal-to-Interference-plus-Noise Ratio (SINR), bottleneck rate, and power consumption across multi-hop paths. A lookahead-based greedy routing algorithm with scenario-aware power control is implemented to emulate practical behavior. Supervised ML models, …

Isometric Centroid Encoder (Ice) And Synthetic Data Generation Approaches For Biological Datasets, Prathyusha Kanakamalla

Browse all Theses and Dissertations

This thesis addressed two main challenges in biological data analysis: structure-preserving dimensionality reduction and synthetic data generation for small sample datasets. I proposed the Isometric Centroid Encoder (ICE), a supervised dimensionality reduction method that preserves pairwise distances between class centroids during dimension reduction. Unlike existing methods like Centroid Encoder and Super Encoder, ICE explicitly maintains geometric relationships between biological classes, achieving nearly perfect structure preservation at C dimensions (where C equals the number of classes) with strong performance even in 2D and 3D spaces. Additionally, I compared three generative models (VAE, LSH-GAN, and scDiffusion) for synthetic data generation on small …

Hydrogen Storage Density And Adsorption Energy Barriers On Li-Decorated Bc3 Nanosheet, Sri Venkat Pavan Upasi

Browse all Theses and Dissertations

Hydrogen is considered an emerging carrier of clean energy with renewable capabilities. Widespread hydrogen energy utilization necessitates efficient storage strategies. Functionalized nanomaterials, such as Li-decorated BC3 nanosheets, are among the primary candidate materials for hydrogen storage. This research investigates the feasibility of hydrogen storage by estimating energy barriers and their dependence on storage density on Li-decorated BC3 nanosheet. Density functional theory (DFT) simulations provide estimates of adsorption energies and saddle points for hydrogen storage and compare corresponding reaction rates. The results are expected to help us understand the advantages and possible shortcomings of hydrogen storage on such nanomaterials.

Biosensing Applications Of Thz Rotational Spectroscopy: Sensing And Analysis Of Exogenous And Endogenous Compounds In Exhaled Breath, Daniel J. Tyree

Browse all Theses and Dissertations

Exhaled human breath contains a wealth of volatile molecular species which bear an imprint of compounds dissolved in blood. Assessing trace amounts of these species in exhaled breath requires a highly sensitive and selective method. Terahertz (THz) rotational spectroscopy satisfies these needs by detecting numerous and narrow, molecule specific spectral features with feature intensity dependent on the quantity of absorbing molecules, molecular structure, and experimental parameters. Expanding the applicability of THz sensing to biological gases requires systems to measure this spectral data, reliable analysis of the spectra, and demonstration of the utility of biological data extracted from the spectra. To …

Ultrasonic Sensor-Based Sound Synthesis Using Raspberry Pi Pico W, Niraj Jaishwal

Williams Honors College, Honors Research Projects

At the intersection of Human Computer Interaction and digital art, this project transforms simple motion into musical expression. It explores an interactive real-time sound synthesis system using ultrasonic sensors to generate continuous audio. The objective is to design a system that maps physical distances into musical parameters such as pitch and amplitude, which will create a responsive audio environment. Two ultrasonic sensors are used in combination with the Raspberry Pi Pico W microcontroller running CircuitPython and Adafruit Audio Hat for real-time sound output. One sensor controls the pitch of the generated tone, while the other controls volume. This enables expressive …

Pca Text Sentiment Analysis Tool, Luke Gegick

Williams Honors College, Honors Research Projects

This project applies principal component analysis (PCA) to sentiment analysis of text to identify complex emotional responses from plain text. Existing sentiment analysis tools often rely on large language models or struggle to achieve high accuracy when processing large collections of short inputs, such as social media comments. By contrast, this project uses PCA as a lightweight, mathematically grounded alternative that can scale efficiently while still capturing meaningful emotional structure in text data.

PCA has shown strong effectiveness in text analysis, particularly when supported by a sufficiently large dataset and a robust preprocessing pipeline. To create consistent, information-rich input vectors, …

Improving The Accuracy Of Neighborhood Median Pixel Method (Nmpm) In Classifying Landsat-8 Oli Images By Optimizing The Scoring System’S Point Values, Abraham T. Magpantay, Proceso L. Fernandez Jr

Department of Information Systems & Computer Science Faculty Publications

The Neighborhood Median Pixel Method has previously been introduced as an image processing technique in remote sensing, developed to classify Landsat-8 OLI satellite image pixels into categories of vegetation, water, and built-up areas. This method relies on a lookup table based on the median pixel values within a pixel’s neighborhood and a scoring system that assigns point values for classification. While a 9x9 neighborhood size was originally proposed, a succeeding study suggested a 13x13 neighborhood for better classification accuracy. This study focuses on refining the scoring system used in the Neighborhood Median Pixel Method, particularly the original set of arbitrary …

A Unionid Mussel Biodiversity Hotspot Experiencing Unexplained Declines: Evaluating The Influence Of Chemical Stressors Using Caged Juveniles, W. Aaron Wilson, Christine Bergeron, Jennifer Archambault, Jason M. Unrine, Jess Jones, Braven Beaty, Damian Shea, Peter R. Lazaro, Jody L. Callihan, Jennifer J. Rogers

Plant and Soil Sciences Faculty Publications

Unionid mussel populations in a section of the Clinch River in Virginia, USA, has declined substantially, but the causes of the decline remain unknown. To investigate this zone of decline (ZOD), we deployed juvenile freshwater mussels (Villosa iris in 2012 and Lampsilis fasciola in 2013) in both cages and silos at sites within the Clinch River System. We analyzed mussel tissues for trace element and organic contaminant concentrations, shells for trace elements, and environmental media (total water, dissolved water, particulate sediment, and bedload sediment) for both inorganic and organic contaminants. We found a few differences between mussels deployed in cages …

Personalized Physics Learning Through Ai: Insights From Problem Generation, Chatbot Dialogues, And Intelligent Tutoring Systems, Atharva Dange

Physics Dissertations - Archive

Artificial intelligence (AI) is poised to transform science education, yet questions remain on how best to integrate these technologies into teaching and learning. This dissertation investigates the use of AI-driven tools in university physics courses through three complementary studies. In the first study, a generative language model (ChatGPT) was used to create novel physics homework problems aligned with course objectives. Analysis showed that, after expert vetting, AI-generated questions can foster higher-order problem-solving and reduce student reliance on solution memorization, though careful instructor oversight is required to ensure accuracy. The second study embedded an AI chatbot as a learning aid in …

Development And Application Of Gpu Based Monte Carlo Simulation Techniques In Radiation Medicine, Satzhan Sitmukhambetov

Physics Dissertations - Archive

Cancer remains a significant public health challenge, with treatments like radiation therapy forming a cornerstone of modern care. To address this challenge, advanced computer simulations can improve radiotherapy in two primary ways. From one hand, mechanistic simulations help elucidate the fundamental radiobiological working principles, which could contribute to the clinical advancements from a bottom-up framework. On the other hand, modality simulations could help design better clinical systems with better detection and therapeutic capabilities. This research enhances these critical simulation tools by introducing two significant developments.

First, this work introduces a metaphase DNA model into a microscopic Monte Carlo simulation framework …

Uncertainty In Solar Wind Propagation: An Analysis Of L1 To Earth Variability And The Implications For Geospace Modeling In Space Weather Operations, Espen T. Fredrick

Physics Dissertations - Archive

As humanity's technological dependence grows, so does its vulnerability to space weather. Space weather describes solar-driven phenomena in the near-Earth space environment and their terrestrial effects. Many of these effects occur due to the interaction of the solar wind and Earth's magnetosphere. The solar wind originates at the solar corona and carries solar plasma and magnetic field outward through the solar system. This magnetic field, known as the interplanetary magnetic field (IMF) during transit, can undergo magnetic reconnection with Earth's geomagnetic field when oppositely aligned field lines converge. This process transfers energy into Earth's magnetosphere, driving space weather phenomena.

Space …

Characterizing The Earth's Magnetosheath With In Situ Measurements, Hector A. Salinas

Physics Dissertations - Archive

Earth’s magnetosheath is a region of shocked plasma that mediates energy and momentum transfer from the solar wind to the magnetosphere. The dynamics and thus the plasma structures of this region are highly dependent on upstream solar wind conditions. As such, the region is often characterized as a turbulent environment, with the most intense periods of turbulence occurring often under quasi-parallel bow shock conditions. This magnetosheath turbulence displays as variable and large-scale fluctuations with in-situ measurements. Given that turbulence is a characteristic feature of the magnetosheath, this dissertation asks two questions: (1) How are plasma structures inside the sheath affected …

On The Orbital Dynamics Of Exoplanets, Exomoons, And Submoons, Shaan Dharmesh Patel

Physics Dissertations - Archive

Although exoplanet detection has long been a central focus in astronomy, growing interest in exomoons has highlighted the increasing need for theoretical frameworks to interpret emerging candidates. Furthermore, while submoons, natural satellites orbiting moons, are not presently observed in the Solar System and remain speculative (e.g., the hypothesized past submoon of Saturn’s Iapetus), their existence is plausible within the context of the complex and diverse architectures now identified across planetary and stellar systems. We develop a generalized framework to assess the orbital stability of exomoons and submoons through comprehensive N-body simulations incorporating both three-body dynamics and tidal interactions, with the …

Study Of Structural Changes In Bone From Osteogenesis Imperfecta Using Positron Annihilation Lifetime Spectroscopy, Pablo Kohlmann Garcia, Richard Vallery

Student Summer Scholars Manuscripts

Osteogenesis Imperfecta (OI), commonly referred to as Brittle Bone Disease, is a genetic disorder that results in increased bone fragility. There are many known variations, with four of them being the most common and each with a different level of severity. However, the exact causes of OI and their molecular and structural effects on bones are largely unknown. To investigate the relationship between nanoscale bone structure and disease severity, this research investigates OI by using positron annihilation lifetime spectroscopy (PALS) to understand whether normal bone structure differs from OI-infected bones. Using this method, positrons are directed towards mice’s bones, forming …

Polarimetric Capture And Differentiable Rendering, Katherine Anne Salesin

Dartmouth College Ph.D Dissertations

Many scientific fields rely on the capture and modeling of light to extract underlying information about the world. Often, more information can be extracted by capturing more about the nature of the light, such as its spectral shape or polarization state. While polarization is a relatively unexplored topic in computer graphics, when used in tandem with other recent advancements in the field it has enormous potential to improve both forward and inverse models in other scientific disciplines. We demonstrate this potential in two distinct settings in this thesis.

First, we apply the capture of polarized light to an inverse problem …